Machine learning enables identification of an alternative yeast galactose utilization pathway

Harrison, Marie-Claire; Ubbelohde, Emily J.; LaBella, Abigail L.; Opulente, Dana A.; Wolters, John F.; Zhou, Xiaofan; Shen, Xing-Xing; Groenewald, Marizeth; Hittinger, Chris Todd; Rokas, Antonis

doi:10.1073/pnas.2315314121

Machine learning enables identification of an alternative yeast galactose utilization pathway

Journal Article · Fri Apr 26 00:00:00 EDT 2024 · Proceedings of the National Academy of Sciences of the United States of America

DOI:https://doi.org/10.1073/pnas.2315314121· OSTI ID:2370376

^[1]; Ubbelohde, Emily J. ^[2]; LaBella, Abigail L. ^[3]; Opulente, Dana A. ^[4]; Wolters, John F. ^[2]; Zhou, Xiaofan ^[5]; ^[6]; ^[7]; ^[2]; ^[8]

Vanderbilt University, Nashville, TN (United States); Vanderbilt University Department of Biological Sciences and Evolutionary Studies Initiative
University of Wisconsin-Madison, WI (United States)
Vanderbilt University, Nashville, TN (United States); University of North Carolina at Charlotte, NC (United States)
University of Wisconsin-Madison, WI (United States); Villanova University, PA (United States)
South China Agricultural University, Guangzhou (China)
Zhejiang University, Hangzhou (China)
Westerdijk Fungal Biodiversity Institute, Utrecht (The Netherlands)
Vanderbilt University, Nashville, TN (United States)

How genomic differences contribute to phenotypic differences is a major question in biology. The recently characterized genomes, isolation environments, and qualitative patterns of growth on 122 sources and conditions of 1,154 strains from 1,049 fungal species (nearly all known) in the yeast subphylum Saccharomycotina provide a powerful, yet complex, dataset for addressing this question. We used a random forest algorithm trained on these genomic, metabolic, and environmental data to predict growth on several carbon sources with high accuracy. Known structural genes involved in assimilation of these sources and presence/absence patterns of growth in other sources were important features contributing to prediction accuracy. By further examining growth on galactose, we found that it can be predicted with high accuracy from either genomic (92.2%) or growth data (82.6%) but not from isolation environment data (65.6%). Prediction accuracy was even higher (93.3%) when we combined genomic and growth data. After the GALactose utilization genes, the most important feature for predicting growth on galactose was growth on galactitol, raising the hypothesis that several species in two orders, Serinales and Pichiales (containing the emerging pathogen Candida auris and the genus Ogataea, respectively), have an alternative galactose utilization pathway because they lack the GAL genes. Growth and biochemical assays confirmed that several of these species utilize galactose through an alternative oxidoreductive D-galactose pathway, rather than the canonical GAL pathway. Machine learning approaches are powerful for investigating the evolution of the yeast genotype–phenotype map, and their application will uncover novel biology, even in well-studied traits.

View Accepted Manuscript (DOE)

Research Organization:: Great Lakes Bioenergy Research Center (GLBRC), Madison, WI (United States)

Sponsoring Organization:: National Science Foundation (NSF); USDOE Office of Science (SC), Biological and Environmental Research (BER)

Grant/Contract Number:: SC0018409

OSTI ID:: 2370376

Journal Information:: Proceedings of the National Academy of Sciences of the United States of America, Journal Name: Proceedings of the National Academy of Sciences of the United States of America Journal Issue: 18 Vol. 121; ISSN 0027-8424

Publisher:: National Academy of SciencesCopyright Statement

Country of Publication:: United States

Language:: English

References (61)

