@article{JoseClementeMorenoOmranianSaezetal.2019, author = {Jose Clemente-Moreno, Maria and Omranian, Nooshin and Saez, Patricia and Maria Figueroa, Carlos and Del-Saz, Nestor and Elso, Mhartyn and Poblete, Leticia and Orf, Isabel and Cuadros-Inostroza, Alvaro and Cavieres, Lohengrin and Bravo, Leon and Fernie, Alisdair R. and Ribas-Carbo, Miquel and Flexas, Jaume and Nikoloski, Zoran and Brotman, Yariv and Gago, Jorge}, title = {Cytochrome respiration pathway and sulphur metabolism sustain stress tolerance to low temperature in the Antarctic species Colobanthus quitensis}, series = {New phytologist : international journal of plant science}, volume = {225}, journal = {New phytologist : international journal of plant science}, number = {2}, publisher = {Wiley}, address = {Hoboken}, issn = {0028-646X}, doi = {10.1111/nph.16167}, pages = {754 -- 768}, year = {2019}, abstract = {Understanding the strategies employed by plant species that live in extreme environments offers the possibility to discover stress tolerance mechanisms. We studied the physiological, antioxidant and metabolic responses to three temperature conditions (4, 15, and 23 degrees C) of Colobanthus quitensis (CQ), one of the only two native vascular species in Antarctica. We also employed Dianthus chinensis (DC), to assess the effects of the treatments in a non-Antarctic species from the same family. Using fused LASSO modelling, we associated physiological and biochemical antioxidant responses with primary metabolism. This approach allowed us to highlight the metabolic pathways driving the response specific to CQ. Low temperature imposed dramatic reductions in photosynthesis (up to 88\%) but not in respiration (sustaining rates of 3.0-4.2 mu mol CO2 m(-2) s(-1)) in CQ, and no change in the physiological stress parameters was found. Its notable antioxidant capacity and mitochondrial cytochrome respiratory activity (20 and two times higher than DC, respectively), which ensure ATP production even at low temperature, was significantly associated with sulphur-containing metabolites and polyamines. Our findings potentially open new biotechnological opportunities regarding the role of antioxidant compounds and respiratory mechanisms associated with sulphur metabolism in stress tolerance strategies to low temperature.}, language = {en} } @misc{BaslerFernieNikoloski2018, author = {Basler, Georg and Fernie, Alisdair R. and Nikoloski, Zoran}, title = {Advances in metabolic flux analysis toward genome-scale profiling of higher organisms}, series = {Bioscience reports : communications and reviews in molecular and cellular biology}, volume = {38}, journal = {Bioscience reports : communications and reviews in molecular and cellular biology}, publisher = {Portland Press (London)}, address = {London}, issn = {0144-8463}, doi = {10.1042/BSR20170224}, pages = {11}, year = {2018}, abstract = {Methodological and technological advances have recently paved the way for metabolic flux profiling in higher organisms, like plants. However, in comparison with omics technologies, flux profiling has yet to provide comprehensive differential flux maps at a genome-scale and in different cell types, tissues, and organs. Here we highlight the recent advances in technologies to gather metabolic labeling patterns and flux profiling approaches. We provide an opinion of how recent local flux profiling approaches can be used in conjunction with the constraint-based modeling framework to arrive at genome-scale flux maps. In addition, we point at approaches which use metabolomics data without introduction of label to predict either non-steady state fluxes in a time-series experiment or flux changes in different experimental scenarios. The combination of these developments allows an experimentally feasible approach for flux-based large-scale systems biology studies.}, language = {en} } @article{SmithDupontMcCarthyetal.2019, author = {Smith, Sarah R. and Dupont, Chris L. and McCarthy, James K. and Broddrick, Jared T. and Obornik, Miroslav and Horak, Ales and F{\"u}ssy, Zolt{\´a}n and Cihlar, Jaromir and Kleessen, Sabrina and Zheng, Hong and McCrow, John P. and Hixson, Kim K. and Araujo, Wagner L. and Nunes-Nesi, Adriano and Fernie, Alisdair R. and Nikoloski, Zoran and Palsson, Bernhard O. and Allen, Andrew E.}, title = {Evolution and regulation of nitrogen flux through compartmentalized metabolic networks in a marine diatom}, series = {Nature Communications}, volume = {10}, journal = {Nature Communications}, publisher = {Nature Publ. Group}, address = {London}, issn = {2041-1723}, doi = {10.1038/s41467-019-12407-y}, pages = {14}, year = {2019}, abstract = {Diatoms outcompete other phytoplankton for nitrate, yet little is known about the mechanisms underpinning this ability. Genomes and genome-enabled studies have shown that diatoms possess unique features of nitrogen metabolism however, the implications for nutrient utilization and growth are poorly understood. Using a combination of transcriptomics, proteomics, metabolomics, fluxomics, and flux balance analysis to examine short-term shifts in nitrogen utilization in the model pennate diatom in Phaeodactylum tricornutum, we obtained a systems-level understanding of assimilation and intracellular distribution of nitrogen. Chloroplasts and mitochondria are energetically integrated at the critical intersection of carbon and nitrogen metabolism in diatoms. Pathways involved in this integration are organelle-localized GS-GOGAT cycles, aspartate and alanine systems for amino moiety exchange, and a split-organelle arginine biosynthesis pathway that clarifies the role of the diatom urea cycle. This unique configuration allows diatoms to efficiently adjust to changing nitrogen status, conferring an ecological advantage over other phytoplankton taxa.}, language = {en} } @article{AngeleskaNikoloski2019, author = {Angeleska, Angela and Nikoloski, Zoran}, title = {Coherent network partitions}, series = {Discrete applied mathematics}, volume = {266}, journal = {Discrete applied mathematics}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0166-218X}, doi = {10.1016/j.dam.2019.02.048}, pages = {283 -- 290}, year = {2019}, abstract = {Graph clustering is widely applied in the analysis of cellular networks reconstructed from large-scale data or obtained from experimental evidence. Here we introduce a new type of graph clustering based on the concept of coherent partition. A coherent partition of a graph G is a partition of the vertices of G that yields only disconnected subgraphs in the complement of G. The coherence number of G is then the size of the smallest edge cut inducing a coherent partition. A coherent partition of G is optimal if the size of the inducing edge cut is the coherence number of G. Given a graph G, we study coherent partitions and the coherence number in connection to (bi)clique partitions and the (bi)clique cover number. We show that the problem of finding the coherence number is NP-hard, but is of polynomial time complexity for trees. We also discuss the relation between coherent partitions and prominent graph clustering quality measures.}, language = {en} } @article{RobainaEstevezDalosoZhangetal.2017, author = {Robaina-Estevez, Semidan and Daloso, Danilo M. and Zhang, Youjun and Fernie, Alisdair R. and Nikoloski, Zoran}, title = {Resolving the central metabolism of Arabidopsis guard cells}, series = {Scientific reports}, volume = {7}, journal = {Scientific reports}, publisher = {Nature Publ. Group}, address = {London}, issn = {2045-2322}, doi = {10.1038/s41598-017-07132-9}, pages = {1913 -- 1932}, year = {2017}, abstract = {Photosynthesis and water use efficiency, key factors affecting plant growth, are directly controlled by microscopic and adjustable pores in the leaf-the stomata. The size of the pores is modulated by the guard cells, which rely on molecular mechanisms to sense and respond to environmental changes. It has been shown that the physiology of mesophyll and guard cells differs substantially. However, the implications of these differences to metabolism at a genome-scale level remain unclear. Here, we used constraint-based modeling to predict the differences in metabolic fluxes between the mesophyll and guard cells of Arabidopsis thaliana by exploring the space of fluxes that are most concordant to cell-type-specific transcript profiles. An independent C-13-labeling experiment using isolated mesophyll and guard cells was conducted and provided support for our predictions about the role of the Calvin-Benson cycle in sucrose synthesis in guard cells. The combination of in silico with in vivo analyses indicated that guard cells have higher anaplerotic CO2 fixation via phosphoenolpyruvate carboxylase, which was demonstrated to be an important source of malate. Beyond highlighting the metabolic differences between mesophyll and guard cells, our findings can be used in future integrated modeling of multicellular plant systems and their engineering towards improved growth.}, language = {en} } @misc{BreuerNowakIvakovetal.2017, author = {Breuer, David and Nowak, Jacqueline and Ivakov, Alexander and Somssich, Marc and Persson, Staffan and Nikoloski, Zoran}, title = {System-wide organization of actin cytoskeleton determines organelle transport in hypocotyl plant cells}, series = {Proceedings of the National Academy of Sciences of the United States of America}, volume = {114}, journal = {Proceedings of the National Academy of Sciences of the United States of America}, publisher = {National Acad. of Sciences}, address = {Washington}, issn = {0027-8424}, doi = {10.1073/pnas.1712371114}, pages = {E6732 -- E6732}, year = {2017}, language = {en} } @article{deAbreueLimaWillmitzerNikoloski2018, author = {de Abreu e Lima, Francisco Anastacio and Willmitzer, Lothar and Nikoloski, Zoran}, title = {Classification-driven framework to predict maize hybrid field performance from metabolic profiles of young parental roots}, series = {PLoS one}, volume = {13}, journal = {PLoS one}, number = {4}, publisher = {PLoS}, address = {San Fransisco}, issn = {1932-6203}, doi = {10.1371/journal.pone.0196038}, pages = {16}, year = {2018}, abstract = {Maize (Zea mays L.) is a staple food whose production relies on seed stocks that largely comprise hybrid varieties. Therefore, knowledge about the molecular determinants of hybrid performance (HP) in the field can be used to devise better performing hybrids to address the demands for sustainable increase in yield. Here, we propose and test a classification-driven framework that uses metabolic profiles from in vitro grown young roots of parental lines from the Dent x Flint maize heterotic pattern to predict field HP. We identify parental analytes that best predict the metabolic inheritance patterns in 328 hybrids. We then demonstrate that these analytes are also predictive of field HP (0.64 >= r >= 0.79) and discriminate hybrids of good performance (accuracy of 87.50\%). Therefore, our approach provides a cost-effective solution for hybrid selection programs.}, language = {en} } @article{SchwahnNikoloski2018, author = {Schwahn, Kevin and Nikoloski, Zoran}, title = {Data reduction approaches for dissecting transcriptional effects on metabolism}, series = {Frontiers in plant science}, volume = {9}, journal = {Frontiers in plant science}, publisher = {Frontiers Research Foundation}, address = {Lausanne}, issn = {1664-462X}, doi = {10.3389/fpls.2018.00538}, pages = {12}, year = {2018}, abstract = {The availability of high-throughput data from transcriptomics and metabolomics technologies provides the opportunity to characterize the transcriptional effects on metabolism. Here we propose and evaluate two computational approaches rooted in data reduction techniques to identify and categorize transcriptional effects on metabolism by combining data on gene expression and metabolite levels. The approaches determine the partial correlation between two metabolite data profiles upon control of given principal components extracted from transcriptomics data profiles. Therefore, they allow us to investigate both data types with all features simultaneously without doing preselection of genes. The proposed approaches allow us to categorize the relation between pairs of metabolites as being under transcriptional or post-transcriptional regulation. The resulting classification is compared to existing literature and accumulated evidence about regulatory mechanism of reactions and pathways in the cases of Escherichia coil, Saccharomycies cerevisiae, and Arabidopsis thaliana.}, language = {en} } @article{RodriguezCubillosTongAlseekhetal.2018, author = {Rodriguez Cubillos, Andres Eduardo and Tong, Hao and Alseekh, Saleh and de Abreu e Lima, Francisco Anastacio and Yu, Jing and Fernie, Alisdair R. and Nikoloski, Zoran and Laitinen, Roosa A. E.}, title = {Inheritance patterns in metabolism and growth in diallel crosses of Arabidopsis thaliana from a single growth habitat}, series = {Heredity}, volume = {120}, journal = {Heredity}, number = {5}, publisher = {Nature Publ. Group}, address = {London}, issn = {0018-067X}, doi = {10.1038/s41437-017-0030-5}, pages = {463 -- 473}, year = {2018}, abstract = {Metabolism is a key determinant of plant growth and modulates plant adaptive responses. Increased metabolic variation due to heterozygosity may be beneficial for highly homozygous plants if their progeny is to respond to sudden changes in the habitat. Here, we investigate the extent to which heterozygosity contributes to the variation in metabolism and size of hybrids of Arabidopsis thaliana whose parents are from a single growth habitat. We created full diallel crosses among seven parents, originating from Southern Germany, and analysed the inheritance patterns in primary and secondary metabolism as well as in rosette size in situ. In comparison to primary metabolites, compounds from secondary metabolism were more variable and showed more pronounced non-additive inheritance patterns which could be attributed to epistasis. In addition, we showed that glucosinolates, among other secondary metabolites, were positively correlated with a proxy for plant size. Therefore, our study demonstrates that heterozygosity in local A. thaliana population generates metabolic variation and may impact several tasks directly linked to metabolism.}, language = {en} } @article{HansenMeyerFerrarietal.2017, author = {Hansen, Bjoern Oest and Meyer, Etienne H. and Ferrari, Camilla and Vaid, Neha and Movahedi, Sara and Vandepoele, Klaas and Nikoloski, Zoran and Mutwil, Marek}, title = {Ensemble gene function prediction database reveals genes important for complex I formation in Arabidopsis thaliana}, series = {New phytologist : international journal of plant science}, volume = {217}, journal = {New phytologist : international journal of plant science}, number = {4}, publisher = {Wiley}, address = {Hoboken}, issn = {0028-646X}, doi = {10.1111/nph.14921}, pages = {1521 -- 1534}, year = {2017}, abstract = {Recent advances in gene function prediction rely on ensemble approaches that integrate results from multiple inference methods to produce superior predictions. Yet, these developments remain largely unexplored in plants. We have explored and compared two methods to integrate 10 gene co-function networks for Arabidopsis thaliana and demonstrate how the integration of these networks produces more accurate gene function predictions for a larger fraction of genes with unknown function. These predictions were used to identify genes involved in mitochondrial complex I formation, and for five of them, we confirmed the predictions experimentally. The ensemble predictions are provided as a user-friendly online database, EnsembleNet. The methods presented here demonstrate that ensemble gene function prediction is a powerful method to boost prediction performance, whereas the EnsembleNet database provides a cutting-edge community tool to guide experimentalists.}, language = {en} } @article{deAbreueLimaLiWenetal.2018, author = {de Abreu e Lima, Francisco Anastacio and Li, Kun and Wen, Weiwei and Yan, Jianbing and Nikoloski, Zoran and Willmitzer, Lothar and Brotman, Yariv}, title = {Unraveling lipid metabolism in maize with time-resolved multi-omics data}, series = {The plant journal}, volume = {93}, journal = {The plant journal}, number = {6}, publisher = {Wiley}, address = {Hoboken}, issn = {0960-7412}, doi = {10.1111/tpj.13833}, pages = {1102 -- 1115}, year = {2018}, abstract = {Maize is the cereal crop with the highest production worldwide, and its oil is a key energy resource. Improving the quantity and quality of maize oil requires a better understanding of lipid metabolism. To predict the function of maize genes involved in lipid biosynthesis, we assembled transcriptomic and lipidomic data sets from leaves of B73 and the high-oil line By804 in two distinct time-series experiments. The integrative analysis based on high-dimensional regularized regression yielded lipid-transcript associations indirectly validated by Gene Ontology and promoter motif enrichment analyses. The co-localization of lipid-transcript associations using the genetic mapping of lipid traits in leaves and seedlings of a B73 x By804 recombinant inbred line population uncovered 323 genes involved in the metabolism of phospholipids, galactolipids, sulfolipids and glycerolipids. The resulting association network further supported the involvement of 50 gene candidates in modulating levels of representatives from multiple acyl-lipid classes. Therefore, the proposed approach provides high-confidence candidates for experimental testing in maize and model plant species.}, language = {en} } @misc{KleessenNikoloski2012, author = {Kleessen, Sabrina and Nikoloski, Zoran}, title = {Dynamic regulatory on/off minimization for biological systems under internal temporal perturbations}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, number = {852}, issn = {1866-8372}, doi = {10.25932/publishup-43112}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-431128}, pages = {15}, year = {2012}, abstract = {Background: Flux balance analysis (FBA) together with its extension, dynamic FBA, have proven instrumental for analyzing the robustness and dynamics of metabolic networks by employing only the stoichiometry of the included reactions coupled with adequately chosen objective function. In addition, under the assumption of minimization of metabolic adjustment, dynamic FBA has recently been employed to analyze the transition between metabolic states. Results: Here, we propose a suite of novel methods for analyzing the dynamics of (internally perturbed) metabolic networks and for quantifying their robustness with limited knowledge of kinetic parameters. Following the biochemically meaningful premise that metabolite concentrations exhibit smooth temporal changes, the proposed methods rely on minimizing the significant fluctuations of metabolic profiles to predict the time-resolved metabolic state, characterized by both fluxes and concentrations. By conducting a comparative analysis with a kinetic model of the Calvin-Benson cycle and a model of plant carbohydrate metabolism, we demonstrate that the principle of regulatory on/off minimization coupled with dynamic FBA can accurately predict the changes in metabolic states. Conclusions: Our methods outperform the existing dynamic FBA-based modeling alternatives, and could help in revealing the mechanisms for maintaining robustness of dynamic processes in metabolic networks over time.}, language = {en} } @misc{ChildsNikoloskiMayetal.2009, author = {Childs, Liam H. and Nikoloski, Zoran and May, Patrick and Walther, Dirk}, title = {Identification and classification of ncRNA molecules using graph properties}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-45192}, year = {2009}, abstract = {The study of non-coding RNA genes has received increased attention in recent years fuelled by accumulating evidence that larger portions of genomes than previously acknowledged are transcribed into RNA molecules of mostly unknown function, as well as the discovery of novel non-coding RNA types and functional RNA elements. Here, we demonstrate that specific properties of graphs that represent the predicted RNA secondary structure reflect functional information. We introduce a computational algorithm and an associated web-based tool (GraPPLE) for classifying non-coding RNA molecules as functional and, furthermore, into Rfam families based on their graph properties. Unlike sequence-similarity-based methods and covariance models, GraPPLE is demonstrated to be more robust with regard to increasing sequence divergence, and when combined with existing methods, leads to a significant improvement of prediction accuracy. Furthermore, graph properties identified as most informative are shown to provide an understanding as to what particular structural features render RNA molecules functional. Thus, GraPPLE may offer a valuable computational filtering tool to identify potentially interesting RNA molecules among large candidate datasets.