{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T14:54:00Z","timestamp":1791212040636,"version":"4.1.0"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100005825","name":"USDA National Institute of Food and Agriculture","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005825","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The ability to predict phenotypes from genotypes in multicellular organisms remains limited despite rapid advances in genotyping and phenotyping methods. Machine learning offers a promising way to model phenotype from genotype but requires sizable datasets that quantitatively link phenotype to specific genes. Such datasets remain limited; however, maize pollen provides a unique biological system that is especially well suited for this challenge. Because maize pollen is haploid, mutations that affect its function can result in a quantitative phenotypic effect on pollen fitness, measurable as deviations in transmission rate from the expected Mendelian ratio. We leveraged a large set of fluorescently-marked insertional mutations, the Ds-GFP lines, to link fitness effects to specific genes. We then developed a machine learning framework that integrates expression profiling and genomic data to predict genes contributing to pollen fitness in maize. Well performing models that distinguish genes with strong fitness effects from those with little or no fitness effect could be generated using features, such as codon usage, derived solely from genome sequence (area under receiver operating characteristic curve 85%). Using expression data enabled even more successful models, achieving area under receiver operating characteristic curve values above 90%. Because we used interpretable machine learning methods, we were able to identify expression specificity as a critical feature for strongest model performance. The best-performing model was achieved when specificity measures were complemented with certain genomic sequence features. Models that include expression specificity generalize well across the maize genome, as predictions meet expectations of mutational frequencies for thousands of genes in a well characterized mutagenized population.<\/jats:p>","DOI":"10.1093\/plcell\/koag272","type":"journal-article","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:47:15Z","timestamp":1789127235000},"source":"Crossref","is-referenced-by-count":0,"title":["Successful predictive modeling of pollen fitness phenotypes is enabled by measures of expression specificity"],"prefix":"10.1093","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7710-5803","authenticated-orcid":false,"given":"Sebastian A F","family":"Mueller","sequence":"first","affiliation":[{"name":"School of Chemical, Biological, and Environmental Engineering, Oregon State University , 116 Johnson Hall, 105 SW 26th Street, Corvallis, OR 97331 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8682-3558","authenticated-orcid":false,"given":"Zuzana","family":"Vejlupkova","sequence":"additional","affiliation":[{"name":"Department of Botany and Plant Pathology, Oregon State University , 2503 Cordley Hall, 2701 SW Campus Way, Corvallis, OR 97331 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6793-6151","authenticated-orcid":false,"given":"Molly","family":"Megraw","sequence":"additional","affiliation":[{"name":"School of Chemical, Biological, and Environmental Engineering, Oregon State University , 116 Johnson Hall, 105 SW 26th Street, Corvallis, OR 97331 ,","place":["United States"]},{"name":"Department of Botany and Plant Pathology, Oregon State University , 2503 Cordley Hall, 2701 SW Campus Way, Corvallis, OR 97331 ,","place":["United States"]},{"name":"School of Electrical Engineering and Computer Science, Oregon State University , 1148 Kelley Engineering Center, 2461 SW Campus Way, Corvallis, OR 97331 ,","place":["United States"]},{"name":"Center for Quantitative Life Sciences, Oregon State University , 3021 Agricultural and Life Sciences Building, 2750 SW Campus Way, Corvallis, OR 97331 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9254-5934","authenticated-orcid":false,"given":"John E","family":"Fowler","sequence":"additional","affiliation":[{"name":"Department of Botany and Plant Pathology, Oregon State University , 2503 Cordley Hall, 2701 SW Campus Way, Corvallis, OR 97331 ,","place":["United States"]},{"name":"Center for Quantitative Life Sciences, Oregon State University , 3021 Agricultural and Life Sciences Building, 2750 SW Campus Way, Corvallis, OR 97331 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,10,5]]},"reference":[{"key":"2026100510124657600_koag272-B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2020.107663","article-title":"Predicting mRNA abundance directly from genomic sequence using deep convolutional neural networks","volume":"31","author":"Agarwal","year":"2020","journal-title":"Cell Rep."