Candida albicans SOU1 encodes a sorbose reductase required forL-sorbose utilization Greenberg, Jay R.; Price, Neil P.; Oliver, Richard P. Yeast, Vol. 22, Issue 12 https://doi.org/10.1002/yea.1282	journal	January 2005
Giant GAL gene clusters for the melibiose‐galactose pathway in Torulaspora Venkatesh, Anjan; Murray, Anthony L.; Coughlan, Aisling Y. Yeast, Vol. 38, Issue 1 https://doi.org/10.1002/yea.3532	journal	December 2020
ggplot2 Wickham, Hadley Use R! https://doi.org/10.1007/978-3-319-24277-4	book	January 2016
Fruits and vegetables are a source of galactose: Implications in planning the diets of patients with Galactosaemia Gross, K. C.; Acosta, P. B. Journal of Inherited Metabolic Disease, Vol. 14, Issue 2 https://doi.org/10.1007/BF01800599	journal	July 1990
Hidden sources of galactose in the environment Acosta, Phyllis B.; Gross, Kenneth C. European Journal of Pediatrics, Vol. 154, Issue S2 https://doi.org/10.1007/BF02143811	journal	February 1995
The alternative d-galactose degrading pathway of Aspergillus nidulans proceeds via l-sorbose Fekete, Erzs�bet; Karaffa, Levente; S�ndor, Erzs�bet Archives of Microbiology, Vol. 181, Issue 1 https://doi.org/10.1007/s00203-003-0622-8	journal	January 2004
Fungal arabinan and l-arabinose metabolism Seiboth, Bernhard; Metz, Benjamin Applied Microbiology and Biotechnology, Vol. 89, Issue 6 https://doi.org/10.1007/s00253-010-3071-8	journal	January 2011
A deep convolutional neural network approach for predicting phenotypes from genotypes Ma, Wenlong; Qiu, Zhixu; Song, Jie Planta, Vol. 248, Issue 5 https://doi.org/10.1007/s00425-018-2976-9	journal	August 2018
A random forest guided tour Biau, Gérard; Scornet, Erwan TEST, Vol. 25, Issue 2 https://doi.org/10.1007/s11749-016-0481-7	journal	April 2016
Getting started with yeast Sherman, Fred Guide to Yeast Genetics and Molecular and Cell Biology - Part B https://doi.org/10.1016/S0076-6879(02)50954-X	book	January 2002
Sugar and polyol compositions of some European olive fruit varieties (Olea europaea L.) suitable for table olive purposes Marsilio, V.; Campestre, C.; Lanza, B. Food Chemistry, Vol. 72, Issue 4 https://doi.org/10.1016/S0308-8146(00)00268-5	journal	March 2001
Enzymatic synthesis of 2-keto-d-gluconate and 2-keto-d-galactonate from d-glucose and d-galactose with cell culture of Pseudomonas fluorescens and 2-keto-galactonate from d-galactono 1,4-lactone with partially purified 2-ketogalactonate reductase Tanimura, Ritsuko; Hamada, Akemi; Ikehara, Kenji Journal of Molecular Catalysis B: Enzymatic, Vol. 23, Issue 2-6 https://doi.org/10.1016/S1381-1177(03)00092-4	journal	September 2003
Neoadjuvant anastrozole versus tamoxifen in patients receiving goserelin for premenopausal breast cancer (STAGE): a double-blind, randomised phase 3 trial Masuda, Norikazu; Sagara, Yasuaki; Kinoshita, Takayuki The Lancet Oncology, Vol. 13, Issue 4 https://doi.org/10.1016/S1470-2045(11)70373-4	journal	April 2012
Tempo and Mode of Genome Evolution in the Budding Yeast Subphylum Shen, Xing-Xing; Opulente, Dana A.; Kominek, Jacek Cell, Vol. 175, Issue 6 https://doi.org/10.1016/j.cell.2018.10.023	journal	November 2018
Diverse yeasts for diverse fermented beverages and foods Hittinger, Chris Todd; Steele, James L.; Ryder, David S. Current Opinion in Biotechnology, Vol. 49 https://doi.org/10.1016/j.copbio.2017.10.004	journal	February 2018
Specialized Sugar Sensing in Diverse Fungi Brown, Victoria; Sabina, Jeffrey; Johnston, Mark Current Biology, Vol. 19, Issue 5 https://doi.org/10.1016/j.cub.2009.01.056	journal	March 2009