}, language = {en} } @misc{SzymanskiJozefczukNikoloskietal.2009, author = {Szymanski, Jedrzej and Jozefczuk, Szymon and Nikoloski, Zoran and Selbig, Joachim and Nikiforova, Victoria and Catchpole, Gareth and Willmitzer, Lothar}, title = {Stability of metabolic correlations under changing environmental conditions in Escherichia coli : a systems approach}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-45253}, year = {2009}, abstract = {Background: Biological systems adapt to changing environments by reorganizing their cellula r and physiological program with metabolites representing one important response level. Different stresses lead to both conserved and specific responses on the metabolite level which should be reflected in the underl ying metabolic network. Methodology/Principal Findings: Starting from experimental data obtained by a GC-MS based high-throughput metabolic profiling technology we here develop an approach that: (1) extracts network representations from metabolic conditiondependent data by using pairwise correlations, (2) determines the sets of stable and condition-dependent correlations based on a combination of statistical significance and homogeneity tests, and (3) can identify metabolites related to the stress response, which goes beyond simple ob servation s about the changes of metabolic concentrations. The approach was tested with Escherichia colias a model organism observed under four different environmental stress conditions (cold stress, heat stress, oxidative stress, lactose diau xie) and control unperturbed conditions. By constructing the stable network component, which displays a scale free topology and small-world characteristics, we demonstrated that: (1) metabolite hubs in this reconstructed correlation networks are significantly enriched for those contained in biochemical networks such as EcoCyc, (2) particular components of the stable network are enriched for functionally related biochemical path ways, and (3) ind ependently of the response scale, based on their importance in the reorganization of the cor relation network a set of metabolites can be identified which represent hypothetical candidates for adjusting to a stress-specific response. Conclusions/Significance: Network-based tools allowed the identification of stress-dependent and general metabolic correlation networks. This correlation-network-ba sed approach does not rely on major changes in concentration to identify metabolites important for st ress adaptation, but rather on the changes in network properties with respect to metabolites. This should represent a useful complementary technique in addition to more classical approaches.}, language = {en} } @article{KuekenGennermannNikoloski2020, author = {K{\"u}ken, Anika and Gennermann, Kristin and Nikoloski, Zoran}, title = {Characterization of maximal enzyme catalytic rates in central metabolism of Arabidopsis thaliana}, series = {The plant journal}, volume = {103}, journal = {The plant journal}, number = {6}, publisher = {Wiley}, address = {Oxford}, issn = {0960-7412}, doi = {10.1111/tpj.14890}, pages = {2168 -- 2177}, year = {2020}, abstract = {Availability of plant-specific enzyme kinetic data is scarce, limiting the predictive power of metabolic models and precluding identification of genetic factors of enzyme properties. Enzyme kinetic data are measuredin vitro, often under non-physiological conditions, and conclusions elicited from modeling warrant caution. Here we estimate maximalin vivocatalytic rates for 168 plant enzymes, including photosystems I and II, cytochrome-b6f complex, ATP-citrate synthase, sucrose-phosphate synthase as well as enzymes from amino acid synthesis with previously undocumented enzyme kinetic data in BRENDA. The estimations are obtained by integrating condition-specific quantitative proteomics data, maximal rates of selected enzymes, growth measurements fromArabidopsis thalianarosette with and fluxes through canonical pathways in a constraint-based model of leaf metabolism. In comparison to findings inEscherichia coli, we demonstrate weaker concordance between the plant-specificin vitroandin vivoenzyme catalytic rates due to a low degree of enzyme saturation. This is supported by the finding that concentrations of nicotinamide adenine dinucleotide (phosphate), adenosine triphosphate and uridine triphosphate, calculated based on our maximalin vivocatalytic rates, and available quantitative metabolomics data are below reportedKMvalues and, therefore, indicate undersaturation of respective enzymes. Our findings show that genome-wide profiling of enzyme kinetic properties is feasible in plants, paving the way for understanding resource allocation.}, language = {en} } @misc{KuekenSommerYanevaRoderetal.2018, author = {K{\"u}ken, Anika and Sommer, Frederik and Yaneva-Roder, Liliya and Mackinder, Luke C.M. and H{\"o}hne, Melanie and Geimer, Stefan and Jonikas, Martin C. and Schroda, Michael and Stitt, Mark and Nikoloski, Zoran and Mettler-Altmann, Tabea}, title = {Effects of microcompartmentation on flux distribution and metabolic pools in Chlamydomonas reinhardtii chloroplasts}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {1122}, issn = {1866-8372}, doi = {10.25932/publishup-44635}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-446358}, pages = {25}, year = {2018}, abstract = {Cells and organelles are not homogeneous but include microcompartments that alter the spatiotemporal characteristics of cellular processes. The effects of microcompartmentation on metabolic pathways are however difficult to study experimentally. The pyrenoid is a microcompartment that is essential for a carbon concentrating mechanism (CCM) that improves the photosynthetic performance of eukaryotic algae. Using Chlamydomonas reinhardtii, we obtained experimental data on photosynthesis, metabolites, and proteins in CCM-induced and CCM-suppressed cells. We then employed a computational strategy to estimate how fluxes through the Calvin-Benson cycle are compartmented between the pyrenoid and the stroma. Our model predicts that ribulose-1,5-bisphosphate (RuBP), the substrate of Rubisco, and 3-phosphoglycerate (3PGA), its product, diffuse in and out of the pyrenoid, respectively, with higher fluxes in CCM-induced cells. It also indicates that there is no major diffusional barrier to metabolic flux between the pyrenoid and stroma. Our computational approach represents a stepping stone to understanding microcompartmentalized CCM in other organisms.}, language = {en} } @article{OmranianNikoloski2022, author = {Omranian, Sara and Nikoloski, Zoran}, title = {CUBCO+: prediction of protein complexes based on min-cut network partitioning into biclique spanned subgraphs}, series = {Applied Network Science}, volume = {7}, journal = {Applied Network Science}, publisher = {Springer International Publishing}, address = {Cham}, issn = {2364-8228}, doi = {10.1007/s41109-022-00508-5}, pages = {12}, year = {2022}, abstract = {High-throughput proteomics approaches have resulted in large-scale protein-protein interaction (PPI) networks that have been employed for the prediction of protein complexes. However, PPI networks contain false-positive as well as false-negative PPIs that affect the protein complex prediction algorithms. To address this issue, here we propose an algorithm called CUBCO+ that: (1) employs GO semantic similarity to retain only biologically relevant interactions with a high similarity score, (2) based on link prediction approaches, scores the false-negative edges, and (3) incorporates the resulting scores to predict protein complexes. Through comprehensive analyses with PPIs from Escherichia coli, Saccharomyces cerevisiae, and Homo sapiens, we show that CUBCO+ performs as well as the approaches that predict protein complexes based on recently introduced graph partitions into biclique spanned subgraphs and outperforms the other state-of-the-art approaches. Moreover, we illustrate that in combination with GO semantic similarity, CUBCO+ enables us to predict more accurate protein complexes in 36\% of the cases in comparison to CUBCO as its predecessor.}, language = {en} } @article{ScheunemannBradyNikoloski2018, author = {Scheunemann, Michael and Brady, Siobhan M. and Nikoloski, Zoran}, title = {Integration of large-scale data for extraction of integrated Arabidopsis root cell-type specific models}, series = {Scientific reports}, volume = {8}, journal = {Scientific reports}, publisher = {Nature Publ. Group}, address = {London}, issn = {2045-2322}, doi = {10.1038/s41598-018-26232-8}, pages = {15}, year = {2018}, abstract = {Plant organs consist of multiple cell types that do not operate in isolation, but communicate with each other to maintain proper functions. Here, we extract models specific to three developmental stages of eight root cell types or tissue layers in Arabidopsis thaliana based on a state-of-the-art constraint-based modeling approach with all publicly available transcriptomics and metabolomics data from this system to date. We integrate these models into a multi-cell root model which we investigate with respect to network structure, distribution of fluxes, and concordance to transcriptomics and proteomics data. From a methodological point, we show that the coupling of tissue-specific models in a multi-tissue model yields a higher specificity of the interconnected models with respect to network structure and flux distributions. We use the extracted models to predict and investigate the flux of the growth hormone indole-3-actetate and its antagonist, trans-Zeatin, through the root. While some of predictions are in line with experimental evidence, constraints other than those coming from the metabolic level may be necessary to replicate the flow of indole-3-actetate from other simulation studies. Therefore, our work provides the means for data-driven multi-tissue metabolic model extraction of other Arabidopsis organs in the constraint-based modeling framework.}, language = {en} } @article{PandeyYuOmranianetal.2019, author = {Pandey, Prashant K. and Yu, Jing and Omranian, Nooshin and Alseekh, Saleh and Vaid, Neha and Fernie, Alisdair R. and Nikoloski, Zoran and Laitinen, Roosa A. E.}, title = {Plasticity in metabolism underpins local responses to nitrogen in Arabidopsis thaliana populations}, series = {Plant Direct}, volume = {3}, journal = {Plant Direct}, number = {11}, publisher = {John Wiley \& sonst LTD}, address = {Chichester}, issn = {2475-4455}, doi = {10.1002/pld3.186}, pages = {6}, year = {2019}, abstract = {Nitrogen (N) is central for plant growth, and metabolic plasticity can provide a strategy to respond to changing N availability. We showed that two local A. thaliana populations exhibited differential plasticity in the compounds of photorespiratory and starch degradation pathways in response to three N conditions. Association of metabolite levels with growth-related and fitness traits indicated that controlled plasticity in these pathways could contribute to local adaptation and play a role in plant evolution.}, language = {en} } @article{deAbreueLimaLeifelsNikoloski2018, author = {de Abreu e Lima, Francisco Anastacio and Leifels, Lydia and Nikoloski, Zoran}, title = {Regression-based modeling of complex plant traits based on metabolomics data}, series = {Plant Metabolomics}, volume = {1778}, journal = {Plant Metabolomics}, publisher = {Humana Press Inc.}, address = {New York}, isbn = {978-1-4939-7819-9}, issn = {1064-3745}, doi = {10.1007/978-1-4939-7819-9_23}, pages = {321 -- 327}, year = {2018}, abstract = {Bridging metabolomics with plant phenotypic responses is challenging. Multivariate analyses account for the existing dependencies among metabolites, and regression models in particular capture such dependencies in search for association with a given trait. However, special care should be undertaken with metabolomics data. Here we propose a modeling workflow that considers all caveats imposed by such large data sets.}, language = {en} } @article{NunesNesiAlseekhdeOliveiraSilvaetal.2019, author = {Nunes-Nesi, Adriano and Alseekh, Saleh and de Oliveira Silva, Franklin Magnum and Omranian, Nooshin and Lichtenstein, Gabriel and Mirnezhad, Mohammad and Romero Gonzalez, Roman R. and Sabio y Garcia, Julia and Conte, Mariana and Leiss, Kirsten A. and Klinkhamer, Peter Gerardus Leonardus and Nikoloski, Zoran and Carrari, Fernando and Fernie, Alisdair R.}, title = {Identification and characterization of metabolite quantitative trait loci in tomato leaves and comparison with those reported for fruits and seeds}, series = {Metabolomics}, volume = {15}, journal = {Metabolomics}, number = {46}, publisher = {Springer}, address = {New York}, issn = {1573-3882}, doi = {10.1007/s11306-019-1503-8}, pages = {13}, year = {2019}, abstract = {IntroductionTo date, most studies of natural variation and metabolite quantitative trait loci (mQTL) in tomato have focused on fruit metabolism, leaving aside the identification of genomic regions involved in the regulation of leaf metabolism.ObjectiveThis study was conducted to identify leaf mQTL in tomato and to assess the association of leaf metabolites and physiological traits with the metabolite levels from other tissues.MethodsThe analysis of components of leaf metabolism was performed by phenotypying 76 tomato ILs with chromosome segments of the wild species Solanum pennellii in the genetic background of a cultivated tomato (S. lycopersicum) variety M82. The plants were cultivated in two different environments in independent years and samples were harvested from mature leaves of non-flowering plants at the middle of the light period. The non-targeted metabolite profiling was obtained by gas chromatography time-of-flight mass spectrometry (GC-TOF-MS). With the data set obtained in this study and already published metabolomics data from seed and fruit, we performed QTL mapping, heritability and correlation analyses.ResultsChanges in metabolite contents were evident in the ILs that are potentially important with respect to stress responses and plant physiology. By analyzing the obtained data, we identified 42 positive and 76 negative mQTL involved in carbon and nitrogen metabolism.ConclusionsOverall, these findings allowed the identification of S. lycopersicum genome regions involved in the regulation of leaf primary carbon and nitrogen metabolism, as well as the association of leaf metabolites with metabolites from seeds and fruits.}, language = {en} } @misc{LaitinenNikoloski2018, author = {Laitinen, Roosa A. E. and Nikoloski, Zoran}, title = {Genetic basis of plasticity in plants}, series = {Journal of experimental botany}, volume = {70}, journal = {Journal of experimental botany}, number = {3}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {0022-0957}, doi = {10.1093/jxb/ery404}, pages = {739 -- 745}, year = {2018}, abstract = {The ability of an organism to change its phenotype in response to different environments, termed plasticity, is a particularly important characteristic to enable sessile plants to adapt to rapid changes in their surroundings. Plasticity is a quantitative trait that can provide a fitness advantage and mitigate negative effects due to environmental perturbations. Yet, its genetic basis is not fully understood. Alongside technological limitations, the main challenge in studying plasticity has been the selection of suitable approaches for quantification of phenotypic plasticity. Here, we propose a categorization of the existing quantitative measures of phenotypic plasticity into nominal and relative approaches. Moreover, we highlight the recent advances in the understanding of the genetic architecture underlying phenotypic plasticity in plants. We identify four pillars for future research to uncover the genetic basis of phenotypic plasticity, with emphasis on development of computational approaches and theories. These developments will allow us to perform specific experiments to validate the causal genes for plasticity and to discover their role in plant fitness and evolution.}, language = {en} } @article{FerrariProostJanowskietal.2019, author = {Ferrari, Camilla and Proost, Sebastian and Janowski, Marcin Andrzej and Becker, J{\"o}rg and Nikoloski, Zoran and Bhattacharya, Debashish and Price, Dana and Tohge, Takayuki and Bar-Even, Arren and Fernie, Alisdair R. and Stitt, Mark and Mutwil, Marek}, title = {Kingdom-wide comparison reveals the evolution of diurnal gene expression in Archaeplastida}, series = {Nature Communications}, volume = {10}, journal = {Nature Communications}, publisher = {Nature Publ. Group}, address = {London}, issn = {2041-1723}, doi = {10.1038/s41467-019-08703-2}, pages = {13}, year = {2019}, abstract = {Plants have adapted to the diurnal light-dark cycle by establishing elaborate transcriptional programs that coordinate many metabolic, physiological, and developmental responses to the external environment. These transcriptional programs have been studied in only a few species, and their function and conservation across algae and plants is currently unknown. We performed a comparative transcriptome analysis of the diurnal cycle of nine members of Archaeplastida, and we observed that, despite large phylogenetic distances and dramatic differences in morphology and lifestyle, diurnal transcriptional programs of these organisms are similar. Expression of genes related to cell division and the majority of biological pathways depends on the time of day in unicellular algae but we did not observe such patterns at the tissue level in multicellular land plants. Hence, our study provides evidence for the universality of diurnal gene expression and elucidates its evolutionary history among different photosynthetic eukaryotes.}, language = {en} } @article{KuekenNikoloski2019, author = {K{\"u}ken, Anika and Nikoloski, Zoran}, title = {Computational Approaches to Design and Test Plant Synthetic Metabolic Pathways}, series = {Plant physiology : an international journal devoted to physiology, biochemistry, cellular and molecular biology, biophysics and environmental biology of plants}, volume = {179}, journal = {Plant physiology : an international journal devoted to physiology, biochemistry, cellular and molecular biology, biophysics and environmental biology of plants}, number = {3}, publisher = {American Society of Plant Physiologists}, address = {Rockville}, issn = {0032-0889}, doi = {10.1104/pp.18.01273}, pages = {894 -- 906}, year = {2019}, abstract = {Successfully designed and implemented plant-specific synthetic metabolic pathways hold promise to increase crop yield and nutritional value. Advances in synthetic biology have already demonstrated the capacity to design artificial biological pathways whose behavior can be predicted and controlled in microbial systems. However, the transfer of these advances to model plants and crops faces the lack of characterization of plant cellular pathways and increased complexity due to compartmentalization and multicellularity. Modern computational developments provide the means to test the feasibility of plant synthetic metabolic pathways despite gaps in the accumulated knowledge of plant metabolism. Here, we provide a succinct systematic review of optimization-based and retrobiosynthesis approaches that can be used to design and in silico test synthetic metabolic pathways in large-scale plant context-specific metabolic models. In addition, by surveying the existing case studies, we highlight the challenges that these approaches face when applied to plants. Emphasis is placed on understanding the effect that metabolic designs can have on native metabolism, particularly with respect to metabolite concentrations and thermodynamics of biochemical reactions. In addition, we discuss the computational developments that may help to transform the identified challenges into opportunities for plant synthetic biology.}, language = {en} } @article{YuWuNowaketal.2019, author = {Yu, Yanjun and Wu, Shenjie and Nowak, Jacqueline and Wang, Guangda and Han, Libo and Feng, Zhidi and Mendrinna, Amelie and Ma, Yinping and Wang, Huan and Zhang, Xiaxia and Tian, Juan and Dong, Li and Nikoloski, Zoran and Persson, Staffan and Kong, Zhaosheng}, title = {Live-cell imaging of the cytoskeleton in elongating cotton fibres}, series = {Nature plants}, volume = {5}, journal = {Nature plants}, number = {5}, publisher = {Nature Publ. Group}, address = {London}, issn = {2055-026X}, doi = {10.1038/s41477-019-0418-8}, pages = {498 -- 504}, year = {2019}, abstract = {Cotton (Gossypium hirsutum) fibres consist of single cells that grow in a highly polarized manner, assumed to be controlled by the cytoskeleton(1-3). However, how the cytoskeletal organization and dynamics underpin fibre development remains unexplored. Moreover, it is unclear whether cotton fibres expand via tip growth or diffuse growth(2-4). We generated stable transgenic cotton plants expressing fluorescent markers of the actin and microtubule cytoskeleton. Live-cell imaging revealed that elongating cotton fibres assemble a cortical filamentous actin network that extends along the cell axis to finally form actin strands with closed loops in the tapered fibre tip. Analyses of F-actin network properties indicate that cotton fibres have a unique actin organization that blends features of both diffuse and tip growth modes. Interestingly, typical actin organization and endosomal vesicle aggregation found in tip-growing cell apices were not observed in fibre tips. Instead, endomembrane compartments were evenly distributed along the elongating fibre cells and moved bi-directionally along the fibre shank to the fibre tip. Moreover, plus-end tracked microtubules transversely encircled elongating fibre shanks, reminiscent of diffusely growing cells. Collectively, our findings indicate that cotton fibres elongate via a unique tip-biased diffuse growth mode.