},{"key":"2026100510124657600_koag272-B2","doi-asserted-by":"publisher","first-page":"809","DOI":"10.3390\/genes16070809","article-title":"Harnessing multi-omics and predictive modeling for climate-resilient crop breeding: from genomes to fields","volume":"16","author":"Amin","year":"2025","journal-title":"Genes (Basel)."},{"key":"2026100510124657600_koag272-B3","doi-asserted-by":"publisher","author":"Ansariola","year":"2020","DOI":"10.1101\/2020.09.01.278424"},{"key":"2026100510124657600_koag272-B4","doi-asserted-by":"crossref","first-page":"188","DOI":"10.4018\/978-1-5225-2607-0.ch008","volume-title":"Applying big data analytics in bioinformatics and medicine","author":"Bansal","year":"2018"},{"key":"2026100510124657600_koag272-B5","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.pbi.2020.01.006","article-title":"We aren\u2019t good at picking candidate genes, and it's slowing us down","volume":"54","author":"Baxter","year":"2020","journal-title":"Curr Opin Plant Biol."},{"key":"2026100510124657600_koag272-B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.xplc.2020.100115","article-title":"Evolutionary genomics of plant gametophytic selection","volume":"1","author":"Beaudry","year":"2020","journal-title":"Plant Commun."},{"key":"2026100510124657600_koag272-B7","first-page":"55","volume-title":"Handbook of maize: its biology","author":"Bedinger","year":"2009"},{"key":"2026100510124657600_koag272-B8","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/s00497-016-0283-9","article-title":"Pollen proteomics: from stress physiology to developmental priming","volume":"29","author":"Chaturvedi","year":"2016","journal-title":"Plant Reprod."},{"key":"2026100510124657600_koag272-B9","doi-asserted-by":"publisher","DOI":"10.1002\/tpg2.20015","article-title":"Non-homology-based prediction of gene functions in maize (Zea mays ssp. mays)","volume":"13","author":"Dai","year":"2020","journal-title":"Plant Genome."},{"key":"2026100510124657600_koag272-B10","doi-asserted-by":"publisher","first-page":"3423","DOI":"10.1093\/bioinformatics\/btr539","article-title":"Pybedtools: a flexible Python library for manipulating genomic datasets and annotations","volume":"27","author":"Dale","year":"2011","journal-title":"Bioinformatics"},{"key":"2026100510124657600_koag272-B11","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1016\/j.tig.2024.07.001","article-title":"Artificial intelligence in plant breeding","volume":"40","author":"Farooq","year":"2024","journal-title":"Trends Genet."},{"key":"2026100510124657600_koag272-B12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005535","article-title":"Post-transcriptional regulation across human tissues","volume":"13","author":"Franks","year":"2017","journal-title":"PLoS Comput Biol"},{"key":"2026100510124657600_koag272-B13","doi-asserted-by":"publisher","first-page":"5165","DOI":"10.1073\/pnas.1703498114","article-title":"Maize defective kernel mutant generated by insertion of a Ds element in a gene encoding a highly conserved TTI2 cochaperone","volume":"114","author":"Garcia","year":"2017","journal-title":"Proc Natl Acad Sci U S A."},{"key":"2026100510124657600_koag272-B14","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1104\/pp.18.00648","article-title":"Dynamics of the pollen sequestrome defined by subcellular coupled omics","volume":"178","author":"Hafidh","year":"2018","journal-title":"Plant Physiol."},{"key":"2026100510124657600_koag272-B15","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1146\/annurev-arplant-080620-021907","article-title":"Reproduction multitasking: the male gametophyte","volume":"72","author":"Hafidh","year":"2021","journal-title":"Annu Rev Plant Biol."},{"key":"2026100510124657600_koag272-B16","doi-asserted-by":"publisher","DOI":"10.1093\/g3journal\/jkac255","article-title":"Prioritizing candidate eQTL causal genes in Arabidopsis using RANDOM FORESTS","volume":"12","author":"Hartanto","year":"2022","journal-title":"G3 (Bethesda, Md.)"},{"key":"2026100510124657600_koag272-B17","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1146\/annurev-arplant-050213-035715","article-title":"Natural variations and genome-wide association studies in crop plants","volume":"65","author":"Huang","year":"2014","journal-title":"Annu Rev Plant Biol."},{"key":"2026100510124657600_koag272-B18","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1126\/science.abg5289","article-title":"De novo assembly, annotation, and comparative analysis of 26 diverse maize genomes","volume":"373","author":"Hufford","year":"2021","journal-title":"Science"},{"key":"2026100510124657600_koag272-B19","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1086\/698483","article-title":"The evolutionary consequences of selection at the haploid gametic stage","volume":"192","author":"Immler","year":"2018","journal-title":"Am Nat."