@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} } @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{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{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} } @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} }