}, language = {en} } @article{SulpiceNikoloskiTschoepetal.2013, author = {Sulpice, Ronan and Nikoloski, Zoran and Tschoep, Hendrik and Antonio, Carla and Kleessen, Sabrina and Larhlimi, Abdelhalim and Selbig, Joachim and Ishihara, Hirofumi and Gibon, Yves and Fernie, Alisdair R. and Stitt, Mark}, title = {Impact of the Carbon and Nitrogen Supply on Relationships and Connectivity between Metabolism and Biomass in a Broad Panel of Arabidopsis Accessions(1[W][OA])}, series = {Plant physiology : an international journal devoted to physiology, biochemistry, cellular and molecular biology, biophysics and environmental biology of plants}, volume = {162}, journal = {Plant physiology : an international journal devoted to physiology, biochemistry, cellular and molecular biology, biophysics and environmental biology of plants}, number = {1}, publisher = {American Society of Plant Physiologists}, address = {Rockville}, issn = {0032-0889}, doi = {10.1104/pp.112.210104}, pages = {347 -- 363}, year = {2013}, abstract = {Natural genetic diversity provides a powerful tool to study the complex interrelationship between metabolism and growth. Profiling of metabolic traits combined with network-based and statistical analyses allow the comparison of conditions and identification of sets of traits that predict biomass. However, it often remains unclear why a particular set of metabolites is linked with biomass and to what extent the predictive model is applicable beyond a particular growth condition. A panel of 97 genetically diverse Arabidopsis (Arabidopsis thaliana) accessions was grown in near-optimal carbon and nitrogen supply, restricted carbon supply, and restricted nitrogen supply and analyzed for biomass and 54 metabolic traits. Correlation-based metabolic networks were generated from the genotype-dependent variation in each condition to reveal sets of metabolites that show coordinated changes across accessions. The networks were largely specific for a single growth condition. Partial least squares regression from metabolic traits allowed prediction of biomass within and, slightly more weakly, across conditions (cross-validated Pearson correlations in the range of 0.27-0.58 and 0.21-0.51 and P values in the range of <0.001-<0.13 and <0.001-<0.023, respectively). Metabolic traits that correlate with growth or have a high weighting in the partial least squares regression were mainly condition specific and often related to the resource that restricts growth under that condition. Linear mixed-model analysis using the combined metabolic traits from all growth conditions as an input indicated that inclusion of random effects for the conditions improves predictions of biomass. Thus, robust prediction of biomass across a range of conditions requires condition-specific measurement of metabolic traits to take account of environment-dependent changes of the underlying networks.}, language = {en} } @article{ApeltBreuerNikoloskietal.2015, author = {Apelt, Federico and Breuer, David and Nikoloski, Zoran and Stitt, Mark and Kragler, Friedrich}, title = {Phytotyping(4D): a light-field imaging system for non-invasive and accurate monitoring of spatio-temporal plant growth}, series = {The plant journal}, volume = {82}, journal = {The plant journal}, number = {4}, publisher = {Wiley-Blackwell}, address = {Hoboken}, issn = {0960-7412}, doi = {10.1111/tpj.12833}, pages = {693 -- 706}, year = {2015}, abstract = {Integrative studies of plant growth require spatially and temporally resolved information from high-throughput imaging systems. However, analysis and interpretation of conventional two-dimensional images is complicated by the three-dimensional nature of shoot architecture and by changes in leaf position over time, termed hyponasty. To solve this problem, Phytotyping(4D) uses a light-field camera that simultaneously provides a focus image and a depth image, which contains distance information about the object surface. Our automated pipeline segments the focus images, integrates depth information to reconstruct the three-dimensional architecture, and analyses time series to provide information about the relative expansion rate, the timing of leaf appearance, hyponastic movement, and shape for individual leaves and the whole rosette. Phytotyping(4D) was calibrated and validated using discs of known sizes, and plants tilted at various orientations. Information from this analysis was integrated into the pipeline to allow error assessment during routine operation. To illustrate the utility of Phytotyping(4D), we compare diurnal changes in Arabidopsis thaliana wild-type Col-0 and the starchless pgm mutant. Compared to Col-0, pgm showed very low relative expansion rate in the second half of the night, a transiently increased relative expansion rate at the onset of light period, and smaller hyponastic movement including delayed movement after dusk, both at the level of the rosette and individual leaves. Our study introduces light-field camera systems as a tool to accurately measure morphological and growth-related features in plants. Significance Statement Phytotyping(4D) is a non-invasive and accurate imaging system that combines a 3D light-field camera with an automated pipeline, which provides validated measurements of growth, movement, and other morphological features at the rosette and single-leaf level. In a case study in which we investigated the link between starch and growth, we demonstrated that Phytotyping(4D) is a key step towards bridging the gap between phenotypic observations and the rich genetic and metabolic knowledge.}, language = {en} } @article{KuekenSommerYanevaRoderetal.2018, author = {K{\"u}ken, Anika and Sommer, Frederik and Yaneva-Roder, Liliya and Mackinder, Luke C. M. and Hoehne, Melanie and Geimer, Stefan and Jonikas, Martin C. and Schroda, Michael and Stitt, Mark and Nikoloski, Zoran and Mettler-Altmann, Tabea}, title = {Effects of microcompartmentation on flux distribution and metabolic pools in Chlamydomonas reinhardtii chloroplasts}, series = {eLife}, volume = {7}, journal = {eLife}, publisher = {eLife Sciences Publications}, address = {Cambridge}, issn = {2050-084X}, doi = {10.7554/eLife.37960}, pages = {23}, year = {2018}, abstract = {Cells and organelles are not homogeneous but include microcompartments that alter the spatiotemporal characteristics of cellular processes. The effects of microcompartmentation on metabolic pathways are however difficult to study experimentally. The pyrenoid is a microcompartment that is essential for a carbon concentrating mechanism (CCM) that improves the photosynthetic performance of eukaryotic algae. Using Chlamydomonas reinhardtii, we obtained experimental data on photosynthesis, metabolites, and proteins in CCM-induced and CCM-suppressed cells. We then employed a computational strategy to estimate how fluxes through the Calvin-Benson cycle are compartmented between the pyrenoid and the stroma. Our model predicts that ribulose-1,5-bisphosphate (RuBP), the substrate of Rubisco, and 3-phosphoglycerate (3PGA), its product, diffuse in and out of the pyrenoid, respectively, with higher fluxes in CCM-induced cells. It also indicates that there is no major diffusional barrier to metabolic flux between the pyrenoid and stroma. Our computational approach represents a stepping stone to understanding microcompartmentalized CCM in other organisms.}, language = {en} } @article{AnnunziataApeltCarilloetal.2017, author = {Annunziata, Maria Grazia and Apelt, Federico and Carillo, Petronia and Krause, Ursula and Feil, Regina and Mengin, Virginie and Lauxmann, Martin A. and Koehl, Karin and Nikoloski, Zoran and Stitt, Mark and Lunn, John Edward}, title = {Getting back to nature: a reality check for experiments in controlled environments}, series = {Journal of experimental botany}, volume = {68}, journal = {Journal of experimental botany}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {0022-0957}, doi = {10.1093/jxb/erx220}, pages = {4463 -- 4477}, year = {2017}, abstract = {Irradiance from sunlight changes in a sinusoidal manner during the day, with irregular fluctuations due to clouds, and light-dark shifts at dawn and dusk are gradual. Experiments in controlled environments typically expose plants to constant irradiance during the day and abrupt light-dark transitions. To compare the effects on metabolism of sunlight versus artificial light regimes, Arabidopsis thaliana plants were grown in a naturally illuminated greenhouse around the vernal equinox, and in controlled environment chambers with a 12-h photoperiod and either constant or sinusoidal light profiles, using either white fluorescent tubes or light-emitting diodes (LEDs) tuned to a sunlight-like spectrum as the light source. Rosettes were sampled throughout a 24-h diurnal cycle for metabolite analysis. The diurnal metabolite profiles revealed that carbon and nitrogen metabolism differed significantly between sunlight and artificial light conditions. The variability of sunlight within and between days could be a factor underlying these differences. Pairwise comparisons of the artificial light sources (fluorescent versus LED) or the light profiles (constant versus sinusoidal) showed much smaller differences. The data indicate that energy-efficient LED lighting is an acceptable alternative to fluorescent lights, but results obtained from plants grown with either type of artificial lighting might not be representative of natural conditions.}, language = {en} } @article{TongNikoloski2020, author = {Tong, Hao and Nikoloski, Zoran}, title = {Machine learning approaches for crop improvement}, series = {Journal of plant physiology : biochemistry, physiology, molecular biology and biotechnology of plants}, volume = {257}, journal = {Journal of plant physiology : biochemistry, physiology, molecular biology and biotechnology of plants}, publisher = {Elsevier}, address = {M{\"u}nchen}, issn = {0176-1617}, doi = {10.1016/j.jplph.2020.153354}, pages = {13}, year = {2020}, abstract = {Highly efficient and accurate selection of elite genotypes can lead to dramatic shortening of the breeding cycle in major crops relevant for sustaining present demands for food, feed, and fuel. In contrast to classical approaches that emphasize the need for resource-intensive phenotyping at all stages of artificial selection, genomic selection dramatically reduces the need for phenotyping. Genomic selection relies on advances in machine learning and the availability of genotyping data to predict agronomically relevant phenotypic traits. Here we provide a systematic review of machine learning approaches applied for genomic selection of single and multiple traits in major crops in the past decade. We emphasize the need to gather data on intermediate phenotypes, e.g. metabolite, protein, and gene expression levels, along with developments of modeling techniques that can lead to further improvements of genomic selection. In addition, we provide a critical view of factors that affect genomic selection, with attention to transferability of models between different environments. Finally, we highlight the future aspects of integrating high-throughput molecular phenotypic data from omics technologies with biological networks for crop improvement.}, language = {en} } @article{ZakharovaNikoloskiKoseska2013, author = {Zakharova, A. and Nikoloski, Zoran and Koseska, Aneta}, title = {Dimensionality reduction of bistable biological systems}, series = {Bulletin of mathematical biology : official journal of the Society for Mathematical Biology}, volume = {75}, journal = {Bulletin of mathematical biology : official journal of the Society for Mathematical Biology}, number = {3}, publisher = {Springer}, address = {New York}, issn = {0092-8240}, doi = {10.1007/s11538-013-9807-8}, pages = {373 -- 392}, year = {2013}, abstract = {Time hierarchies, arising as a result of interactions between system's components, represent a ubiquitous property of dynamical biological systems. In addition, biological systems have been attributed switch-like properties modulating the response to various stimuli across different organisms and environmental conditions. Therefore, establishing the interplay between these features of system dynamics renders itself a challenging question of practical interest in biology. Existing methods are suitable for systems with one stable steady state employed as a well-defined reference. In such systems, the characterization of the time hierarchies has already been used for determining the components that contribute to the dynamics of biological systems. However, the application of these methods to bistable nonlinear systems is impeded due to their inherent dependence on the reference state, which in this case is no longer unique. Here, we extend the applicability of the reference-state analysis by proposing, analyzing, and applying a novel method, which allows investigation of the time hierarchies in systems exhibiting bistability. The proposed method is in turn used in identifying the components, other than reactions, which determine the systemic dynamical properties. We demonstrate that in biological systems of varying levels of complexity and spanning different biological levels, the method can be effectively employed for model simplification while ensuring preservation of qualitative dynamical properties (i.e., bistability). Finally, by establishing a connection between techniques from nonlinear dynamics and multivariate statistics, the proposed approach provides the basis for extending reference-based analysis to bistable systems.}, language = {en} } @article{NikoloskiMaySelbig2009, author = {Nikoloski, Zoran and May, Patrick and Selbig, Joachim}, title = {A new network model explains the evolution of plant-specific metabolic networks}, issn = {1095-6433}, doi = {10.1016/j.cbpa.2009.04.567}, year = {2009}, language = {en} } @article{NeigenfindGrimbsNikoloski2013, author = {Neigenfind, Jost and Grimbs, Sergio and Nikoloski, Zoran}, title = {On the relation between reactions and complexes of (bio)chemical reaction networks}, series = {Journal of theoretical biology}, volume = {317}, journal = {Journal of theoretical biology}, number = {2}, publisher = {Elsevier}, address = {London}, issn = {0022-5193}, doi = {10.1016/j.jtbi.2012.10.016}, pages = {359 -- 365}, year = {2013}, abstract = {Robustness of biochemical systems has become one of the central questions in systems biology although it is notoriously difficult to formally capture its multifaceted nature. Maintenance of normal system function depends not only on the stoichiometry of the underlying interrelated components, but also on the multitude of kinetic parameters. Invariant flux ratios, obtained within flux coupling analysis, as well as invariant complex ratios, derived within chemical reaction network theory, can characterize robust properties of a system at steady state. However, the existing formalisms for the description of these invariants do not provide full characterization as they either only focus on the flux-centric or the concentration-centric view. Here we develop a novel mathematical framework which combines both views and thereby overcomes the limitations of the classical methodologies. Our unified framework will be helpful in analyzing biologically important system properties.}, language = {en} } @article{ToepferCaldanaGrimbsetal.2013, author = {T{\"o}pfer, Nadine and Caldana, Camila and Grimbs, Sergio and Willmitzer, Lothar and Fernie, Alisdair R. and Nikoloski, Zoran}, title = {Integration of genome-scale modeling and transcript profiling reveals metabolic pathways underlying light and temperature acclimation in arabidopsis}, series = {The plant cell}, volume = {25}, journal = {The plant cell}, number = {4}, publisher = {American Society of Plant Physiologists}, address = {Rockville}, issn = {1040-4651}, doi = {10.1105/tpc.112.108852}, pages = {1197 -- 1211}, year = {2013}, abstract = {Understanding metabolic acclimation of plants to challenging environmental conditions is essential for dissecting the role of metabolic pathways in growth and survival. As stresses involve simultaneous physiological alterations across all levels of cellular organization, a comprehensive characterization of the role of metabolic pathways in acclimation necessitates integration of genome-scale models with high-throughput data. Here, we present an integrative optimization-based approach, which, by coupling a plant metabolic network model and transcriptomics data, can predict the metabolic pathways affected in a single, carefully controlled experiment. Moreover, we propose three optimization-based indices that characterize different aspects of metabolic pathway behavior in the context of the entire metabolic network. We demonstrate that the proposed approach and indices facilitate quantitative comparisons and characterization of the plant metabolic response under eight different light and/or temperature conditions. The predictions of the metabolic functions involved in metabolic acclimation of Arabidopsis thaliana to the changing conditions are in line with experimental evidence and result in a hypothesis about the role of homocysteine-to-Cys interconversion and Asn biosynthesis. The approach can also be used to reveal the role of particular metabolic pathways in other scenarios, while taking into consideration the entirety of characterized plant metabolism.}, language = {en} } @article{HempelKoseskaNikoloski2013, author = {Hempel, Sabrina and Koseska, Aneta and Nikoloski, Zoran}, title = {Data-driven reconstruction of directed networks}, series = {The European physical journal : B, Condensed matter and complex systems}, volume = {86}, journal = {The European physical journal : B, Condensed matter and complex systems}, number = {6}, publisher = {Springer}, address = {New York}, issn = {1434-6028}, doi = {10.1140/epjb/e2013-31111-8}, pages = {17}, year = {2013}, abstract = {We investigate the properties of a recently introduced asymmetric association measure, called inner composition alignment (IOTA), aimed at inferring regulatory links (couplings). We show that the measure can be used to determine the direction of coupling, detect superfluous links, and to account for autoregulation. In addition, the measure can be extended to infer the type of regulation (positive or negative). The capabilities of IOTA to correctly infer couplings together with their directionality are compared against Kendall's rank correlation for time series of different lengths, particularly focussing on biological examples. We demonstrate that an extended version of the measure, bidirectional inner composition alignment (biIOTA), increases the accuracy of the network reconstruction for short time series. Finally, we discuss the applicability of the measure to infer couplings in chaotic systems.}, language = {en} } @article{BaslerEbenhoehSelbigetal.2011, author = {Basler, Georg and Ebenhoeh, Oliver and Selbig, Joachim and Nikoloski, Zoran}, title = {Mass-balanced randomization of metabolic networks}, series = {Bioinformatics}, volume = {27}, journal = {Bioinformatics}, number = {10}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btr145}, pages = {1397 -- 1403}, year = {2011}, abstract = {Motivation: Network-centered studies in systems biology attempt to integrate the topological properties of biological networks with experimental data in order to make predictions and posit hypotheses. For any topology-based prediction, it is necessary to first assess the significance of the analyzed property in a biologically meaningful context. Therefore, devising network null models, carefully tailored to the topological and biochemical constraints imposed on the network, remains an important computational problem. Results: We first review the shortcomings of the existing generic sampling scheme-switch randomization-and explain its unsuitability for application to metabolic networks. We then devise a novel polynomial-time algorithm for randomizing metabolic networks under the (bio)chemical constraint of mass balance. The tractability of our method follows from the concept of mass equivalence classes, defined on the representation of compounds in the vector space over chemical elements. We finally demonstrate the uniformity of the proposed method on seven genome-scale metabolic networks, and empirically validate the theoretical findings. The proposed method allows a biologically meaningful estimation of significance for metabolic network properties.}, language = {en} } @article{KleessenNikoloski2012, author = {Kleessen, Sabrina and Nikoloski, Zoran}, title = {Dynamic regulatory on/off minimization for biological systems under internal temporal perturbations}, series = {BMC systems biology}, volume = {6}, journal = {BMC systems biology}, publisher = {BioMed Central}, address = {London}, issn = {1752-0509}, doi = {10.1186/1752-0509-6-16}, pages = {13}, year = {2012}, abstract = {Background: Flux balance analysis (FBA) together with its extension, dynamic FBA, have proven instrumental for analyzing the robustness and dynamics of metabolic networks by employing only the stoichiometry of the included reactions coupled with adequately chosen objective function. In addition, under the assumption of minimization of metabolic adjustment, dynamic FBA has recently been employed to analyze the transition between metabolic states. Results: Here, we propose a suite of novel methods for analyzing the dynamics of (internally perturbed) metabolic networks and for quantifying their robustness with limited knowledge of kinetic parameters. Following the biochemically meaningful premise that metabolite concentrations exhibit smooth temporal changes, the proposed methods rely on minimizing the significant fluctuations of metabolic profiles to predict the time-resolved metabolic state, characterized by both fluxes and concentrations. By conducting a comparative analysis with a kinetic model of the Calvin-Benson cycle and a model of plant carbohydrate metabolism, we demonstrate that the principle of regulatory on/off minimization coupled with dynamic FBA can accurately predict the changes in metabolic states. Conclusions: Our methods outperform the existing dynamic FBA-based modeling alternatives, and could help in revealing the mechanisms for maintaining robustness of dynamic processes in metabolic networks over time.}, language = {en} } @article{KleessenAraujoFernieetal.2012, author = {Kleessen, Sabrina and Araujo, Wagner L. and Fernie, Alisdair R. and Nikoloski, Zoran}, title = {Model-based Confirmation of Alternative Substrates of Mitochondrial Electron Transport Chain}, series = {The journal of biological chemistry}, volume = {287}, journal = {The journal of biological chemistry}, number = {14}, publisher = {American Society for Biochemistry and Molecular Biology}, address = {Bethesda}, issn = {0021-9258}, doi = {10.1074/jbc.M111.310383}, pages = {11122 -- 11131}, year = {2012}, abstract = {Background: There are alternative substrates to the mitochondrial respiration. Results: Data-driven model-based analysis renders predictions of alternative substrates to the mitochondrial respiration. Conclusion: Metabolomics data in conjunction with flux-based models can discriminate among hypotheses based on enzymology alone. Significance: This analysis provides a basic framework for in silico studies of alternative pathways in metabolism.