},{"key":"2026100510124657600_koag272-B20","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/978-1-62703-568-2_6","volume-title":"Plant transposable elements","author":"Li","year":"2013"},{"key":"2026100510124657600_koag272-B21","doi-asserted-by":"publisher","first-page":"3129","DOI":"10.1534\/g3.119.400319","article-title":"QTG-Finder: a machine-learning based algorithm to prioritize causal genes of quantitative trait loci in Arabidopsis and rice","volume":"9","author":"Lin","year":"2019","journal-title":"G3 (Bethesda, Md.)"},{"key":"2026100510124657600_koag272-B22","doi-asserted-by":"publisher","first-page":"2411","DOI":"10.1534\/g3.120.401122","article-title":"QTG-Finder2: a generalized machine-learning algorithm for prioritizing QTL causal genes in plants","volume":"10","author":"Lin","year":"2020","journal-title":"G3 (Bethesda, Md.)"},{"key":"2026100510124657600_koag272-B23","doi-asserted-by":"publisher","first-page":"2133","DOI":"10.1105\/tpc.15.00051","article-title":"Characteristics of plant essential genes allow for within- and between-species prediction of lethal mutant phenotypes","volume":"27","author":"Lloyd","year":"2015","journal-title":"Plant Cell."},{"key":"2026100510124657600_koag272-B24","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1104\/pp.20.00478","article-title":"Bonnmu: a sequence-indexed resource of transposon-induced maize mutations for functional genomics studies","volume":"184","author":"Marcon","year":"2020","journal-title":"Plant Physiol."},{"key":"2026100510124657600_koag272-B25","doi-asserted-by":"publisher","first-page":"2746","DOI":"10.1105\/tpc.114.125617","article-title":"Paired-end analysis of transcription start sites in Arabidopsis reveals plant-specific promoter signatures","volume":"26","author":"Morton","year":"2014","journal-title":"Plant Cell."},{"key":"2026100510124657600_koag272-B26","doi-asserted-by":"publisher","first-page":"3725","DOI":"10.1093\/bioinformatics\/btv464","article-title":"TIPR: transcription initiation pattern recognition on a genome scale","volume":"31","author":"Morton","year":"2015","journal-title":"Bioinformatics"},{"key":"2026100510124657600_koag272-B27","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1126\/science.abl7392","article-title":"Gametophyte genome activation occurs at pollen mitosis I in maize","volume":"375","author":"Nelms","year":"2022","journal-title":"Science"},{"key":"2026100510124657600_koag272-B28","doi-asserted-by":"publisher","first-page":"1965","DOI":"10.1534\/g3.113.008144","article-title":"Characterization and prediction of haploinsufficiency using systems-level gene properties in yeast","volume":"3","author":"Norris","year":"2013","journal-title":"G3 (Bethesda, Md.)"},{"key":"2026100510124657600_koag272-B29","doi-asserted-by":"publisher","first-page":"1546","DOI":"10.1111\/tpj.15219","article-title":"The Brassica mature pollen and stigma proteomes: preparing to meet","volume":"107","author":"Robinson","year":"2021","journal-title":"Plant J."},{"key":"2026100510124657600_koag272-B30","doi-asserted-by":"publisher","first-page":"e70760","DOI":"10.1111\/tpj.70760","article-title":"Spatial inheritance patterns across maize ears are associated with alleles that reduce pollen fitness","volume":"125","author":"Ruggiero","year":"2026","journal-title":"Plant J."},{"key":"2026100510124657600_koag272-B31","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1111\/nph.16011","article-title":"Genes and gene models, an important distinction","volume":"228","author":"Schnable","year":"2020","journal-title":"New Phytol."},{"key":"2026100510124657600_koag272-B32","doi-asserted-by":"publisher","first-page":"baad078","DOI":"10.1093\/database\/baad078","article-title":"Maize feature store: a centralized resource to manage and analyze curated maize multi-omics features for machine learning applications","volume":"2023","author":"Sen","year":"2023","journal-title":"Database"},{"key":"2026100510124657600_koag272-B33","doi-asserted-by":"publisher","DOI":"10.1002\/tpg2.20077","article-title":"Status and prospects of genome-wide association studies in plants","volume":"14","author":"Tibbs Cortes","year":"2021","journal-title":"Plant Genome."},{"key":"2026100510124657600_koag272-B34","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-021-00056-9","article-title":"Genome-wide association studies","volume":"1","author":"Uffelmann","year":"2021","journal-title":"Nat Rev Methods Primers."},{"key":"2026100510124657600_koag272-B35","doi-asserted-by":"publisher","first-page":"1910","DOI":"10.2135\/cropsci2002.1910","article-title":"Pollen production, pollination dynamics, and kernel set in maize","volume":"42","author":"Uribelarrea","year":"2002","journal-title":"Crop Sci."},{"key":"2026100510124657600_koag272-B36","doi-asserted-by":"publisher","DOI":"10.1111\/pbr.13228","article-title":"Precision phenotyping in crop science: from plant traits to gene discovery for climate-smart agriculture","author":"Visakh","year":"2024","journal-title":"Plant Breed"},{"key":"2026100510124657600_koag272-B37","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1126\/science.aag1125","article-title":"Integration of omic networks in a developmental atlas of maize","volume":"353","author":"Walley","year":"2016","journal-title":"Science"},{"key":"2026100510124657600_koag272-B38","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s12870-019-2218-8","article-title":"Tissue-specific gene expression and protein abundance patterns are associated with fractionation bias in maize","volume":"20","author":"Walsh","year":"2020","journal-title":"BMC Plant Biol."