Rapid Expansion and Functional Divergence of Subtelomeric Gene Families in Yeasts Brown, Chris A.; Murray, Andrew W.; Verstrepen, Kevin J. Current Biology, Vol. 20, Issue 10 https://doi.org/10.1016/j.cub.2010.04.027	journal	May 2010
Detailed analysis of the D-galactose catabolic pathways in Aspergillus niger reveals complexity at both metabolic and regulatory level Chroumpi, Tania; Martínez-Reyes, Natalia; Kun, Roland S. Fungal Genetics and Biology, Vol. 159 https://doi.org/10.1016/j.fgb.2022.103670	journal	April 2022
Genomics and the making of yeast biodiversity Hittinger, Chris Todd; Rokas, Antonis; Bai, Feng-Yan Current Opinion in Genetics & Development, Vol. 35 https://doi.org/10.1016/j.gde.2015.10.008	journal	December 2015
Tracking alternative versions of the galactose gene network in the genus Saccharomyces and their expansion after domestication Pontes, Ana; Paraíso, Francisca; Liu, Yu-Ching iScience, Vol. 27, Issue 2 https://doi.org/10.1016/j.isci.2024.108987	journal	February 2024
New insights into galactose metabolism by Schizosaccharomyces pombe: Isolation and characterization of a galactose-assimilating mutant Matsuzawa, Tomohiko; Fujita, Yasuko; Tanaka, Naotaka Journal of Bioscience and Bioengineering, Vol. 111, Issue 2 https://doi.org/10.1016/j.jbiosc.2010.10.007	journal	February 2011
101 Dothideomycetes genomes: A test case for predicting lifestyles and emergence of pathogens Haridas, S.; Albert, R.; Binder, M. Studies in Mycology, Vol. 96 https://doi.org/10.1016/j.simyco.2020.01.003	journal	June 2020
The evolution of the GALactose utilization pathway in budding yeasts Harrison, Marie-Claire; LaBella, Abigail L.; Hittinger, Chris Todd Trends in Genetics, Vol. 38, Issue 1 https://doi.org/10.1016/j.tig.2021.08.013	journal	January 2022
Phylogenetics is the New Genetics (for Most of Biodiversity) Smith, Stacey D.; Pennell, Matthew W.; Dunn, Casey W. Trends in Ecology & Evolution, Vol. 35, Issue 5 https://doi.org/10.1016/j.tree.2020.01.005	journal	May 2020
Random forests for genomic data analysis Chen, Xi; Ishwaran, Hemant Genomics, Vol. 99, Issue 6 https://doi.org/10.1016/j.ygeno.2012.04.003	journal	June 2012
Crabtree/Warburg-like aerobic xylose fermentation by engineered Saccharomyces cerevisiae Lee, Sae-Byuk; Tremaine, Mary; Place, Michael Metabolic Engineering, Vol. 68 https://doi.org/10.1016/j.ymben.2021.09.008	journal	November 2021
A Machine Learning Bioinformatics Method to Predict Biological Activity from Biosynthetic Gene Clusters Walker, Allison S.; Clardy, Jon Journal of Chemical Information and Modeling, Vol. 61, Issue 6 https://doi.org/10.1021/acs.jcim.0c01304	journal	May 2021
Remarkably ancient balanced polymorphisms in a multi-locus gene network Hittinger, Chris Todd; Gonçalves, Paula; Sampaio, José Paulo Nature, Vol. 464, Issue 7285 https://doi.org/10.1038/nature08791	journal	February 2010
Deep learning suggests that gene expression is encoded in all parts of a co-evolving interacting gene regulatory structure Zrimec, Jan; Börlin, Christoph S.; Buric, Filip Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-19921-4	journal	December 2020
A primer on deep learning in genomics Zou, James; Huss, Mikael; Abid, Abubakar Nature Genetics, Vol. 51, Issue 1 https://doi.org/10.1038/s41588-018-0295-5	journal	November 2018
Parallel inactivation of multiple GAL pathway genes and ecological diversification in yeasts Hittinger, C. T.; Rokas, A.; Carroll, S. B. Proceedings of the National Academy of Sciences, Vol. 101, Issue 39 https://doi.org/10.1073/pnas.0404319101	journal	September 2004
Multiple GAL pathway gene clusters evolved independently and by different mechanisms in fungi Slot, J. C.; Rokas, A. Proceedings of the National Academy of Sciences, Vol. 107, Issue 22 https://doi.org/10.1073/pnas.0914418107	journal	May 2010