}, language = {en} } @article{HempelKoseskaKurthsetal.2011, author = {Hempel, Stefan and Koseska, Aneta and Kurths, J{\"u}rgen and Nikoloski, Zoran}, title = {Inner composition alignment for inferring directed networks from short time series}, series = {Physical review letters}, volume = {107}, journal = {Physical review letters}, number = {5}, publisher = {American Physical Society}, address = {College Park}, issn = {0031-9007}, doi = {10.1103/PhysRevLett.107.054101}, pages = {4}, year = {2011}, abstract = {Identifying causal links (couplings) is a fundamental problem that facilitates the understanding of emerging structures in complex networks. We propose and analyze inner composition alignment-a novel, permutation-based asymmetric association measure to detect regulatory links from very short time series, currently applied to gene expression. The measure can be used to infer the direction of couplings, detect indirect (superfluous) links, and account for autoregulation. Applications to the gene regulatory network of E. coli are presented.}, language = {en} } @article{HempelKoseskaNikoloskietal.2011, author = {Hempel, Sabrina and Koseska, Aneta and Nikoloski, Zoran and Kurths, J{\"u}rgen}, title = {Unraveling gene regulatory networks from time-resolved gene expression data - a measures comparison study}, series = {BMC bioinformatics}, volume = {12}, journal = {BMC bioinformatics}, number = {1}, publisher = {BioMed Central}, address = {London}, issn = {1471-2105}, doi = {10.1186/1471-2105-12-292}, pages = {26}, year = {2011}, abstract = {Background: Inferring regulatory interactions between genes from transcriptomics time-resolved data, yielding reverse engineered gene regulatory networks, is of paramount importance to systems biology and bioinformatics studies. Accurate methods to address this problem can ultimately provide a deeper insight into the complexity, behavior, and functions of the underlying biological systems. However, the large number of interacting genes coupled with short and often noisy time-resolved read-outs of the system renders the reverse engineering a challenging task. Therefore, the development and assessment of methods which are computationally efficient, robust against noise, applicable to short time series data, and preferably capable of reconstructing the directionality of the regulatory interactions remains a pressing research problem with valuable applications. Results: Here we perform the largest systematic analysis of a set of similarity measures and scoring schemes within the scope of the relevance network approach which are commonly used for gene regulatory network reconstruction from time series data. In addition, we define and analyze several novel measures and schemes which are particularly suitable for short transcriptomics time series. We also compare the considered 21 measures and 6 scoring schemes according to their ability to correctly reconstruct such networks from short time series data by calculating summary statistics based on the corresponding specificity and sensitivity. Our results demonstrate that rank and symbol based measures have the highest performance in inferring regulatory interactions. In addition, the proposed scoring scheme by asymmetric weighting has shown to be valuable in reducing the number of false positive interactions. On the other hand, Granger causality as well as information-theoretic measures, frequently used in inference of regulatory networks, show low performance on the short time series analyzed in this study. Conclusions: Our study is intended to serve as a guide for choosing a particular combination of similarity measures and scoring schemes suitable for reconstruction of gene regulatory networks from short time series data. We show that further improvement of algorithms for reverse engineering can be obtained if one considers measures that are rooted in the study of symbolic dynamics or ranks, in contrast to the application of common similarity measures which do not consider the temporal character of the employed data. Moreover, we establish that the asymmetric weighting scoring scheme together with symbol based measures (for low noise level) and rank based measures (for high noise level) are the most suitable choices.}, language = {en} } @misc{ArnoldNikoloski2011, author = {Arnold, Anne and Nikoloski, Zoran}, title = {A quantitative comparison of Calvin-Benson cycle models}, series = {Trends in plant science}, volume = {16}, journal = {Trends in plant science}, number = {12}, publisher = {Elsevier}, address = {London}, issn = {1360-1385}, doi = {10.1016/j.tplants.2011.09.004}, pages = {676 -- 683}, year = {2011}, abstract = {The Calvin-Benson cycle (CBC) provides the precursors for biomass synthesis necessary for plant growth. The dynamic behavior and yield of the CBC depend on the environmental conditions and regulation of the cellular state. Accurate quantitative models hold the promise of identifying the key determinants of the tightly regulated CBC function and their effects on the responses in future climates. We provide an integrative analysis of the largest compendium of existing models for photosynthetic processes. Based on the proposed ranking, our framework facilitates the discovery of best-performing models with regard to metabolomics data and of candidates for metabolic engineering.}, language = {en} } @article{ArnoldNikoloski2014, author = {Arnold, Anne and Nikoloski, Zoran}, title = {In search for an accurate model of the photosynthetic carbon metabolism}, series = {Mathematics and computers in simulation : transactions of IMACS}, volume = {96}, journal = {Mathematics and computers in simulation : transactions of IMACS}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0378-4754}, doi = {10.1016/j.matcom.2012.03.011}, pages = {171 -- 194}, year = {2014}, abstract = {The photosynthetic carbon metabolism, including the Calvin-Benson cycle, is the primary pathway in C-3-plants, producing starch and sucrose from CO2. Understanding the interplay between regulation and efficiency of this pathway requires the development of mathematical models which would explain the observed dynamics of metabolic transformations. Here, we address this question by casting the existing models of Calvin-Benson cycle and the end-product processes into an analysis framework which not only facilitates the comparison of the different models, but also allows for their ranking with respect to chosen criteria, including stability, sensitivity, robustness and/or compliance with experimental data. The importance of the photosynthetic carbon metabolism for the increase of plant biomass has resulted in many models with various levels of detail. We provide the largest compendium of 15 existing, well-investigated models together with a comprehensive classification as well as a ranking framework to determine the best-performing models for metabolic engineering and planning of in silica experiments. The classification can be additionally used, based on the model structure, as a tool to identify the models which match best the experimental design. The provided ranking is just one alternative to score models and, by changing the weighting factor, this framework also could be applied for selection of other criteria of interest.}, language = {en} } @article{CuiLvChenetal.2015, author = {Cui, Xiao and Lv, Yang and Chen, Miaolin and Nikoloski, Zoran and Twell, David and Zhang, Dabing}, title = {Young Genes out of the Male: An Insight from Evolutionary Age Analysis of the Pollen Transcriptome}, series = {Molecular plant}, volume = {8}, journal = {Molecular plant}, number = {6}, publisher = {Cell Press}, address = {Cambridge}, issn = {1674-2052}, doi = {10.1016/j.molp.2014.12.008}, pages = {935 -- 945}, year = {2015}, abstract = {The birth of new genes in genomes is an important evolutionary event. Several studies reveal that new genes in animals tend to be preferentially expressed in male reproductive tissues such as testis (Betran et al., 2002; Begun et al., 2007; Dubruille et al., 2012), and thus an "out of testis' hypothesis for the emergence of new genes has been proposed (Vinckenbosch et al., 2006; Kaessmann, 2010). However, such phenomena have not been examined in plant species. Here, by employing a phylostratigraphic method, we dated the origin of protein-coding genes in rice and Arabidopsis thaliana and observed a number of young genes in both species. These young genes tend to encode short extracellular proteins, which may be involved in rapid evolving processes, such as reproductive barriers, species specification, and antimicrobial processes. Further analysis of transcriptome age indexes across different tissues revealed that male reproductive cells express a phylogenetically younger transcriptome than other plant tissues. Compared with sporophytic tissues, the young transcriptomes of the male gametophyte displayed greater complexity and diversity, which included a higher ratio of anti-sense and inter-genic transcripts, reflecting a pervasive transcription state that facilitated the emergence of new genes. Here, we propose that pollen may act as an "innovation incubator' for the birth of de novo genes. With cases of male-biased expression of young genes reported in animals, the "new genes out of the male' model revealed a common evolutionary force that drives reproductive barriers, species specification, and the upgrading of defensive mechanisms against pathogens.}, language = {en} } @article{BaslerGrimbsNikoloski2012, author = {Basler, Georg and Grimbs, Sergio and Nikoloski, Zoran}, title = {Optimizing metabolic pathways by screening for feasible synthetic reactions}, series = {Biosystems : journal of biological and information processing sciences}, volume = {109}, journal = {Biosystems : journal of biological and information processing sciences}, number = {2}, publisher = {Elsevier}, address = {Oxford}, issn = {0303-2647}, doi = {10.1016/j.biosystems.2012.04.007}, pages = {186 -- 191}, year = {2012}, abstract = {Background: Reconstruction of genome-scale metabolic networks has resulted in models capable of reproducing experimentally observed biomass yield/growth rates and predicting the effect of alterations in metabolism for biotechnological applications. The existing studies rely on modifying the metabolic network of an investigated organism by removing or inserting reactions taken either from evolutionary similar organisms or from databases of biochemical reactions (e.g., KEGG). A potential disadvantage of these knowledge-driven approaches is that the result is biased towards known reactions, as such approaches do not account for the possibility of including novel enzymes, together with the reactions they catalyze. Results: Here, we explore the alternative of increasing biomass yield in three model organisms, namely Bacillus subtilis, Escherichia coil, and Hordeum vulgare, by applying small, chemically feasible network modifications. We use the predicted and experimentally confirmed growth rates of the wild-type networks as reference values and determine the effect of inserting mass-balanced, thermodynamically feasible reactions on predictions of growth rate by using flux balance analysis. Conclusions: While many replacements of existing reactions naturally lead to a decrease or complete loss of biomass production ability, in all three investigated organisms we find feasible modifications which facilitate a significant increase in this biological function. We focus on modifications with feasible chemical properties and a significant increase in biomass yield. The results demonstrate that small modifications are sufficient to substantially alter biomass yield in the three organisms. The method can be used to predict the effect of targeted modifications on the yield of any set of metabolites (e.g., ethanol), thus providing a computational framework for synthetic metabolic engineering.}, language = {en} } @article{NikoloskiGrimbsKlieetal.2011, author = {Nikoloski, Zoran and Grimbs, Sergio and Klie, Sebastian and Selbig, Joachim}, title = {Complexity of automated gene annotation}, series = {Biosystems : journal of biological and information processing sciences}, volume = {104}, journal = {Biosystems : journal of biological and information processing sciences}, number = {1}, publisher = {Elsevier}, address = {Oxford}, issn = {0303-2647}, doi = {10.1016/j.biosystems.2010.12.003}, pages = {1 -- 8}, year = {2011}, abstract = {Integration of high-throughput data with functional annotation by graph-theoretic methods has been postulated as promising way to unravel the function of unannotated genes. Here, we first review the existing graph-theoretic approaches for automated gene function annotation and classify them into two categories with respect to their relation to two instances of transductive learning on networks - with dynamic costs and with constant costs - depending on whether or not ontological relationship between functional terms is employed. The determined categories allow to characterize the computational complexity of the existing approaches and establish the relation to classical graph-theoretic problems, such as bisection and multiway cut. In addition, our results point out that the ontological form of the structured functional knowledge does not lower the complexity of the transductive learning with dynamic costs - one of the key problems in modern systems biology. The NP-hardness of automated gene annotation renders the development of heuristic or approximation algorithms a priority for additional research.}, language = {en} } @article{GrimbsArnoldKoseskaetal.2011, author = {Grimbs, Sergio and Arnold, Anne and Koseska, Aneta and Kurths, J{\"u}rgen and Selbig, Joachim and Nikoloski, Zoran}, title = {Spatiotemporal dynamics of the Calvin cycle multistationarity and symmetry breaking instabilities}, series = {Biosystems : journal of biological and information processing sciences}, volume = {103}, journal = {Biosystems : journal of biological and information processing sciences}, number = {2}, publisher = {Elsevier}, address = {Oxford}, issn = {0303-2647}, doi = {10.1016/j.biosystems.2010.10.015}, pages = {212 -- 223}, year = {2011}, abstract = {The possibility of controlling the Calvin cycle has paramount implications for increasing the production of biomass. Multistationarity, as a dynamical feature of systems, is the first obvious candidate whose control could find biotechnological applications. Here we set out to resolve the debate on the multistationarity of the Calvin cycle. Unlike the existing simulation-based studies, our approach is based on a sound mathematical framework, chemical reaction network theory and algebraic geometry, which results in provable results for the investigated model of the Calvin cycle in which we embed a hierarchy of realistic kinetic laws. Our theoretical findings demonstrate that there is a possibility for multistationarity resulting from two sources, homogeneous and inhomogeneous instabilities, which partially settle the debate on multistability of the Calvin cycle. In addition, our tractable analytical treatment of the bifurcation parameters can be employed in the design of validation experiments.}, language = {en} } @article{RuprechtMutwilSaxeetal.2011, author = {Ruprecht, Colin and Mutwil, Marek and Saxe, Friederike and Eder, Michaela and Nikoloski, Zoran and Persson, Staffan}, title = {Large-scale co-expression approach to dissect secondary cell wall formation across plant species}, series = {Frontiers in plant science}, volume = {2}, journal = {Frontiers in plant science}, publisher = {Frontiers Research Foundation}, address = {Lausanne}, issn = {1664-462X}, doi = {10.3389/fpls.2011.00023}, pages = {13}, year = {2011}, abstract = {Plant cell walls are complex composites largely consisting of carbohydrate-based polymers, and are generally divided into primary and secondary walls based on content and characteristics. Cellulose microfibrils constitute a major component of both primary and secondary cell walls and are synthesized at the plasma membrane by cellulose synthase (CESA) complexes. Several studies in Arabidopsis have demonstrated the power of co-expression analyses to identify new genes associated with secondary wall cellulose biosynthesis. However, across-species comparative co-expression analyses remain largely unexplored. Here, we compared co-expressed gene vicinity networks of primary and secondary wall CESAsin Arabidopsis, barley, rice, poplar, soybean, Medicago, and wheat, and identified gene families that are consistently co-regulated with cellulose biosynthesis. In addition to the expected polysaccharide acting enzymes, we also found many gene families associated with cytoskeleton, signaling, transcriptional regulation, oxidation, and protein degradation. Based on these analyses, we selected and biochemically analyzed T-DNA insertion lines corresponding to approximately twenty genes from gene families that re-occur in the co-expressed gene vicinity networks of secondary wall CESAs across the seven species. We developed a statistical pipeline using principal component analysis and optimal clustering based on silhouette width to analyze sugar profiles. One of the mutants, corresponding to a pinoresinol reductase gene, displayed disturbed xylem morphology and held lower levels of lignin molecules. We propose that this type of large-scale co-expression approach, coupled with statistical analysis of the cell wall contents, will be useful to facilitate rapid knowledge transfer across plant species.}, language = {en} } @misc{NikoloskivanDongen2011, author = {Nikoloski, Zoran and van Dongen, Joost T.}, title = {Modeling alternatives for interpreting the change in oxygen-consumption rates during hypoxic conditions}, series = {New phytologist : international journal of plant science}, volume = {190}, journal = {New phytologist : international journal of plant science}, number = {2}, publisher = {Wiley-Blackwell}, address = {Malden}, issn = {0028-646X}, doi = {10.1111/j.1469-8137.2011.03674.x}, pages = {273 -- 276}, year = {2011}, language = {en} } @article{KlieNikoloskiSelbig2014, author = {Klie, Sebastian and Nikoloski, Zoran and Selbig, Joachim}, title = {Biological cluster evaluation for gene function prediction}, series = {Journal of computational biology}, volume = {21}, journal = {Journal of computational biology}, number = {6}, publisher = {Liebert}, address = {New Rochelle}, issn = {1066-5277}, doi = {10.1089/cmb.2009.0129}, pages = {428 -- 445}, year = {2014}, abstract = {Recent advances in high-throughput omics techniques render it possible to decode the function of genes by using the "guilt-by-association" principle on biologically meaningful clusters of gene expression data. However, the existing frameworks for biological evaluation of gene clusters are hindered by two bottleneck issues: (1) the choice for the number of clusters, and (2) the external measures which do not take in consideration the structure of the analyzed data and the ontology of the existing biological knowledge. Here, we address the identified bottlenecks by developing a novel framework that allows not only for biological evaluation of gene expression clusters based on existing structured knowledge, but also for prediction of putative gene functions. The proposed framework facilitates propagation of statistical significance at each of the following steps: (1) estimating the number of clusters, (2) evaluating the clusters in terms of novel external structural measures, (3) selecting an optimal clustering algorithm, and (4) predicting gene functions. The framework also includes a method for evaluation of gene clusters based on the structure of the employed ontology. Moreover, our method for obtaining a probabilistic range for the number of clusters is demonstrated valid on synthetic data and available gene expression profiles from Saccharomyces cerevisiae. Finally, we propose a network-based approach for gene function prediction which relies on the clustering of optimal score and the employed ontology. Our approach effectively predicts gene function on the Saccharomyces cerevisiae data set and is also employed to obtain putative gene functions for an Arabidopsis thaliana data set.}, language = {en} } @article{LarhlimiBaslerGrimbsetal.2012, author = {Larhlimi, Abdelhalim and Basler, Georg and Grimbs, Sergio and Selbig, Joachim and Nikoloski, Zoran}, title = {Stoichiometric capacitance reveals the theoretical capabilities of metabolic networks}, series = {Bioinformatics}, volume = {28}, journal = {Bioinformatics}, number = {18}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/bts381}, pages = {I502 -- I508}, year = {2012}, abstract = {Motivation: Metabolic engineering aims at modulating the capabilities of metabolic networks by changing the activity of biochemical reactions. The existing constraint-based approaches for metabolic engineering have proven useful, but are limited only to reactions catalogued in various pathway databases. Results: We consider the alternative of designing synthetic strategies which can be used not only to characterize the maximum theoretically possible product yield but also to engineer networks with optimal conversion capability by using a suitable biochemically feasible reaction called 'stoichiometric capacitance'. In addition, we provide a theoretical solution for decomposing a given stoichiometric capacitance over a set of known enzymatic reactions. We determine the stoichiometric capacitance for genome-scale metabolic networks of 10 organisms from different kingdoms of life and examine its implications for the alterations in flux variability patterns. Our empirical findings suggest that the theoretical capacity of metabolic networks comes at a cost of dramatic system's changes.