},{"key":"2026100510124657600_koag272-B39","doi-asserted-by":"publisher","DOI":"10.1093\/plphys\/kiaf275","article-title":"A computer vision-based approach for high-throughput automated analysis of Arabidopsis seedling phenotypes","volume":"198","author":"Wan","year":"2025","journal-title":"Plant Physiol."},{"key":"2026100510124657600_koag272-B40","doi-asserted-by":"publisher","first-page":"6856","DOI":"10.1038\/s41467-024-50701-6","article-title":"Prediction of plant complex traits via integration of multi-omics data","volume":"15","author":"Wang","year":"2024","journal-title":"Nat Commun."},{"key":"2026100510124657600_koag272-B41","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.1008462","article-title":"High expression in maize pollen correlates with genetic contributions to pollen fitness as well as with coordinated transcription from neighboring transposable elements","volume":"16","author":"Warman","year":"2020","journal-title":"PLoS Genet."},{"key":"2026100510124657600_koag272-B42","doi-asserted-by":"publisher","first-page":"2253","DOI":"10.1111\/tpj.17088","article-title":"Expanding the BonnMu sequence-indexed repository of transposon induced maize (Zea mays L.) mutations in dent and flint germplasm","volume":"120","author":"Win","year":"2024","journal-title":"Plant J."},{"key":"2026100510124657600_koag272-B43","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1186\/s12870-021-03173-5","article-title":"A pan-genomic approach to genome databases using maize as a model system","volume":"21","author":"Woodhouse","year":"2021","journal-title":"BMC Plant Biol."},{"key":"2026100510124657600_koag272-B44","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1093\/bioinformatics\/btab604","article-title":"Qteller: a tool for comparative multi-genomic gene expression analysis","volume":"38","author":"Woodhouse","year":"2021","journal-title":"Bioinformatics"},{"key":"2026100510124657600_koag272-B45","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/j.molp.2016.12.008","article-title":"Genome-wide association studies in maize: praise and stargaze","volume":"10","author":"Xiao","year":"2017","journal-title":"Mol Plant."},{"key":"2026100510124657600_koag272-B46","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1186\/1471-2164-14-679","article-title":"InsertionMapper: a pipeline tool for the identification of targeted sequences from multidimensional high throughput sequencing data","volume":"14","author":"Xiong","year":"2013","journal-title":"BMC Genomics"},{"key":"2026100510124657600_koag272-B47","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaa393","article-title":"Identification of haploinsufficient genes from epigenomic data using deep forest","volume":"22","author":"Yang","year":"2021","journal-title":"Brief Bioinform."},{"key":"2026100510124657600_koag272-B48","doi-asserted-by":"publisher","first-page":"114669","DOI":"10.1016\/j.indcrop.2022.114669","article-title":"Exploitation of next generation sequencing technologies for unraveling metabolic pathways in medicinal plants: a concise review","volume":"178","author":"Younessi-Hamzekhanlu","year":"2022","journal-title":"Ind Crops Prod."},{"key":"2026100510124657600_koag272-B49","doi-asserted-by":"publisher","first-page":"6685","DOI":"10.1093\/nar\/gkaa370","article-title":"Transposable elements employ distinct integration strategies with respect to transcriptional landscapes in eukaryotic genomes","volume":"48","author":"Zhang","year":"2020","journal-title":"Nucleic Acids Res."},{"key":"2026100510124657600_koag272-B50","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.molp.2017.01.012","article-title":"Germline development and fertilization mechanisms in maize","volume":"10","author":"Zhou","year":"2017","journal-title":"Mol Plant."}],"container-title":["The Plant Cell"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/plcell\/article-pdf\/38\/10\/koag272\/71603750\/koag272.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/plcell\/article-pdf\/38\/10\/koag272\/71603750\/koag272.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T14:12:59Z","timestamp":1791209579000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/plcell\/article\/doi\/10.1093\/plcell\/koag272\/8864944"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":50,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10,5]]}},"URL":"https:\/\/doi.org\/10.1093\/plcell\/koag272","relation":{},"ISSN":["1040-4651","1532-298X"],"issn-type":[{"value":"1040-4651","type":"print"},{"value":"1532-298X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,10]]},"published":{"date-parts":[[2026,10]]},"article-number":"koag272"}}