Comparative genomics of xylose-fermenting fungi for enhanced biofuel production Wohlbach, D. J.; Kuo, A.; Sato, T. K. Proceedings of the National Academy of Sciences, Vol. 108, Issue 32, p. 13212-13217 https://doi.org/10.1073/pnas.1103039108	journal	July 2011
Comparative genomics of biotechnologically important yeasts Riley, Robert; Haridas, Sajeet; Wolfe, Kenneth H. Proceedings of the National Academy of Sciences, Vol. 113, Issue 35 https://doi.org/10.1073/pnas.1603941113	journal	August 2016
Robust predictions of specialized metabolism genes through machine learning Moore, Bethany M.; Wang, Peipei; Fan, Pengxiang Proceedings of the National Academy of Sciences, Vol. 116, Issue 6 https://doi.org/10.1073/pnas.1817074116	journal	January 2019
R: A Language for Data Analysis and Graphics Ihaka, Ross; Gentleman, Robert Journal of Computational and Graphical Statistics, Vol. 5, Issue 3 https://doi.org/10.1080/10618600.1996.10474713	journal	September 1996
InterProScan 5: genome-scale protein function classification Jones, P.; Binns, D.; Chang, H. -Y. Bioinformatics, Vol. 30, Issue 9 https://doi.org/10.1093/bioinformatics/btu031	journal	January 2014
The future of fungi: threats and opportunities Case, Nicola T.; Berman, Judith; Blehert, David S. G3 Genes\|Genomes\|Genetics, Vol. 12, Issue 11 https://doi.org/10.1093/g3journal/jkac224	journal	September 2022
Repeated horizontal gene transfer of GAL actose metabolism genes violates Dollo’s law of irreversible loss Haase, Max A. B.; Kominek, Jacek; Opulente, Dana A. Genetics, Vol. 217, Issue 2 https://doi.org/10.1093/genetics/iyaa012	journal	November 2020
Codon Optimization Improves the Prediction of Xylose Metabolism from Gene Content in Budding Yeasts Nalabothu, Rishitha L.; Fisher, Kaitlin J.; LaBella, Abigail Leavitt Molecular Biology and Evolution, Vol. 40, Issue 6 https://doi.org/10.1093/molbev/msad111	journal	May 2023
Repeated Cis-Regulatory Tuning of a Metabolic Bottleneck Gene during Evolution Kuang, Meihua Christina; Kominek, Jacek; Alexander, William G. Molecular Biology and Evolution, Vol. 35, Issue 8 https://doi.org/10.1093/molbev/msy102	journal	May 2018
KEGG: Kyoto Encyclopedia of Genes and Genomes Kanehisa, Minoru; Goto, Susumu Nucleic Acids Research, Vol. 28, Issue 1, p. 27-30 https://doi.org/10.1093/nar/28.1.27	journal	January 2000
KEGG for taxonomy-based analysis of pathways and genomes Kanehisa, Minoru; Furumichi, Miho; Sato, Yoko Nucleic Acids Research, Vol. 51, Issue D1 https://doi.org/10.1093/nar/gkac963	journal	October 2022
Characterization of two different types of UDP-glucose/-galactose4-epimerase involved in galactosylation in fission yeast Suzuki, Shotaro; Matsuzawa, Tomohiko; Nukigi, Yayoi Microbiology, Vol. 156, Issue 3 https://doi.org/10.1099/mic.0.035279-0	journal	March 2010
GalR, GalX and AraR co‐regulate d‐galactose and l‐arabinose utilization in Aspergillus nidulans Meng, Jiali; Németh, Zoltán; Peng, Mao Microbial Biotechnology, Vol. 15, Issue 6 https://doi.org/10.1111/1751-7915.14025	journal	February 2022
Ancient balancing selection maintains incompatible versions of the galactose pathway in yeast Boocock, James; Sadhu, Meru J.; Durvasula, Arun Science, Vol. 371, Issue 6527 https://doi.org/10.1126/science.aba0542	journal	January 2021
Decoupling transcription factor expression and activity enables dimmer switch gene regulation Ricci-Tam, C.; Ben-Zion, I.; Wang, J. Science, Vol. 372, Issue 6539 https://doi.org/10.1126/science.aba7582	journal	April 2021