}, language = {en} } @misc{LarhlimiBlachonSelbigetal.2011, author = {Larhlimi, Abdelhalim and Blachon, Sylvain and Selbig, Joachim and Nikoloski, Zoran}, title = {Robustness of metabolic networks a review of existing definitions}, series = {Biosystems : journal of biological and information processing sciences}, volume = {106}, journal = {Biosystems : journal of biological and information processing sciences}, number = {1}, publisher = {Elsevier}, address = {Oxford}, issn = {0303-2647}, doi = {10.1016/j.biosystems.2011.06.002}, pages = {1 -- 8}, year = {2011}, abstract = {Describing the determinants of robustness of biological systems has become one of the central questions in systems biology. Despite the increasing research efforts, it has proven difficult to arrive at a unifying definition for this important concept. We argue that this is due to the multifaceted nature of the concept of robustness and the possibility to formally capture it at different levels of systemic formalisms (e.g, topology and dynamic behavior). Here we provide a comprehensive review of the existing definitions of robustness pertaining to metabolic networks. As kinetic approaches have been excellently reviewed elsewhere, we focus on definitions of robustness proposed within graph-theoretic and constraint-based formalisms.}, language = {en} } @article{BaslerNikoloski2011, author = {Basler, Georg and Nikoloski, Zoran}, title = {JMassBalance - mass-balanced randomization and analysis of metabolic networks}, series = {Bioinformatics}, volume = {27}, journal = {Bioinformatics}, number = {19}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btr448}, pages = {2761 -- 2762}, year = {2011}, abstract = {Analysis of biological networks requires assessing the statistical significance of network-based predictions by using a realistic null model. However, the existing network null model, switch randomization, is unsuitable for metabolic networks, as it does not include physical constraints and generates unrealistic reactions. We present JMassBalance, a tool for mass-balanced randomization and analysis of metabolic networks. The tool allows efficient generation of large sets of randomized networks under the physical constraint of mass balance. In addition, various structural properties of the original and randomized networks can be calculated, facilitating the identification of the salient properties of metabolic networks with a biologically meaningful null model.}, language = {en} } @article{BaslerGrimbsEbenhoehetal.2012, author = {Basler, Georg and Grimbs, Sergio and Ebenh{\"o}h, Oliver and Selbig, Joachim and Nikoloski, Zoran}, title = {Evolutionary significance of metabolic network properties}, series = {Interface : journal of the Royal Society}, volume = {9}, journal = {Interface : journal of the Royal Society}, number = {71}, publisher = {Royal Society}, address = {London}, issn = {1742-5689}, doi = {10.1098/rsif.2011.0652}, pages = {1168 -- 1176}, year = {2012}, abstract = {Complex networks have been successfully employed to represent different levels of biological systems, ranging from gene regulation to protein-protein interactions and metabolism. Network-based research has mainly focused on identifying unifying structural properties, such as small average path length, large clustering coefficient, heavy-tail degree distribution and hierarchical organization, viewed as requirements for efficient and robust system architectures. However, for biological networks, it is unclear to what extent these properties reflect the evolutionary history of the represented systems. Here, we show that the salient structural properties of six metabolic networks from all kingdoms of life may be inherently related to the evolution and functional organization of metabolism by employing network randomization under mass balance constraints. Contrary to the results from the common Markov-chain switching algorithm, our findings suggest the evolutionary importance of the small-world hypothesis as a fundamental design principle of complex networks. The approach may help us to determine the biologically meaningful properties that result from evolutionary pressure imposed on metabolism, such as the global impact of local reaction knockouts. Moreover, the approach can be applied to test to what extent novel structural properties can be used to draw biologically meaningful hypothesis or predictions from structure alone.}, language = {en} } @article{AraujoNunesNesiNikoloskietal.2012, author = {Araujo, Wagner L. and Nunes-Nesi, Adriano and Nikoloski, Zoran and Sweetlove, Lee J. and Fernie, Alisdair R.}, title = {Metabolic control and regulation of the tricarboxylic acid cycle in photosynthetic and heterotrophic plant tissues}, series = {Plant, cell \& environment : cell physiology, whole-plant physiology, community physiology}, volume = {35}, journal = {Plant, cell \& environment : cell physiology, whole-plant physiology, community physiology}, number = {1}, publisher = {Wiley-Blackwell}, address = {Hoboken}, issn = {0140-7791}, doi = {10.1111/j.1365-3040.2011.02332.x}, pages = {1 -- 21}, year = {2012}, abstract = {The tricarboxylic acid (TCA) cycle is a crucial component of respiratory metabolism in both photosynthetic and heterotrophic plant organs. All of the major genes of the tomato TCA cycle have been cloned recently, allowing the generation of a suite of transgenic plants in which the majority of the enzymes in the pathway are progressively decreased. Investigations of these plants have provided an almost complete view of the distribution of control in this important pathway. Our studies suggest that citrate synthase, aconitase, isocitrate dehydrogenase, succinyl CoA ligase, succinate dehydrogenase, fumarase and malate dehydrogenase have control coefficients flux for respiration of -0.4, 0.964, -0.123, 0.0008, 0.289, 0.601 and 1.76, respectively; while 2-oxoglutarate dehydrogenase is estimated to have a control coefficient of 0.786 in potato tubers. These results thus indicate that the control of this pathway is distributed among malate dehydrogenase, aconitase, fumarase, succinate dehydrogenase and 2-oxoglutarate dehydrogenase. The unusual distribution of control estimated here is consistent with specific non-cyclic flux mode and cytosolic bypasses that operate in illuminated leaves. These observations are discussed in the context of known regulatory properties of the enzymes and some illustrative examples of how the pathway responds to environmental change are given.}, language = {en} } @article{SchwahnBeleggiaOmranianetal.2017, author = {Schwahn, Kevin and Beleggia, Romina and Omranian, Nooshin and Nikoloski, Zoran}, title = {Stoichiometric Correlation Analysis: Principles of Metabolic Functionality from Metabolomics Data}, series = {Frontiers in plant science}, volume = {8}, journal = {Frontiers in plant science}, publisher = {Frontiers Research Foundation}, address = {Lausanne}, issn = {1664-462X}, doi = {10.3389/fpls.2017.02152}, pages = {12}, year = {2017}, abstract = {Recent advances in metabolomics technologies have resulted in high-quality (time-resolved) metabolic profiles with an increasing coverage of metabolic pathways. These data profiles represent read-outs from often non-linear dynamics of metabolic networks. Yet, metabolic profiles have largely been explored with regression-based approaches that only capture linear relationships, rendering it difficult to determine the extent to which the data reflect the underlying reaction rates and their couplings. Here we propose an approach termed Stoichiometric Correlation Analysis (SCA) based on correlation between positive linear combinations of log-transformed metabolic profiles. The log-transformation is due to the evidence that metabolic networks can be modeled by mass action law and kinetics derived from it. Unlike the existing approaches which establish a relation between pairs of metabolites, SCA facilitates the discovery of higherorder dependence between more than two metabolites. By using a paradigmatic model of the tricarboxylic acid cycle we show that the higher-order dependence reflects the coupling of concentration of reactant complexes, capturing the subtle difference between the employed enzyme kinetics. Using time-resolved metabolic profiles from Arabidopsis thaliana and Escherichia coli, we show that SCA can be used to quantify the difference in coupling of reactant complexes, and hence, reaction rates, underlying the stringent response in these model organisms. By using SCA with data from natural variation of wild and domesticated wheat and tomato accession, we demonstrate that the domestication is accompanied by loss of such couplings, in these species. Therefore, application of SCA to metabolomics data from natural variation in wild and domesticated populations provides a mechanistic way to understanding domestication and its relation to metabolic networks.}, language = {en} } @misc{HempelKoseskaNikoloskietal.2017, author = {Hempel, Sabrina and Koseska, Aneta and Nikoloski, Zoran and Kurths, J{\"u}rgen}, title = {Unraveling gene regulatory networks from time-resolved gene expression data}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-400924}, pages = {26}, year = {2017}, abstract = {Background: Inferring regulatory interactions between genes from transcriptomics time-resolved data, yielding reverse engineered gene regulatory networks, is of paramount importance to systems biology and bioinformatics studies. Accurate methods to address this problem can ultimately provide a deeper insight into the complexity, behavior, and functions of the underlying biological systems. However, the large number of interacting genes coupled with short and often noisy time-resolved read-outs of the system renders the reverse engineering a challenging task. Therefore, the development and assessment of methods which are computationally efficient, robust against noise, applicable to short time series data, and preferably capable of reconstructing the directionality of the regulatory interactions remains a pressing research problem with valuable applications. Results: Here we perform the largest systematic analysis of a set of similarity measures and scoring schemes within the scope of the relevance network approach which are commonly used for gene regulatory network reconstruction from time series data. In addition, we define and analyze several novel measures and schemes which are particularly suitable for short transcriptomics time series. We also compare the considered 21 measures and 6 scoring schemes according to their ability to correctly reconstruct such networks from short time series data by calculating summary statistics based on the corresponding specificity and sensitivity. Our results demonstrate that rank and symbol based measures have the highest performance in inferring regulatory interactions. In addition, the proposed scoring scheme by asymmetric weighting has shown to be valuable in reducing the number of false positive interactions. On the other hand, Granger causality as well as information-theoretic measures, frequently used in inference of regulatory networks, show low performance on the short time series analyzed in this study. Conclusions: Our study is intended to serve as a guide for choosing a particular combination of similarity measures and scoring schemes suitable for reconstruction of gene regulatory networks from short time series data. We show that further improvement of algorithms for reverse engineering can be obtained if one considers measures that are rooted in the study of symbolic dynamics or ranks, in contrast to the application of common similarity measures which do not consider the temporal character of the employed data. Moreover, we establish that the asymmetric weighting scoring scheme together with symbol based measures (for low noise level) and rank based measures (for high noise level) are the most suitable choices.}, language = {en} } @article{RobainaEstevezNikoloski2017, author = {Robaina-Estevez, Semidan and Nikoloski, Zoran}, title = {On the effects of alternative optima in context-specific metabolic model predictions}, series = {PLoS Computational Biology : a new community journal}, volume = {13}, journal = {PLoS Computational Biology : a new community journal}, publisher = {PLoS}, address = {San Fransisco}, issn = {1553-734X}, doi = {10.1371/journal.pcbi.1005568}, pages = {750 -- 766}, year = {2017}, abstract = {The integration of experimental data into genome-scale metabolic models can greatly improve flux predictions. This is achieved by restricting predictions to a more realistic context-specific domain, like a particular cell or tissue type. Several computational approaches to integrate data have been proposed D generally obtaining context-specific (sub) models or flux distributions. However, these approaches may lead to a multitude of equally valid but potentially different models or flux distributions, due to possible alternative optima in the underlying optimization problems. Although this issue introduces ambiguity in context-specific predictions, it has not been generally recognized, especially in the case of model reconstructions. In this study, we analyze the impact of alternative optima in four state-of-the-art context-specific data integration approaches, providing both flux distributions and/or metabolic models. To this end, we present three computational methods and apply them to two particular case studies: leaf-specific predictions from the integration of gene expression data in a metabolic model of Arabidopsis thaliana, and liver-specific reconstructions derived from a human model with various experimental data sources. The application of these methods allows us to obtain the following results: (i) we sample the space of alternative flux distributions in the leaf-and the liver-specific case and quantify the ambiguity of the predictions. In addition, we show how the inclusion of l(1)-regularization during data integration reduces the ambiguity in both cases. (ii) We generate sets of alternative leaf-and liver-specific models that are optimal to each one of the evaluated model reconstruction approaches. We demonstrate that alternative models of the same context contain a marked fraction of disparate reactions. Further, we show that a careful balance between model sparsity and metabolic functionality helps in reducing the discrepancies between alternative models. Finally, our findings indicate that alternative optima must be taken into account for rendering the context-specific metabolic model predictions less ambiguous.}, language = {en} } @article{BreuerNowakIvakovetal.2017, author = {Breuer, David and Nowak, Jacqueline and Ivakov, Alexander and Somssich, Marc and Persson, Staffan and Nikoloski, Zoran}, title = {System-wide organization of actin cytoskeleton determines organelle transport in hypocotyl plant cells}, series = {Proceedings of the National Academy of Sciences of the United States of America}, volume = {114}, journal = {Proceedings of the National Academy of Sciences of the United States of America}, publisher = {National Acad. of Sciences}, address = {Washington}, issn = {0027-8424}, doi = {10.1073/pnas.1706711114}, pages = {E5741 -- E5749}, year = {2017}, abstract = {The actin cytoskeleton is an essential intracellular filamentous structure that underpins cellular transport and cytoplasmic streaming in plant cells. However, the system-level properties of actin-based cellular trafficking remain tenuous, largely due to the inability to quantify key features of the actin cytoskeleton. Here, we developed an automated image-based, network-driven framework to accurately segment and quantify actin cytoskeletal structures and Golgi transport. We show that the actin cytoskeleton in both growing and elongated hypocotyl cells has structural properties facilitating efficient transport. Our findings suggest that the erratic movement of Golgi is a stable cellular phenomenon that might optimize distribution efficiency of cell material. Moreover, we demonstrate that Golgi transport in hypocotyl cells can be accurately predicted from the actin network topology alone. Thus, our framework provides quantitative evidence for system-wide coordination of cellular transport in plant cells and can be readily applied to investigate cytoskeletal organization and transport in other organisms.}, language = {en} } @article{RuprechtLohausVannesteetal.2017, author = {Ruprecht, Colin and Lohaus, Rolf and Vanneste, Kevin and Mutwil, Marek and Nikoloski, Zoran and Van de Peer, Yves and Persson, Staffan}, title = {Revisiting ancestral polyploidy in plants}, series = {Science Advances}, volume = {3}, journal = {Science Advances}, publisher = {American Assoc. for the Advancement of Science}, address = {Washington}, issn = {2375-2548}, doi = {10.1126/sciadv.1603195}, pages = {6}, year = {2017}, abstract = {Whole-genome duplications (WGDs) or polyploidy events have been studied extensively in plants. In a now widely cited paper, Jiao et al. presented evidence for two ancient, ancestral plant WGDs predating the origin of flowering and seed plants, respectively. This finding was based primarily on a bimodal age distribution of gene duplication events obtained from molecular dating of almost 800 phylogenetic gene trees. We reanalyzed the phylogenomic data of Jiao et al. and found that the strong bimodality of the age distribution may be the result of technical and methodological issues and may hence not be a "true" signal of two WGD events. By using a state-of-the-art molecular dating algorithm, we demonstrate that the reported bimodal age distribution is not robust and should be interpreted with caution. Thus, there exists little evidence for two ancient WGDs in plants from phylogenomic dating.}, language = {en} } @article{KuekenLangaryNikoloski2022, author = {K{\"u}ken, Anika and Langary, Damoun and Nikoloski, Zoran}, title = {The hidden simplicity of metabolic networks is revealed by multireaction dependencies}, series = {Science Advances}, volume = {8}, journal = {Science Advances}, number = {13}, publisher = {American Assoc. for the Advancement of Science}, address = {Washington}, issn = {2375-2548}, doi = {10.1126/sciadv.abl6962}, pages = {10}, year = {2022}, abstract = {Understanding the complexity of metabolic networks has implications for manipulation of their functions. The complexity of metabolic networks can be characterized by identifying multireaction dependencies that are challenging to determine due to the sheer number of combinations to consider. Here, we propose the concept of concordant complexes that captures multireaction dependencies and can be efficiently determined from the algebraic structure and operational constraints of metabolic networks. The concordant complexes imply the existence of concordance modules based on which the apparent complexity of 12 metabolic networks of organisms from all kingdoms of life can be reduced by at least 78\%. A comparative analysis against an ensemble of randomized metabolic networks shows that the metabolic network of Escherichia coli contains fewer concordance modules and is, therefore, more tightly coordinated than expected by chance. Together, our findings demonstrate that metabolic networks are considerably simpler than what can be perceived from their structure alone.}, language = {en} } @article{LisecRoemischMarglNikoloskietal.2011, author = {Lisec, Jan and R{\"o}misch-Margl, Lilla and Nikoloski, Zoran and Piepho, Hans-Peter and Giavalisco, Patrick and Selbig, Joachim and Gierl, Alfons and Willmitzer, Lothar}, title = {Corn hybrids display lower metabolite variability and complex metabolite inheritance patterns}, series = {The plant journal}, volume = {68}, journal = {The plant journal}, number = {2}, publisher = {Wiley-Blackwell}, address = {Malden}, issn = {0960-7412}, doi = {10.1111/j.1365-313X.2011.04689.x}, pages = {326 -- 336}, year = {2011}, abstract = {We conducted a comparative analysis of the root metabolome of six parental maize inbred lines and their 14 corresponding hybrids showing fresh weight heterosis. We demonstrated that the metabolic profiles not only exhibit distinct features for each hybrid line compared with its parental lines, but also separate reciprocal hybrids. Reconstructed metabolic networks, based on robust correlations between metabolic profiles, display a higher network density in most hybrids as compared with the corresponding inbred lines. With respect to metabolite level inheritance, additive, dominant and overdominant patterns are observed with no specific overrepresentation. Despite the observed complexity of the inheritance pattern, for the majority of metabolites the variance observed in all 14 hybrids is lower compared with inbred lines. Deviations of metabolite levels from the average levels of the hybrids correlate negatively with biomass, which could be applied for developing predictors of hybrid performance based on characteristics of metabolite patterns.}, language = {en} } @article{FeherLisecRoemischMargletal.2014, author = {Feher, Kristen and Lisec, Jan and Roemisch-Margl, Lilla and Selbig, Joachim and Gierl, Alfons and Piepho, Hans-Peter and Nikoloski, Zoran and Willmitzer, Lothar}, title = {Deducing hybrid performance from parental metabolic profiles of young primary roots of maize by using a multivariate diallel approach}, series = {PLoS one}, volume = {9}, journal = {PLoS one}, number = {1}, publisher = {PLoS}, address = {San Fransisco}, issn = {1932-6203}, doi = {10.1371/journal.pone.0085435}, pages = {9}, year = {2014}, language = {en} } @misc{OmidbakhshfardNeerakkalGuptaetal.2020, author = {Omidbakhshfard, Mohammad Amin and Neerakkal, Sujeeth and Gupta, Saurabh and Omranian, Nooshin and Guinan, Kieran J. and Brotman, Yariv and Nikoloski, Zoran and Fernie, Alisdair R. and Mueller-Roeber, Bernd and Gechev, Tsanko S.