@article{OmranianAngeleskaNikoloski2021, author = {Omranian, Sara and Angeleska, Angela and Nikoloski, Zoran}, title = {PC2P}, series = {Bioinformatics}, volume = {37}, journal = {Bioinformatics}, number = {1}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btaa1089}, pages = {73 -- 81}, year = {2021}, abstract = {Motivation: Prediction of protein complexes from protein-protein interaction (PPI) networks is an important problem in systems biology, as they control different cellular functions. The existing solutions employ algorithms for network community detection that identify dense subgraphs in PPI networks. However, gold standards in yeast and human indicate that protein complexes can also induce sparse subgraphs, introducing further challenges in protein complex prediction. Results: To address this issue, we formalize protein complexes as biclique spanned subgraphs, which include both sparse and dense subgraphs. We then cast the problem of protein complex prediction as a network partitioning into biclique spanned subgraphs with removal of minimum number of edges, called coherent partition. Since finding a coherent partition is a computationally intractable problem, we devise a parameter-free greedy approximation algorithm, termed Protein Complexes from Coherent Partition (PC2P), based on key properties of biclique spanned subgraphs. Through comparison with nine contenders, we demonstrate that PC2P: (i) successfully identifies modular structure in networks, as a prerequisite for protein complex prediction, (ii) outperforms the existing solutions with respect to a composite score of five performance measures on 75\% and 100\% of the analyzed PPI networks and gold standards in yeast and human, respectively, and (iii,iv) does not compromise GO semantic similarity and enrichment score of the predicted protein complexes. Therefore, our study demonstrates that clustering of networks in terms of biclique spanned subgraphs is a promising framework for detection of complexes in PPI networks.}, 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{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{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{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{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{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{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{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{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{CalderanRodriguesLuzarowskiMonteBelloetal.2021, author = {Calderan-Rodrigues, Maria Juliana and Luzarowski, Marcin and Monte-Bello, Carolina Cassano and Minen, Romina Ines and Z{\"u}hlke, Boris M. and Nikoloski, Zoran and Skirycz, Aleksandra and Caldana, Camila}, title = {Proteogenic dipeptides are characterized by diel fluctuations and target of rapamycin complex-signaling dependency in the model plant Arabidopsis thaliana}, series = {Frontiers in plant science : FPLS}, volume = {12}, journal = {Frontiers in plant science : FPLS}, publisher = {Frontiers Media}, address = {Lausanne}, issn = {1664-462X}, doi = {10.3389/fpls.2021.758933}, pages = {15}, year = {2021}, abstract = {As autotrophic organisms, plants capture light energy to convert carbon dioxide into ATP, nicotinamide adenine dinucleotide phosphate (NADPH), and sugars, which are essential for the biosynthesis of building blocks, storage, and growth. At night, metabolism and growth can be sustained by mobilizing carbon (C) reserves. In response to changing environmental conditions, such as light-dark cycles, the small-molecule regulation of enzymatic activities is critical for reprogramming cellular metabolism. We have recently demonstrated that proteogenic dipeptides, protein degradation products, act as metabolic switches at the interface of proteostasis and central metabolism in both plants and yeast. Dipeptides accumulate in response to the environmental changes and act via direct binding and regulation of critical enzymatic activities, enabling C flux distribution. Here, we provide evidence pointing to the involvement of dipeptides in the metabolic rewiring characteristics for the day-night cycle in plants. Specifically, we measured the abundance of 13 amino acids and 179 dipeptides over short- (SD) and long-day (LD) diel cycles, each with different light intensities. Of the measured dipeptides, 38 and eight were characterized by day-night oscillation in SD and LD, respectively, reaching maximum accumulation at the end of the day and then gradually falling in the night. Not only the number of dipeptides, but also the amplitude of the oscillation was higher in SD compared with LD conditions. Notably, rhythmic dipeptides were enriched in the glucogenic amino acids that can be converted into glucose. Considering the known role of Target of Rapamycin (TOR) signaling in regulating both autophagy and metabolism, we subsequently investigated whether diurnal fluctuations of dipeptides levels are dependent on the TOR Complex (TORC). The Raptor1b mutant (raptor1b), known for the substantial reduction of TOR kinase activity, was characterized by the augmented accumulation of dipeptides, which is especially pronounced under LD conditions. We were particularly intrigued by the group of 16 dipeptides, which, based on their oscillation under SD conditions and accumulation in raptor1b, can be associated with limited C availability or photoperiod. By mining existing protein-metabolite interaction data, we delineated putative protein interactors for a representative dipeptide Pro-Gln. The obtained list included enzymes of C and amino acid metabolism, which are also linked to the TORC-mediated metabolic network. Based on the obtained results, we speculate that the diurnal accumulation of dipeptides contributes to its metabolic adaptation in response to changes in C availability. We hypothesize that dipeptides would act as alternative respiratory substrates and by directly modulating the activity of the focal enzymes.}, 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{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{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{MbebiBreitlerBordeauxetal.2022, author = {Mbebi, Alain J. and Breitler, Jean-Christophe and Bordeaux, M'elanie and Sulpice, Ronan and McHale, Marcus and Tong, Hao and Toniutti, Lucile and Castillo, Jonny Alonso and Bertrand, Benoit and Nikoloski, Zoran}, title = {A comparative analysis of genomic and phenomic predictions of growth-related traits in 3-way coffee hybrids}, series = {G3: Genes, genomes, genetics}, volume = {12}, journal = {G3: Genes, genomes, genetics}, number = {9}, publisher = {Genetics Soc. of America}, address = {Pittsburgh, PA}, issn = {2160-1836}, doi = {10.1093/g3journal/jkac170}, pages = {11}, year = {2022}, abstract = {Genomic prediction has revolutionized crop breeding despite remaining issues of transferability of models to unseen environmental conditions and environments. Usage of endophenotypes rather than genomic markers leads to the possibility of building phenomic prediction models that can account, in part, for this challenge. Here, we compare and contrast genomic prediction and phenomic prediction models for 3 growth-related traits, namely, leaf count, tree height, and trunk diameter, from 2 coffee 3-way hybrid populations exposed to a series of treatment-inducing environmental conditions. The models are based on 7 different statistical methods built with genomic markers and ChlF data used as predictors. This comparative analysis demonstrates that the best-performing phenomic prediction models show higher predictability than the best genomic prediction models for the considered traits and environments in the vast majority of comparisons within 3-way hybrid populations. In addition, we show that phenomic prediction models are transferrable between conditions but to a lower extent between populations and we conclude that chlorophyll a fluorescence data can serve as alternative predictors in statistical models of coffee hybrid performance. Future directions will explore their combination with other endophenotypes to further improve the prediction of growth-related traits for crops.}, 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{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} } @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{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{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{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{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{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} } @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} }