Genomic factors shape carbon and nitrogen metabolic niche breadth across Saccharomycotina yeasts Opulente, Dana A.; LaBella, Abigail Leavitt; Harrison, Marie-Claire Science, Vol. 384, Issue 6694 https://doi.org/10.1126/science.adj4503	journal	April 2024
Complex Physiology and Compound Stress Responses during Fermentation of Alkali-Pretreated Corn Stover Hydrolysate by an Escherichia coli Ethanologen Schwalbach, Michael S.; Keating, David H.; Tremaine, Mary Applied and Environmental Microbiology, Vol. 78, Issue 9, p. 3442-3457 https://doi.org/10.1128/AEM.07329-11	journal	March 2012
Metabolic Engineering of Saccharomyces cerevisiae Ostergaard, S.; Olsson, L.; Nielsen, J. Microbiology and Molecular Biology Reviews, Vol. 64, Issue 1 https://doi.org/10.1128/MMBR.64.1.34-50.2000	journal	March 2000
Predicting fungal secondary metabolite activity from biosynthetic gene cluster data using machine learning Riedling, Olivia; Walker, Allison S.; Rokas, Antonis Microbiology Spectrum, Vol. 12, Issue 2 https://doi.org/10.1128/spectrum.03400-23	journal	February 2024
XGBoost: A Scalable Tree Boosting System Chen, Tianqi; Guestrin, Carlos Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16 https://doi.org/10.1145/2939672.2939785	conference	January 2016
Factors driving metabolic diversity in the budding yeast subphylum Opulente, Dana A.; Rollinson, Emily J.; Bernick-Roehr, Cleome BMC Biology, Vol. 16, Issue 1 https://doi.org/10.1186/s12915-018-0498-3	journal	March 2018
Exploring xylose metabolism in Spathaspora species: XYL1.2 from Spathaspora passalidarum as the key for efficient anaerobic xylose fermentation in metabolic engineered Saccharomyces cerevisiae Cadete, Raquel M.; de las Heras, Alejandro M.; Sandström, Anders G. Biotechnology for Biofuels, Vol. 9, Issue 1 https://doi.org/10.1186/s13068-016-0570-6	journal	August 2016
Predicting Protein Ligand Binding Sites by Combining Evolutionary Sequence Conservation and 3D Structure Capra, John A.; Laskowski, Roman A.; Thornton, Janet M. PLoS Computational Biology, Vol. 5, Issue 12 https://doi.org/10.1371/journal.pcbi.1000585	journal	December 2009
Engineering and Two-Stage Evolution of a Lignocellulosic Hydrolysate-Tolerant Saccharomyces cerevisiae Strain for Anaerobic Fermentation of Xylose from AFEX Pretreated Corn Stover Parreiras, Lucas S.; Breuer, Rebecca J.; Avanasi Narasimhan, Ragothaman PLoS ONE, Vol. 9, Issue 9 https://doi.org/10.1371/journal.pone.0107499	journal	September 2014
A genome-informed higher rank classification of the biotechnologically important fungal subphylum Saccharomycotina Groenewald, M.; Hittinger, C. T.; Bensch, K. Studies in Mycology, Vol. 105, Issue 1 https://doi.org/10.3114/sim.2023.105.01	journal	June 2023
Two-Stage Semi-Continuous 2-Keto-Gluconic Acid (2KGA) Production by Pseudomonas plecoglossicida JUIM01 From Rice Starch Hydrolyzate Sun, Lei; Wang, Da-Ming; Sun, Wen-Jing Frontiers in Bioengineering and Biotechnology, Vol. 8 https://doi.org/10.3389/fbioe.2020.00120	journal	February 2020
New kids on the block: emerging oleaginous yeast of biotechnological importance Yaguchi, Allison; Rives, Dyllan AIMS Microbiology, Vol. 3, Issue 2 https://doi.org/10.3934/microbiol.2017.2.227	journal	January 2017
Transcriptional rewiring over evolutionary timescales changes quantitative and qualitative properties of gene expression Dalal, Chiraj K.; Zuleta, Ignacio A.; Mitchell, Kaitlin F. eLife, Vol. 5 https://doi.org/10.7554/eLife.18981	journal	September 2016
Recognition of galactose by a scaffold protein recruits a transcriptional activator for the GAL regulon induction in Candida albicans Sun, Xun; Yu, Jing; Zhu, Cheng eLife, Vol. 12 https://doi.org/10.7554/eLife.84155	journal	February 2023