}, title = {A Biostimulant Obtained from the Seaweed Ascophyllum nodosum Protects Arabidopsis thaliana from Severe Oxidative Stress}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, number = {823}, issn = {1866-8372}, doi = {10.25932/publishup-44509}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-445093}, pages = {26}, year = {2020}, abstract = {Abiotic stresses cause oxidative damage in plants. Here, we demonstrate that foliar application of an extract from the seaweed Ascophyllum nodosum, SuperFifty (SF), largely prevents paraquat (PQ)-induced oxidative stress in Arabidopsis thaliana. While PQ-stressed plants develop necrotic lesions, plants pre-treated with SF (i.e., primed plants) were unaffected by PQ. Transcriptome analysis revealed induction of reactive oxygen species (ROS) marker genes, genes involved in ROS-induced programmed cell death, and autophagy-related genes after PQ treatment. These changes did not occur in PQ-stressed plants primed with SF. In contrast, upregulation of several carbohydrate metabolism genes, growth, and hormone signaling as well as antioxidant-related genes were specific to SF-primed plants. Metabolomic analyses revealed accumulation of the stress-protective metabolite maltose and the tricarboxylic acid cycle intermediates fumarate and malate in SF-primed plants. Lipidome analysis indicated that those lipids associated with oxidative stress-induced cell death and chloroplast degradation, such as triacylglycerols (TAGs), declined upon SF priming. Our study demonstrated that SF confers tolerance to PQ-induced oxidative stress in A. thaliana, an effect achieved by modulating a range of processes at the transcriptomic, metabolic, and lipid levels.}, language = {en} } @article{OmidbakhshfardNeerakkalGuptaetal.2020, author = {Omidbakhshfard, Mohammad Amin and Neerakkal, Sujeeth and Gupta, Saurabh and Omranian, Nooshin and Guinan, Kieran J. and Brotman, Yariv and Nikoloski, Zoran and Fernie, Alisdair R. and Mueller-Roeber, Bernd and Gechev, Tsanko S.}, title = {A Biostimulant Obtained from the Seaweed Ascophyllum nodosum Protects Arabidopsis thaliana from Severe Oxidative Stress}, series = {International Journal of Molecular Sciences}, volume = {21}, journal = {International Journal of Molecular Sciences}, number = {2}, publisher = {Molecular Diversity Preservation International}, address = {Basel}, issn = {1422-0067}, doi = {10.3390/ijms21020474}, pages = {26}, year = {2020}, abstract = {Abiotic stresses cause oxidative damage in plants. Here, we demonstrate that foliar application of an extract from the seaweed Ascophyllum nodosum, SuperFifty (SF), largely prevents paraquat (PQ)-induced oxidative stress in Arabidopsis thaliana. While PQ-stressed plants develop necrotic lesions, plants pre-treated with SF (i.e., primed plants) were unaffected by PQ. Transcriptome analysis revealed induction of reactive oxygen species (ROS) marker genes, genes involved in ROS-induced programmed cell death, and autophagy-related genes after PQ treatment. These changes did not occur in PQ-stressed plants primed with SF. In contrast, upregulation of several carbohydrate metabolism genes, growth, and hormone signaling as well as antioxidant-related genes were specific to SF-primed plants. Metabolomic analyses revealed accumulation of the stress-protective metabolite maltose and the tricarboxylic acid cycle intermediates fumarate and malate in SF-primed plants. Lipidome analysis indicated that those lipids associated with oxidative stress-induced cell death and chloroplast degradation, such as triacylglycerols (TAGs), declined upon SF priming. Our study demonstrated that SF confers tolerance to PQ-induced oxidative stress in A. thaliana, an effect achieved by modulating a range of processes at the transcriptomic, metabolic, and lipid levels.}, language = {en} } @misc{RazaghiMoghadamNikoloski2020, author = {Razaghi-Moghadam, Zahra and Nikoloski, Zoran}, title = {Supervised learning of gene regulatory networks}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, issn = {1866-8372}, doi = {10.25932/publishup-51656}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-516561}, pages = {9}, year = {2020}, abstract = {Identifying the entirety of gene regulatory interactions in a biological system offers the possibility to determine the key molecular factors that affect important traits on the level of cells, tissues, and whole organisms. Despite the development of experimental approaches and technologies for identification of direct binding of transcription factors (TFs) to promoter regions of downstream target genes, computational approaches that utilize large compendia of transcriptomics data are still the predominant methods used to predict direct downstream targets of TFs, and thus reconstruct genome-wide gene-regulatory networks (GRNs). These approaches can broadly be categorized into unsupervised and supervised, based on whether data about known, experimentally verified gene-regulatory interactions are used in the process of reconstructing the underlying GRN. Here, we first describe the generic steps of supervised approaches for GRN reconstruction, since they have been recently shown to result in improved accuracy of the resulting networks? We also illustrate how they can be used with data from model organisms to obtain more accurate prediction of gene regulatory interactions.}, language = {en} } @article{HashemiRazaghiMoghadamNikoloski2021, author = {Hashemi, Seirana and Razaghi-Moghadam, Zahra and Nikoloski, Zoran}, title = {Identification of flux trade-offs in metabolic networks}, series = {Scientific reports}, volume = {11}, journal = {Scientific reports}, number = {1}, publisher = {Macmillan Publishers Limited, part of Springer Nature}, address = {London}, issn = {2045-2322}, doi = {10.1038/s41598-021-03224-9}, pages = {10}, year = {2021}, abstract = {Trade-offs are inherent to biochemical networks governing diverse cellular functions, from gene expression to metabolism. Yet, trade-offs between fluxes of biochemical reactions in a metabolic network have not been formally studied. Here, we introduce the concept of absolute flux trade-offs and devise a constraint-based approach, termed FluTO, to identify and enumerate flux trade-offs in a given genome-scale metabolic network. By employing the metabolic networks of Escherichia coli and Saccharomyces cerevisiae, we demonstrate that the flux trade-offs are specific to carbon sources provided but that reactions involved in the cofactor and prosthetic group biosynthesis are present in trade-offs across all carbon sources supporting growth. We also show that absolute flux trade-offs depend on the biomass reaction used to model the growth of Arabidopsis thaliana under different carbon and nitrogen conditions. The identified flux trade-offs reflect the tight coupling between nitrogen, carbon, and sulphur metabolisms in leaves of C-3 plants. Altogether, FluTO provides the means to explore the space of alternative metabolic routes reflecting the constraints imposed by inherent flux trade-offs in large-scale metabolic networks.}, language = {en} } @article{RazaghiMoghadamNikoloski2020, author = {Razaghi-Moghadam, Zahra and Nikoloski, Zoran}, title = {Supervised learning of gene-regulatory networks based on graph distance profiles of transcriptomics data}, series = {npj Systems biology and applications}, volume = {6}, journal = {npj Systems biology and applications}, number = {1}, publisher = {Nature Publ. Group}, address = {London}, issn = {2056-7189}, doi = {10.1038/s41540-020-0140-1}, pages = {8}, year = {2020}, abstract = {Characterisation of gene-regulatory network (GRN) interactions provides a stepping stone to understanding how genes affect cellular phenotypes. Yet, despite advances in profiling technologies, GRN reconstruction from gene expression data remains a pressing problem in systems biology. Here, we devise a supervised learning approach, GRADIS, which utilises support vector machine to reconstruct GRNs based on distance profiles obtained from a graph representation of transcriptomics data. By employing the data fromEscherichia coliandSaccharomyces cerevisiaeas well as synthetic networks from the DREAM4 and five network inference challenges, we demonstrate that our GRADIS approach outperforms the state-of-the-art supervised and unsupervided approaches. This holds when predictions about target genes for individual transcription factors as well as for the entire network are considered. We employ experimentally verified GRNs fromE. coliandS. cerevisiaeto validate the predictions and obtain further insights in the performance of the proposed approach. Our GRADIS approach offers the possibility for usage of other network-based representations of large-scale data, and can be readily extended to help the characterisation of other cellular networks, including protein-protein and protein-metabolite interactions.}, language = {en} } @article{RazaghiMoghadamNikoloski2020, author = {Razaghi-Moghadam, Zahra and Nikoloski, Zoran}, title = {GeneReg}, series = {Bioinformatics}, volume = {37}, journal = {Bioinformatics}, number = {12}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btaa996}, pages = {1717 -- 1723}, year = {2020}, abstract = {Motivation Large-scale metabolic models are widely used to design metabolic engineering strategies for diverse biotechnological applications. However, the existing computational approaches focus on alteration of reaction fluxes and often neglect the manipulations of gene expression to implement these strategies. Results Here, we find that the association of genes with multiple reactions leads to infeasibility of engineering strategies at the flux level, since they require contradicting manipulations of gene expression. Moreover, we identify that all of the existing approaches to design gene knockout strategies do not ensure that the resulting design may also require other gene alterations, such as up- or downregulations, to match the desired flux distribution. To address these issues, we propose a constraint-based approach, termed GeneReg, that facilitates the design of feasible metabolic engineering strategies at the gene level and that is readily applicable to large-scale metabolic networks. We show that GeneReg can identify feasible strategies to overproduce ethanol in Escherichia coli and lactate in Saccharomyces cerevisiae, but overproduction of the TCA cycle intermediates is not feasible in five organisms used as cell factories under default growth conditions. Therefore, GeneReg points at the need to couple gene regulation and metabolism to design rational metabolic engineering strategies.}, language = {en} } @misc{OmranianNikoloski2022, author = {Omranian, Sara and Nikoloski, Zoran}, title = {CUBCO+: prediction of protein complexes based on min-cut network partitioning into biclique spanned subgraphs}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {1315}, issn = {1866-8372}, doi = {10.25932/publishup-58686}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-586863}, pages = {12}, year = {2022}, abstract = {High-throughput proteomics approaches have resulted in large-scale protein-protein interaction (PPI) networks that have been employed for the prediction of protein complexes. However, PPI networks contain false-positive as well as false-negative PPIs that affect the protein complex prediction algorithms. To address this issue, here we propose an algorithm called CUBCO+ that: (1) employs GO semantic similarity to retain only biologically relevant interactions with a high similarity score, (2) based on link prediction approaches, scores the false-negative edges, and (3) incorporates the resulting scores to predict protein complexes. Through comprehensive analyses with PPIs from Escherichia coli, Saccharomyces cerevisiae, and Homo sapiens, we show that CUBCO+ performs as well as the approaches that predict protein complexes based on recently introduced graph partitions into biclique spanned subgraphs and outperforms the other state-of-the-art approaches. Moreover, we illustrate that in combination with GO semantic similarity, CUBCO+ enables us to predict more accurate protein complexes in 36\% of the cases in comparison to CUBCO as its predecessor.}, language = {en} } @article{SeepRazaghiMoghadamNikoloski2021, author = {Seep, Lea and Razaghi-Moghadam, Zahra and Nikoloski, Zoran}, title = {Reaction lumping in metabolic networks for application with thermodynamic metabolic flux analysis}, series = {Scientific reports}, volume = {11}, journal = {Scientific reports}, number = {1}, publisher = {Macmillan Publishers Limited, part of Springer Nature}, address = {London}, issn = {2045-2322}, doi = {10.1038/s41598-021-87643-8}, pages = {11}, year = {2021}, abstract = {Thermodynamic metabolic flux analysis (TMFA) can narrow down the space of steady-state flux distributions, but requires knowledge of the standard Gibbs free energy for the modelled reactions. The latter are often not available due to unknown Gibbs free energy change of formation ,Delta fG0, of metabolites. To optimize the usage of data on thermodynamics in constraining a model, reaction lumping has been proposed to eliminate metabolites with unknown Delta fG0. However, the lumping procedure has not been formalized nor implemented for systematic identification of lumped reactions. Here, we propose, implement, and test a combined procedure for reaction lumping, applicable to genome-scale metabolic models. It is based on identification of groups of metabolites with unknown Delta fG0 whose elimination can be conducted independently of the others via: (1) group implementation, aiming to eliminate an entire such group, and, if this is infeasible, (2) a sequential implementation to ensure that a maximal number of metabolites with unknown Delta fG0 are eliminated. Our comparative analysis with genome-scale metabolic models of Escherichia coli, Bacillus subtilis, and Homo sapiens shows that the combined procedure provides an efficient means for systematic identification of lumped reactions. We also demonstrate that TMFA applied to models with reactions lumped according to the proposed procedure lead to more precise predictions in comparison to the original models. The provided implementation thus ensures the reproducibility of the findings and their application with standard TMFA.}, language = {en} } @article{LyallNikoloskiGechev2020, author = {Lyall, Rafe and Nikoloski, Zoran and Gechev, Tsanko}, title = {Comparative analysis of ROS network genes in extremophile Eukaryotes}, series = {International journal of molecular sciences}, volume = {21}, journal = {International journal of molecular sciences}, number = {23}, publisher = {Molecular Diversity Preservation International (MDPI)}, address = {Basel}, issn = {1422-0067}, doi = {10.3390/ijms21239131}, pages = {27}, year = {2020}, abstract = {The reactive oxygen species (ROS) gene network, consisting of both ROS-generating and detoxifying enzymes, adjusts ROS levels in response to various stimuli. We performed a cross-kingdom comparison of ROS gene networks to investigate how they have evolved across all Eukaryotes, including protists, fungi, plants and animals. We included the genomes of 16 extremotolerant Eukaryotes to gain insight into ROS gene evolution in organisms that experience extreme stress conditions. Our analysis focused on ROS genes found in all Eukaryotes (such as catalases, superoxide dismutases, glutathione reductases, peroxidases and glutathione peroxidase/peroxiredoxins) as well as those specific to certain groups, such as ascorbate peroxidases, dehydroascorbate/monodehydroascorbate reductases in plants and other photosynthetic organisms. ROS-producing NADPH oxidases (NOX) were found in most multicellular organisms, although several NOX-like genes were identified in unicellular or filamentous species. However, despite the extreme conditions experienced by extremophile species, we found no evidence for expansion of ROS-related gene families in these species compared to other Eukaryotes. Tardigrades and rotifers do show ROS gene expansions that could be related to their extreme lifestyles, although a high rate of lineage-specific horizontal gene transfer events, coupled with recent tetraploidy in rotifers, could explain this observation. This suggests that the basal Eukaryotic ROS scavenging systems are sufficient to maintain ROS homeostasis even under the most extreme conditions.}, language = {en} } @article{NowakGennermannPerssonetal.2020, author = {Nowak, Jacqueline and Gennermann, Kristin and Persson, Staffan and Nikoloski, Zoran}, title = {CytoSeg 2.0}, series = {Bioinformatics}, volume = {36}, journal = {Bioinformatics}, number = {9}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btaa035}, pages = {2950 -- 2951}, year = {2020}, abstract = {Motivation: Actin filaments (AFs) are dynamic structures that substantially change their organization over time. The dynamic behavior and the relatively low signal-to-noise ratio during live-cell imaging have rendered the quantification of the actin organization a difficult task. Results: We developed an automated image-based framework that extracts AFs from fluorescence microscopy images and represents them as networks, which are automatically analyzed to identify and compare biologically relevant features. Although the source code is freely available, we have now implemented the framework into a graphical user interface that can be installed as a Fiji plugin, thus enabling easy access by the research community.}, language = {en} } @article{KuekenWenderingLangaryetal.2021, author = {K{\"u}ken, Anika and Wendering, Philipp and Langary, Damoun and Nikoloski, Zoran}, title = {A structural property for reduction of biochemical networks}, series = {Scientific reports}, volume = {11}, journal = {Scientific reports}, number = {1}, publisher = {Macmillan Publishers Limited, part of Springer Nature}, address = {London}, issn = {2045-2322}, doi = {10.1038/s41598-021-96835-1}, pages = {11}, year = {2021}, abstract = {Large-scale biochemical models are of increasing sizes due to the consideration of interacting organisms and tissues. Model reduction approaches that preserve the flux phenotypes can simplify the analysis and predictions of steady-state metabolic phenotypes. However, existing approaches either restrict functionality of reduced models or do not lead to significant decreases in the number of modelled metabolites. Here, we introduce an approach for model reduction based on the structural property of balancing of complexes that preserves the steady-state fluxes supported by the network and can be efficiently determined at genome scale. Using two large-scale mass-action kinetic models of Escherichia coli, we show that our approach results in a substantial reduction of 99\% of metabolites. Applications to genome-scale metabolic models across kingdoms of life result in up to 55\% and 85\% reduction in the number of metabolites when arbitrary and mass-action kinetics is assumed, respectively. We also show that predictions of the specific growth rate from the reduced models match those based on the original models. Since steady-state flux phenotypes from the original model are preserved in the reduced, the approach paves the way for analysing other metabolic phenotypes in large-scale biochemical networks.}, language = {en} } @article{LangaryNikoloski2019, author = {Langary, Damoun and Nikoloski, Zoran}, title = {Inference of chemical reaction networks based on concentration profiles using an optimization framework}, series = {Chaos : an interdisciplinary journal of nonlinear science}, volume = {29}, journal = {Chaos : an interdisciplinary journal of nonlinear science}, number = {11}, publisher = {American Institute of Physics}, address = {Melville}, issn = {1054-1500}, doi = {10.1063/1.5120598}, pages = {12}, year = {2019}, abstract = {Understanding the structure of reaction networks along with the underlying kinetics that lead to particular concentration readouts of the participating components is the first step toward optimization and control of (bio-)chemical processes. Yet, solutions to the problem of inferring the structure of reaction networks, i.e., characterizing the stoichiometry of the participating reactions provided concentration profiles of the participating components, remain elusive. Here, we present an approach to infer the stoichiometric subspace of a chemical reaction network from steady-state concentration data profiles obtained from a continuous isothermal reactor. The subsequent problem of finding reactions consistent with the observed subspace is cast as a series of mixed-integer linear programs whose solution generates potential reaction vectors together with a measure of their likelihood. We demonstrate the efficiency and applicability of the proposed approach using data obtained from synthetic reaction networks and from a well-established biological model for the Calvin-Benson cycle. Furthermore, we investigate the effect of missing information, in the form of unmeasured species or insufficient diversity within the data set, on the ability to accurately reconstruct the network reactions. The proposed framework is, in principle, applicable to many other reaction systems, thus providing future extensions to understanding reaction networks guiding chemical reactors and complex biological mixtures. (C) 2019 Author(s).}, language = {en} } @article{TongKuekenNikoloski2020, author = {Tong, Hao and K{\"u}ken, Anika and Nikoloski, Zoran}, title = {Integrating molecular markers into metabolic models improves genomic selection for Arabidopsis growth}, series = {Nature Communications}, volume = {11}, journal = {Nature Communications}, number = {1}, publisher = {Nature Publishing Group UK}, address = {London}, issn = {2041-1723}, doi = {10.1038/s41467-020-16279-5}, pages = {9}, year = {2020}, abstract = {The current trends of crop yield improvements are not expected to meet the projected rise in demand. Genomic selection uses molecular markers and machine learning to identify superior genotypes with improved traits, such as growth. Plant growth directly depends on rates of metabolic reactions which transform nutrients into the building blocks of biomass. Here, we predict growth of Arabidopsis thaliana accessions by employing genomic prediction of reaction rates estimated from accession-specific metabolic models. We demonstrate that, comparing to classical genomic selection on the available data sets for 67 accessions, our approach improves the prediction accuracy for growth within and across nitrogen environments by 32.6\% and 51.4\%, respectively, and from optimal nitrogen to low carbon environment by 50.4\%. Therefore, integration of molecular markers into metabolic models offers an approach to predict traits directly related to metabolism, and its usefulness in breeding can be examined by gathering matching datasets in crops. An increase in genomic selection (GS) accuracy can accelerate genetic gain by shortening the breeding cycles. Here, the authors introduce a network-based GS method that uses metabolic models and improves the prediction accuracy of Arabidopsis growth within and across environments.}, language = {en} } @article{MbebiTongNikoloski2021, author = {Mbebi, Alain J. and Tong, Hao and Nikoloski, Zoran}, title = {L-2,L-1-norm regularized multivariate regression model with applications to genomic prediction}, series = {Bioinformatics}, volume = {37}, journal = {Bioinformatics}, number = {18}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btab212}, pages = {2896 -- 2904}, year = {2021}, abstract = {Motivation: Genomic selection (GS) is currently deemed the most effective approach to speed up breeding of agricultural varieties. It has been recognized that consideration of multiple traits in GS can improve accuracy of prediction for traits of low heritability. However, since GS forgoes statistical testing with the idea of improving predictions, it does not facilitate mechanistic understanding of the contribution of particular single nucleotide polymorphisms (SNP). Results: Here, we propose a L-2,L-1-norm regularized multivariate regression model and devise a fast and efficient iterative optimization algorithm, called L-2,L-1-joint, applicable in multi-trait GS. The usage of the L-2,L-1-norm facilitates variable selection in a penalized multivariate regression that considers the relation between individuals, when the number of SNPs is much larger than the number of individuals. The capacity for variable selection allows us to define master regulators that can be used in a multi-trait GS setting to dissect the genetic architecture of the analyzed traits. Our comparative analyses demonstrate that the proposed model is a favorable candidate compared to existing state-of-the-art approaches. Prediction and variable selection with datasets from Brassica napus, wheat and Arabidopsis thaliana diversity panels are conducted to further showcase the performance of the proposed model.}, language = {en} } @article{PriesRazaghiMoghadamKopkaetal.2021, author = {Pries, Christopher and Razaghi-Moghadam, Zahra and Kopka, Joachim and Nikoloski, Zoran}, title = {Integration of relative metabolomics and transcriptomics time-course data in a metabolic model pinpoints effects of ribosome biogenesis defects on Arabidopsis thaliana metabolism}, series = {Scientific reports}, volume = {11}, journal = {Scientific reports}, number = {1}, publisher = {Macmillan Publishers Limited, part of Springer Nature}, address = {London}, issn = {2045-2322}, doi = {10.1038/s41598-021-84114-y}, pages = {12}, year = {2021}, abstract = {Ribosome biogenesis is tightly associated to plant metabolism due to the usage of ribosomes in the synthesis of proteins necessary to drive metabolic pathways. Given the central role of ribosome biogenesis in cell physiology, it is important to characterize the impact of different components involved in this process on plant metabolism. Double mutants of the Arabidopsis thaliana cytosolic 60S maturation factors REIL1 and REIL2 do not resume growth after shift to moderate 10 degrees C chilling conditions. To gain mechanistic insights into the metabolic effects of this ribosome biogenesis defect on metabolism, we developed TC-iReMet2, a constraint-based modelling approach that integrates relative metabolomics and transcriptomics time-course data to predict differential fluxes on a genome-scale level. We employed TC-iReMet2 with metabolomics and transcriptomics data from the Arabidopsis Columbia 0 wild type and the reil1-1 reil2-1 double mutant before and after cold shift. We identified reactions and pathways that are highly altered in a mutant relative to the wild type. These pathways include the Calvin-Benson cycle, photorespiration, gluconeogenesis, and glycolysis. Our findings also indicated differential NAD(P)/NAD(P)H ratios after cold shift. TC-iReMet2 allows for mechanistic hypothesis generation and interpretation of system biology experiments related to metabolic fluxes on a genome-scale level.}, language = {en} } @article{SongLiNowaketal.2019, author = {Song, Yu and Li, Gang and Nowak, Jacqueline and Zhang, Xiaoqing and Xu, Dongbei and Yang, Xiujuan and Huang, Guoqiang and Liang, Wanqi and Yang, Litao and Wang, Canhua and Bulone, Vincent and Nikoloski, Zoran and Hu, Jianping and Persson, Staffan and Zhang, Dabing}, title = {The Rice Actin-Binding Protein RMD Regulates Light-Dependent Shoot Gravitropism}, series = {Plant physiology : an international journal devoted to physiology, biochemistry, cellular and molecular biology, biophysics and environmental biology of plants}, volume = {181}, journal = {Plant physiology : an international journal devoted to physiology, biochemistry, cellular and molecular biology, biophysics and environmental biology of plants}, number = {2}, publisher = {American Society of Plant Physiologists}, address = {Rockville}, issn = {0032-0889}, doi = {10.1104/pp.19.00497}, pages = {630 -- 644}, year = {2019}, abstract = {Light and gravity are two key determinants in orientating plant stems for proper growth and development. The organization and dynamics of the actin cytoskeleton are essential for cell biology and critically regulated by actin-binding proteins. However, the role of actin cytoskeleton in shoot negative gravitropism remains controversial. In this work, we report that the actin-binding protein Rice Morphology Determinant (RMD) promotes reorganization of the actin cytoskeleton in rice (Oryza sativa) shoots. The changes in actin organization are associated with the ability of the rice shoots to respond to negative gravitropism. Here, light-grown rmd mutant shoots exhibited agravitropic phenotypes. By contrast, etiolated rmd shoots displayed normal negative shoot gravitropism. Furthermore, we show that RMD maintains an actin configuration that promotes statolith mobility in gravisensing endodermal cells, and for proper auxin distribution in light-grown, but not dark-grown, shoots. RMD gene expression is diurnally controlled and directly repressed by the phytochrome-interacting factor-like protein OsPIL16. Consequently, overexpression of OsPIL16 led to gravisensing and actin patterning defects that phenocopied the rmd mutant. Our findings outline a mechanism that links light signaling and gravity perception for straight shoot growth in rice.}, language = {en} } @article{ApeltBreuerOlasetal.2017, author = {Apelt, Federico and Breuer, David and Olas, Justyna Jadwiga and Annunziata, Maria Grazia and Flis, Anna and Nikoloski, Zoran and Kragler, Friedrich and Stitt, Mark}, title = {Circadian, Carbon, and Light Control of Expansion Growth and Leaf Movement}, series = {Plant physiology : an international journal devoted to physiology, biochemistry, cellular and molecular biology, biophysics and environmental biology of plants}, volume = {174}, journal = {Plant physiology : an international journal devoted to physiology, biochemistry, cellular and molecular biology, biophysics and environmental biology of plants}, publisher = {American Society of Plant Physiologists}, address = {Rockville}, issn = {0032-0889}, doi = {10.1104/pp.17.00503}, pages = {1949 -- 1968}, year = {2017}, language = {en} } @article{XuRazaghiMoghadamNikoloski2021, author = {Xu, Rudan and Razaghi-Moghadam, Zahra and Nikoloski, Zoran}, title = {Maximization of non-idle enzymes improves the coverage of the estimated maximal in vivo enzyme catalytic rates in Escherichia coli}, series = {Bioinformatics}, volume = {37}, journal = {Bioinformatics}, number = {21}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btab575}, pages = {3848 -- 3855}, year = {2021}, abstract = {Motivation: Constraint-based modeling approaches allow the estimation of maximal in vivo enzyme catalytic rates that can serve as proxies for enzyme turnover numbers. Yet, genome-scale flux profiling remains a challenge in deploying these approaches to catalogue proxies for enzyme catalytic rates across organisms. Results: Here, we formulate a constraint-based approach, termed NIDLE-flux, to estimate fluxes at a genome-scale level by using the principle of efficient usage of expressed enzymes. Using proteomics data from Escherichia coli, we show that the fluxes estimated by NIDLE-flux and the existing approaches are in excellent qualitative agreement (Pearson correlation > 0.9). We also find that the maximal in vivo catalytic rates estimated by NIDLE-flux exhibits a Pearson correlation of 0.74 with in vitro enzyme turnover numbers. However, NIDLE-flux results in a 1.4-fold increase in the size of the estimated maximal in vivo catalytic rates in comparison to the contenders. Integration of the maximum in vivo catalytic rates with publically available proteomics and metabolomics data provide a better match to fluxes estimated by NIDLE-flux. Therefore, NIDLE-flux facilitates more effective usage of proteomics data to estimate proxies for kcatomes.}, language = {en} } @article{MettlerMuehlhausHemmeetal.2014, author = {Mettler, Tabea and M{\"u}hlhaus, Timo and Hemme, Dorothea and Sch{\"o}ttler, Mark Aurel and Rupprecht, Jens and Idoine, Adam and Veyel, Daniel and Pal, Sunil Kumar and Yaneva-Roder, Liliya and Winck, Flavia Vischi and Sommer, Frederik and Vosloh, Daniel and Seiwert, Bettina and Erban, Alexander and Burgos, Asdrubal and Arvidsson, Samuel Janne and Schoenfelder, Stephanie and Arnold, Anne and Guenther, Manuela and Krause, Ursula and Lohse, Marc and Kopka, Joachim and Nikoloski, Zoran and M{\"u}ller-R{\"o}ber, Bernd and Willmitzer, Lothar and Bock, Ralph and Schroda, Michael and Stitt, Mark}, title = {Systems analysis of the response of photosynthesis, metabolism, and growth to an increase in irradiance in the photosynthetic model organism chlamydomonas reinhardtii}, series = {The plant cell}, volume = {26}, journal = {The plant cell}, number = {6}, publisher = {American Society of Plant Physiologists}, address = {Rockville}, issn = {1040-4651}, doi = {10.1105/tpc.114.124537}, pages = {2310 -- 2350}, year = {2014}, abstract = {We investigated the systems response of metabolism and growth after an increase in irradiance in the nonsaturating range in the algal model Chlamydomonas reinhardtii. In a three-step process, photosynthesis and the levels of metabolites increased immediately, growth increased after 10 to 15 min, and transcript and protein abundance responded by 40 and 120 to 240 min, respectively. In the first phase, starch and metabolites provided a transient buffer for carbon until growth increased. This uncouples photosynthesis from growth in a fluctuating light environment. In the first and second phases, rising metabolite levels and increased polysome loading drove an increase in fluxes. Most Calvin-Benson cycle (CBC) enzymes were substrate-limited in vivo, and strikingly, many were present at higher concentrations than their substrates, explaining how rising metabolite levels stimulate CBC flux. Rubisco, fructose-1,6-biosphosphatase, and seduheptulose-1,7-bisphosphatase were close to substrate saturation in vivo, and flux was increased by posttranslational activation. In the third phase, changes in abundance of particular proteins, including increases in plastidial ATP synthase and some CBC enzymes, relieved potential bottlenecks and readjusted protein allocation between different processes. Despite reasonable overall agreement between changes in transcript and protein abundance (R-2 = 0.24), many proteins, including those in photosynthesis, changed independently of transcript abundance.}, language = {en} } @article{OmranianEloundouMbebiMuellerRoeberetal.2016, author = {Omranian, Nooshin and Eloundou-Mbebi, Jeanne Marie Onana and M{\"u}ller-R{\"o}ber, Bernd and Nikoloski, Zoran}, title = {Gene regulatory network inference using fused LASSO on multiple data sets}, series = {Scientific reports}, volume = {6}, journal = {Scientific reports}, publisher = {Nature Publ. Group}, address = {London}, issn = {2045-2322}, doi = {10.1038/srep20533}, pages = {14}, year = {2016}, abstract = {Devising computational methods to accurately reconstruct gene regulatory networks given gene expression data is key to systems biology applications. Here we propose a method for reconstructing gene regulatory networks by simultaneous consideration of data sets from different perturbation experiments and corresponding controls. The method imposes three biologically meaningful constraints: (1) expression levels of each gene should be explained by the expression levels of a small number of transcription factor coding genes, (2) networks inferred from different data sets should be similar with respect to the type and number of regulatory interactions, and (3) relationships between genes which exhibit similar differential behavior over the considered perturbations should be favored. We demonstrate that these constraints can be transformed in a fused LASSO formulation for the proposed method. The comparative analysis on transcriptomics time-series data from prokaryotic species, Escherichia coli and Mycobacterium tuberculosis, as well as a eukaryotic species, mouse, demonstrated that the proposed method has the advantages of the most recent approaches for regulatory network inference, while obtaining better performance and assigning higher scores to the true regulatory links. The study indicates that the combination of sparse regression techniques with other biologically meaningful constraints is a promising framework for gene regulatory network reconstructions.}, language = {en} } @article{OmranianKlieMuellerRoeberetal.2013, author = {Omranian, Nooshin and Klie, Sebastian and M{\"u}ller-R{\"o}ber, Bernd and Nikoloski, Zoran}, title = {Network-based segmentation of biological multivariate time series}, series = {PLoS one}, volume = {8}, journal = {PLoS one}, number = {5}, publisher = {PLoS}, address = {San Fransisco}, issn = {1932-6203}, doi = {10.1371/journal.pone.0062974}, pages = {10}, year = {2013}, abstract = {Molecular phenotyping technologies (e.g., transcriptomics, proteomics, and metabolomics) offer the possibility to simultaneously obtain multivariate time series (MTS) data from different levels of information processing and metabolic conversions in biological systems. As a result, MTS data capture the dynamics of biochemical processes and components whose couplings may involve different scales and exhibit temporal changes. Therefore, it is important to develop methods for determining the time segments in MTS data, which may correspond to critical biochemical events reflected in the coupling of the system's components. Here we provide a novel network-based formalization of the MTS segmentation problem based on temporal dependencies and the covariance structure of the data. We demonstrate that the problem of partitioning MTS data into k segments to maximize a distance function, operating on polynomially computable network properties, often used in analysis of biological network, can be efficiently solved. To enable biological interpretation, we also propose a breakpoint-penalty (BP-penalty) formulation for determining MTS segmentation which combines a distance function with the number/length of segments. Our empirical analyses of synthetic benchmark data as well as time-resolved transcriptomics data from the metabolic and cell cycles of Saccharomyces cerevisiae demonstrate that the proposed method accurately infers the phases in the temporal compartmentalization of biological processes. In addition, through comparison on the same data sets, we show that the results from the proposed formalization of the MTS segmentation problem match biological knowledge and provide more rigorous statistical support in comparison to the contending state-of-the-art methods.}, language = {en} } @article{AlseekhTohgeWendenbergetal.2015, author = {Alseekh, Saleh and Tohge, Takayuki and Wendenberg, Regina and Scossa, Federico and Omranian, Nooshin and Li, Jie and Kleessen, Sabrina and Giavalisco, Patrick and Pleban, Tzili and M{\"u}ller-R{\"o}ber, Bernd and Zamir, Dani and Nikoloski, Zoran and Fernie, Alisdair R.}, title = {Identification and Mode of Inheritance of Quantitative Trait Loci for Secondary Metabolite Abundance in Tomato}, series = {The plant cell}, volume = {27}, journal = {The plant cell}, number = {3}, publisher = {American Society of Plant Physiologists}, address = {Rockville}, issn = {1040-4651}, doi = {10.1105/tpc.114.132266}, pages = {485 -- 512}, year = {2015}, abstract = {A large-scale metabolic quantitative trait loci (mQTL) analysis was performed on the well-characterized Solanum pennellii introgression lines to investigate the genomic regions associated with secondary metabolism in tomato fruit pericarp. In total, 679 mQTLs were detected across the 76 introgression lines. Heritability analyses revealed that mQTLs of secondary metabolism were less affected by environment than mQTLs of primary metabolism. Network analysis allowed us to assess the interconnectivity of primary and secondary metabolism as well as to compare and contrast their respective associations with morphological traits. Additionally, we applied a recently established real-time quantitative PCR platform to gain insight into transcriptional control mechanisms of a subset of the mQTLs, including those for hydroxycinnamates, acyl-sugar, naringenin chalcone, and a range of glycoalkaloids. Intriguingly, many of these compounds displayed a dominant-negative mode of inheritance, which is contrary to the conventional wisdom that secondary metabolite contents decreased on domestication. We additionally performed an exemplary evaluation of two candidate genes for glycolalkaloid mQTLs via the use of virus-induced gene silencing. The combined data of this study were compared with previous results on primary metabolism obtained from the same material and to other studies of natural variance of secondary metabolism.}, language = {en} } @article{OmranianMuellerRoeberNikoloski2015, author = {Omranian, Nooshin and M{\"u}ller-R{\"o}ber, Bernd and Nikoloski, Zoran}, title = {Segmentation of biological multivariate time-series data}, series = {Scientific reports}, volume = {5}, journal = {Scientific reports}, publisher = {Nature Publ. Group}, address = {London}, issn = {2045-2322}, doi = {10.1038/srep08937}, pages = {6}, year = {2015}, abstract = {Time-series data from multicomponent systems capture the dynamics of the ongoing processes and reflect the interactions between the components. The progression of processes in such systems usually involves check-points and events at which the relationships between the components are altered in response to stimuli. Detecting these events together with the implicated components can help understand the temporal aspects of complex biological systems. Here we propose a regularized regression-based approach for identifying breakpoints and corresponding segments from multivariate time-series data. In combination with techniques from clustering, the approach also allows estimating the significance of the determined breakpoints as well as the key components implicated in the emergence of the breakpoints. Comparative analysis with the existing alternatives demonstrates the power of the approach to identify biologically meaningful breakpoints in diverse time-resolved transcriptomics data sets from the yeast Saccharomyces cerevisiae and the diatom Thalassiosira pseudonana.}, language = {en} } @article{JanowskiZoschkeScharffetal.2018, author = {Janowski, Marcin Andrzej and Zoschke, Reimo and Scharff, Lars B. and Jaime, Silvia Martinez and Ferrari, Camilla and Proost, Sebastian and Xiong, Jonathan Ng Wei and Omranian, Nooshin and Musialak-Lange, Magdalena and Nikoloski, Zoran and Graf, Alexander and Schoettler, Mark Aurel and Sampathkumar, Arun and Vaid, Neha and Mutwil, Marek}, title = {AtRsgA from Arabidopsis thaliana is important for maturation of the small subunit of the chloroplast ribosome}, series = {The plant journal}, volume = {96}, journal = {The plant journal}, number = {2}, publisher = {Wiley}, address = {Hoboken}, issn = {0960-7412}, doi = {10.1111/tpj.14040}, pages = {404 -- 420}, year = {2018}, abstract = {Plastid ribosomes are very similar in structure and function to the ribosomes of their bacterial ancestors. Since ribosome biogenesis is not thermodynamically favorable under biological conditions it requires the activity of many assembly factors. Here we have characterized a homolog of bacterial RsgA in Arabidopsis thaliana and show that it can complement the bacterial homolog. Functional characterization of a strong mutant in Arabidopsis revealed that the protein is essential for plant viability, while a weak mutant produced dwarf, chlorotic plants that incorporated immature pre-16S ribosomal RNA into translating ribosomes. Physiological analysis of the mutant plants revealed smaller, but more numerous, chloroplasts in the mesophyll cells, reduction of chlorophyll a and b, depletion of proplastids from the rib meristem and decreased photosynthetic electron transport rate and efficiency. Comparative RNA sequencing and proteomic analysis of the weak mutant and wild-type plants revealed that various biotic stress-related, transcriptional regulation and post-transcriptional modification pathways were repressed in the mutant. Intriguingly, while nuclear- and chloroplast-encoded photosynthesis-related proteins were less abundant in the mutant, the corresponding transcripts were increased, suggesting an elaborate compensatory mechanism, potentially via differentially active retrograde signaling pathways. To conclude, this study reveals a chloroplast ribosome assembly factor and outlines the transcriptomic and proteomic responses of the compensatory mechanism activated during decreased chloroplast function. Significance Statement AtRsgA is an assembly factor necessary for maturation of the small subunit of the chloroplast ribosome. Depletion of AtRsgA leads to dwarfed, chlorotic plants, a decrease of mature 16S rRNA and smaller, but more numerous, chloroplasts. Large-scale transcriptomic and proteomic analysis revealed that chloroplast-encoded and -targeted proteins were less abundant, while the corresponding transcripts were increased in the mutant. We analyze the transcriptional responses of several retrograde signaling pathways to suggest the mechanism underlying this compensatory response.}, language = {en} } @article{WenderingNikoloski2022, author = {Wendering, Philipp and Nikoloski, Zoran}, title = {COMMIT}, series = {PLoS Computational Biology : a new community journal / publ. by the Public Library of Science (PLoS) in association with the International Society for Computational Biology (ISCB)}, volume = {18}, journal = {PLoS Computational Biology : a new community journal / publ. by the Public Library of Science (PLoS) in association with the International Society for Computational Biology (ISCB)}, number = {3}, publisher = {Public Library of Science}, address = {San Fransisco}, issn = {1553-734X}, doi = {10.1371/journal.pcbi.1009906}, pages = {24}, year = {2022}, abstract = {Composition and functions of microbial communities affect important traits in diverse hosts, from crops to humans. Yet, mechanistic understanding of how metabolism of individual microbes is affected by the community composition and metabolite leakage is lacking. Here, we first show that the consensus of automatically generated metabolic reconstructions improves the quality of the draft reconstructions, measured by comparison to reference models. We then devise an approach for gap filling, termed COMMIT, that considers metabolites for secretion based on their permeability and the composition of the community. By applying COMMIT with two soil communities from the Arabidopsis thaliana culture collection, we could significantly reduce the gap-filling solution in comparison to filling gaps in individual reconstructions without affecting the genomic support. Inspection of the metabolic interactions in the soil communities allows us to identify microbes with community roles of helpers and beneficiaries. Therefore, COMMIT offers a versatile fully automated solution for large-scale modelling of microbial communities for diverse biotechnological applications.
Author summaryMicrobial communities are important in ecology, human health, and crop productivity. However, detailed information on the interactions within natural microbial communities is hampered by the community size, lack of detailed information on the biochemistry of single organisms, and the complexity of interactions between community members. Metabolic models are comprised of biochemical reaction networks based on the genome annotation, and can provide mechanistic insights into community functions. Previous analyses of microbial community models have been performed with high-quality reference models or models generated using a single reconstruction pipeline. However, these models do not contain information on the composition of the community that determines the metabolites exchanged between the community members. In addition, the quality of metabolic models is affected by the reconstruction approach used, with direct consequences on the inferred interactions between community members. Here, we use fully automated consensus reconstructions from four approaches to arrive at functional models with improved genomic support while considering the community composition. We applied our pipeline to two soil communities from the Arabidopsis thaliana culture collection, providing only genome sequences. Finally, we show that the obtained models have 90\% genomic support and demonstrate that the derived interactions are corroborated by independent computational predictions.}, language = {en} } @article{TongKuekenRazaghiMoghadametal.2021, author = {Tong, Hao and K{\"u}ken, Anika and Razaghi-Moghadam, Zahra and Nikoloski, Zoran}, title = {Characterization of effects of genetic variants via genome-scale metabolic modelling}, series = {Cellular and molecular life sciences : CMLS}, volume = {78}, journal = {Cellular and molecular life sciences : CMLS}, number = {12}, publisher = {Springer International Publishing AG}, address = {Cham}, issn = {1420-682X}, doi = {10.1007/s00018-021-03844-4}, pages = {5123 -- 5138}, year = {2021}, abstract = {Genome-scale metabolic networks for model plants and crops in combination with approaches from the constraint-based modelling framework have been used to predict metabolic traits and design metabolic engineering strategies for their manipulation. With the advances in technologies to generate large-scale genotyping data from natural diversity panels and other populations, genome-wide association and genomic selection have emerged as statistical approaches to determine genetic variants associated with and predictive of traits. Here, we review recent advances in constraint-based approaches that integrate genetic variants in genome-scale metabolic models to characterize their effects on reaction fluxes. Since some of these approaches have been applied in organisms other than plants, we provide a critical assessment of their applicability particularly in crops. In addition, we further dissect the inferred effects of genetic variants with respect to reaction rate constants, abundances of enzymes, and concentrations of metabolites, as main determinants of reaction fluxes and relate them with their combined effects on complex traits, like growth. Through this systematic review, we also provide a roadmap for future research to increase the predictive power of statistical approaches by coupling them with mechanistic models of metabolism.}, language = {en} } @article{WinckArvidssonMauricioRianoPachonetal.2013, author = {Winck, Flavia Vischi and Arvidsson, Samuel Janne and Mauricio Riano-Pachon, Diego and Hempel, Sabrina and Koseska, Aneta and Nikoloski, Zoran and Urbina Gomez, David Alejandro and Rupprecht, Jens and M{\"u}ller-R{\"o}ber, Bernd}, title = {Genome-wide identification of regulatory elements and reconstruction of gene regulatory networks of the green alga chlamydomonas reinhardtii under carbon deprivation}, series = {PLoS one}, volume = {8}, journal = {PLoS one}, number = {11}, publisher = {PLoS}, address = {San Fransisco}, issn = {1932-6203}, doi = {10.1371/journal.pone.0079909}, pages = {16}, year = {2013}, abstract = {The unicellular green alga Chlamydomonas reinhardtii is a long-established model organism for studies on photosynthesis and carbon metabolism-related physiology. Under conditions of air-level carbon dioxide concentration [CO2], a carbon concentrating mechanism (CCM) is induced to facilitate cellular carbon uptake. CCM increases the availability of carbon dioxide at the site of cellular carbon fixation. To improve our understanding of the transcriptional control of the CCM, we employed FAIRE-seq (formaldehyde-assisted Isolation of Regulatory Elements, followed by deep sequencing) to determine nucleosome-depleted chromatin regions of algal cells subjected to carbon deprivation. Our FAIRE data recapitulated the positions of known regulatory elements in the promoter of the periplasmic carbonic anhydrase (Cah1) gene, which is upregulated during CCM induction, and revealed new candidate regulatory elements at a genome-wide scale. In addition, time series expression patterns of 130 transcription factor (TF) and transcription regulator (TR) genes were obtained for cells cultured under photoautotrophic condition and subjected to a shift from high to low [CO2]. Groups of co-expressed genes were identified and a putative directed gene-regulatory network underlying the CCM was reconstructed from the gene expression data using the recently developed IOTA (inner composition alignment) method. Among the candidate regulatory genes, two members of the MYB-related TF family, Lcr1 (Low-CO2 response regulator 1) and Lcr2 (Low-CO2 response regulator 2), may play an important role in down-regulating the expression of a particular set of TF and TR genes in response to low [CO2]. The results obtained provide new insights into the transcriptional control of the CCM and revealed more than 60 new candidate regulatory genes. Deep sequencing of nucleosome-depleted genomic regions indicated the presence of new, previously unknown regulatory elements in the C. reinhardtii genome. Our work can serve as a basis for future functional studies of transcriptional regulator genes and genomic regulatory elements in Chlamydomonas.}, language = {en} } @article{OmranianMuellerRoeberNikoloski2012, author = {Omranian, Nooshin and M{\"u}ller-R{\"o}ber, Bernd and Nikoloski, Zoran}, title = {PageRank-based identification of signaling crosstalk from transcriptomics data the case of Arabidopsis thaliana}, series = {Molecular BioSystems}, volume = {8}, journal = {Molecular BioSystems}, number = {4}, publisher = {Royal Society of Chemistry}, address = {Cambridge}, issn = {1742-206X}, doi = {10.1039/c2mb05365a}, pages = {1121 -- 1127}, year = {2012}, abstract = {The levels of cellular organization, from gene transcription to translation to protein-protein interaction and metabolism, operate via tightly regulated mutual interactions, facilitating organismal adaptability and various stress responses. Characterizing the mutual interactions between genes, transcription factors, and proteins involved in signaling, termed crosstalk, is therefore crucial for understanding and controlling cells' functionality. We aim at using high-throughput transcriptomics data to discover previously unknown links between signaling networks. We propose and analyze a novel method for crosstalk identification which relies on transcriptomics data and overcomes the lack of complete information for signaling pathways in Arabidopsis thaliana. Our method first employs a network-based transformation of the results from the statistical analysis of differential gene expression in given groups of experiments under different signal-inducing conditions. The stationary distribution of a random walk (similar to the PageRank algorithm) on the constructed network is then used to determine the putative transcripts interrelating different signaling pathways. With the help of the proposed method, we analyze a transcriptomics data set including experiments from four different stresses/signals: nitrate, sulfur, iron, and hormones. We identified promising gene candidates, downstream of the transcription factors (TFs), associated to signaling crosstalk, which were validated through literature mining. In addition, we conduct a comparative analysis with the only other available method in this field which used a biclustering-based approach. Surprisingly, the biclustering-based approach fails to robustly identify any candidate genes involved in the crosstalk of the analyzed signals. We demonstrate that our proposed method is more robust in identifying gene candidates involved downstream of the signaling crosstalk for species for which large transcriptomics data sets, normalized with the same techniques, are available. Moreover, unlike approaches based on biclustering, our approach does not rely on any hidden parameters.}, language = {en} } @misc{OmranianKleessenTohgeetal.2015, author = {Omranian, Nooshin and Kleessen, Sabrina and Tohge, Takayuki and Klie, Sebastian and Basler, Georg and M{\"u}ller-R{\"o}ber, Bernd and Fernie, Alisdair R. and Nikoloski, Zoran}, title = {Differential metabolic and coexpression networks of plant metabolism}, series = {Trends in plant science}, volume = {20}, journal = {Trends in plant science}, number = {5}, publisher = {Elsevier}, address = {London}, issn = {1360-1385}, doi = {10.1016/j.tplants.2015.02.002}, pages = {266 -- 268}, year = {2015}, abstract = {Recent analyses have demonstrated that plant metabolic networks do not differ in their structural properties and that genes involved in basic metabolic processes show smaller coexpression than genes involved in specialized metabolism. By contrast, our analysis reveals differences in the structure of plant metabolic networks and patterns of coexpression for genes in (non)specialized metabolism. Here we caution that conclusions concerning the organization of plant metabolism based on network-driven analyses strongly depend on the computational approaches used.}, language = {en} } @article{TongNankarLiuetal.2022, author = {Tong, Hao and Nankar, Amol N. and Liu, Jintao and Todorova, Velichka and Ganeva, Daniela and Grozeva, Stanislava and Tringovska, Ivanka and Pasev, Gancho and Radeva-Ivanova, Vesela and Gechev, Tsanko and Kostova, Dimitrina and Nikoloski, Zoran}, title = {Genomic prediction of morphometric and colorimetric traits in Solanaceous fruits}, series = {Horticulture research}, volume = {9}, journal = {Horticulture research}, publisher = {Oxford Univ. Press}, address = {Cary}, issn = {2052-7276}, doi = {10.1093/hr/uhac072}, pages = {11}, year = {2022}, abstract = {Selection of high-performance lines with respect to traits of interest is a key step in plant breeding. Genomic prediction allows to determine the genomic estimated breeding values of unseen lines for trait of interest using genetic markers, e.g. single-nucleotide polymorphisms (SNPs), and machine learning approaches, which can therefore shorten breeding cycles, referring to genomic selection (GS). Here, we applied GS approaches in two populations of Solanaceous crops, i.e. tomato and pepper, to predict morphometric and colorimetric traits. The traits were measured by using scoring-based conventional descriptors (CDs) as well as by Tomato Analyzer (TA) tool using the longitudinally and latitudinally cut fruit images. The GS performance was assessed in cross-validations of classification-based and regression-based machine learning models for CD and TA traits, respectively. The results showed the usage of TA traits and tag SNPs provide a powerful combination to predict morphology and color-related traits of Solanaceous fruits. The highest predictability of 0.89 was achieved for fruit width in pepper, with an average predictability of 0.69 over all traits. The multi-trait GS models are of slightly better predictability than single-trait models for some colorimetric traits in pepper. While model validation performs poorly on wild tomato accessions, the usage as many as one accession per wild species in the training set can increase the transferability of models to unseen populations for some traits (e.g. fruit shape for which predictability in unseen scenario increased from zero to 0.6). Overall, GS approaches can assist the selection of high-performance Solanaceous fruits in crop breeding.}, language = {en} } @article{AngeleskaOmranianNikoloski2021, author = {Angeleska, Angela and Omranian, Sara and Nikoloski, Zoran}, title = {Coherent network partitions}, series = {Theoretical computer science : the journal of the EATCS}, volume = {894}, journal = {Theoretical computer science : the journal of the EATCS}, publisher = {Elsevier}, address = {Amsterdam [u.a.]}, issn = {0304-3975}, doi = {10.1016/j.tcs.2021.10.002}, pages = {3 -- 11}, year = {2021}, abstract = {We continue to study coherent partitions of graphs whereby the vertex set is partitioned into subsets that induce biclique spanned subgraphs. The problem of identifying the minimum number of edges to obtain biclique spanned connected components (CNP), called the coherence number, is NP-hard even on bipartite graphs. Here, we propose a graph transformation geared towards obtaining an O (log n)-approximation algorithm for the CNP on a bipartite graph with n vertices. The transformation is inspired by a new characterization of biclique spanned subgraphs. In addition, we study coherent partitions on prime graphs, and show that finding coherent partitions reduces to the problem of finding coherent partitions in a prime graph. Therefore, these results provide future directions for approximation algorithms for the coherence number of a given graph.}, language = {en} } @misc{OmranianNikoloskiGrimm2022, author = {Omranian, Sara and Nikoloski, Zoran and Grimm, Dominik G.}, title = {Computational identification of protein complexes from network interactions: Present state, challenges, and the way forward}, series = {Computational and structural biotechnology journal}, volume = {20}, journal = {Computational and structural biotechnology journal}, publisher = {Research Network of Computational and Structural Biotechnology (RNCSB)}, address = {Gotenburg}, issn = {2001-0370}, doi = {10.1016/j.csbj.2022.05.049}, pages = {2699 -- 2712}, year = {2022}, abstract = {Physically interacting proteins form macromolecule complexes that drive diverse cellular processes. Advances in experimental techniques that capture interactions between proteins provide us with protein-protein interaction (PPI) networks from several model organisms. These datasets have enabled the prediction and other computational analyses of protein complexes. Here we provide a systematic review of the state-of-the-art algorithms for protein complex prediction from PPI networks proposed in the past two decades. The existing approaches that solve this problem are categorized into three groups, including: cluster-quality-based, node affinity-based, and network embedding-based approaches, and we compare and contrast the advantages and disadvantages. We further include a comparative analysis by computing the performance of eighteen methods based on twelve well-established performance measures on four widely used benchmark protein-protein interaction networks. Finally, the limitations and drawbacks of both, current data and approaches, along with the potential solutions in this field are discussed, with emphasis on the points that pave the way for future research efforts in this field. (c) 2022 The Author(s). Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology. This is an open access article under the CC BY license (http://creativecommons. org/licenses/by/4.0/).}, language = {en} } @article{OmranianAngeleskaNikoloski2021, author = {Omranian, Sara and Angeleska, Angela and Nikoloski, Zoran}, title = {Efficient and accurate identification of protein complexes from protein-protein interaction networks based on the clustering coefficient}, series = {Computational and structural biotechnology journal}, volume = {19}, journal = {Computational and structural biotechnology journal}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2001-0370}, doi = {10.1016/j.csbj.2021.09.014}, pages = {5255 -- 5263}, year = {2021}, abstract = {Identification of protein complexes from protein-protein interaction (PPI) networks is a key problem in PPI mining, solved by parameter-dependent approaches that suffer from small recall rates. Here we introduce GCC-v, a family of efficient, parameter-free algorithms to accurately predict protein complexes using the (weighted) clustering coefficient of proteins in PPI networks. Through comparative analyses with gold standards and PPI networks from Escherichia coli, Saccharomyces cerevisiae, and Homo sapiens, we demonstrate that GCC-v outperforms twelve state-of-the-art approaches for identification of protein complexes with respect to twelve performance measures in at least 85.71\% of scenarios. We also show that GCC-v results in the exact recovery of similar to 35\% of protein complexes in a pan-plant PPI network and discover 144 new protein complexes in Arabidopsis thaliana, with high support from GO semantic similarity. Our results indicate that findings from GCC-v are robust to network perturbations, which has direct implications to assess the impact of the PPI network quality on the predicted protein complexes. (C) 2021 The Author(s). Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology.}, language = {en} } @article{HussJuddKoperetal.2022, author = {Huß, Sebastian and Judd, Rika Siedah and Koper, Kaan and Maeda, Hiroshi A. and Nikoloski, Zoran}, title = {An automated workflow that generates atom mappings for large-scale metabolic models and its application to Arabidopsis thaliana}, series = {The plant journal}, volume = {111}, journal = {The plant journal}, number = {5}, publisher = {Wiley-Blackwell}, address = {Oxford [u.a.]}, issn = {0960-7412}, doi = {10.1111/tpj.15903}, pages = {1486 -- 1500}, year = {2022}, abstract = {Quantification of reaction fluxes of metabolic networks can help us understand how the integration of different metabolic pathways determines cellular functions. Yet, intracellular fluxes cannot be measured directly but are estimated with metabolic flux analysis (MFA), which relies on the patterns of isotope labeling of metabolites in the network. The application of MFA also requires a stoichiometric model with atom mappings that are currently not available for the majority of large-scale metabolic network models, particularly of plants. While automated approaches such as the Reaction Decoder Toolkit (RDT) can produce atom mappings for individual reactions, tracing the flow of individual atoms of the entire reactions across a metabolic model remains challenging. Here we establish an automated workflow to obtain reliable atom mappings for large-scale metabolic models by refining the outcome of RDT, and apply the workflow to metabolic models of Arabidopsis thaliana. We demonstrate the accuracy of RDT through a comparative analysis with atom mappings from a large database of biochemical reactions, MetaCyc. We further show the utility of our automated workflow by simulating N-15 isotope enrichment and identifying nitrogen (N)-containing metabolites which show enrichment patterns that are informative for flux estimation in future N-15-MFA studies of A. thaliana. The automated workflow established in this study can be readily expanded to other species for which metabolic models have been established and the resulting atom mappings will facilitate MFA and graph-theoretic structural analyses with large-scale metabolic networks.}, language = {en} }