{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:51:56Z","timestamp":1782175916556,"version":"3.54.5"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"vor","delay-in-days":14,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NAIRR"},{"name":"PSC Neocortex and NCSA Delta"},{"name":"Commonwealth Cyber Initiative, Children\u2019s National Hospital, Fralin Biomedical Research Institute"},{"name":"Sanghani Center for AI and Data Analytics"},{"name":"Virginia Tech Innovation Campus"},{"name":"Amazon + Virginia Tech Center for Efficient and Robust Machine Learning"},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["HL111362"],"award-info":[{"award-number":["HL111362"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["CA271891"],"award-info":[{"award-number":["CA271891"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["MH110504"],"award-info":[{"award-number":["MH110504"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["NS123719"],"award-info":[{"award-number":["NS123719"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Single-cell RNA sequencing (scRNA-seq) data offers unprecedented opportunities to infer gene regulatory networks (GRNs) at a fine-grained resolution, shedding light on cellular phenotypes at the molecular level. However, the high sparsity, noise, and dropout events inherent in scRNA-seq data pose significant challenges for accurate and reliable GRN inference. The rapid growth in experimentally validated transcription factor-DNA binding data has enabled supervised machine learning methods, which rely on known regulatory interactions to learn patterns, and achieve high accuracy in GRN inference by framing it as a gene regulatory link prediction task. This study addresses the gene regulatory link prediction problem by learning vectorized representations at the gene level to predict missing regulatory interactions. However, a higher performance of supervised learning methods requires a large amount of known TF-DNA binding data, which is often experimentally expensive and therefore limited in amount. Advances in large-scale pre-training and transfer learning provide a transformative opportunity to address this challenge. In this study, we leverage large-scale pre-trained models, trained on extensive scRNA-seq datasets and known as single-cell foundation models (scFMs). These models are combined with joint graph-based learning to establish a robust foundation for gene regulatory link prediction.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We propose scRegNet, a novel and effective framework that leverages scFMs with joint graph-based learning for gene regulatory link prediction. scRegNet achieves state-of-the-art results in comparison with nine baseline methods on seven scRNA-seq benchmark datasets. Additionally, scRegNet is more robust than the baseline methods on noisy training data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The source code is available at https:\/\/github.com\/sindhura-cs\/scRegNet.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf217","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T13:03:35Z","timestamp":1752584615000},"page":"i619-i627","source":"Crossref","is-referenced-by-count":2,"title":["Prediction of gene regulatory connections with joint single-cell foundation models and graph-based learning"],"prefix":"10.1093","volume":"41","author":[{"given":"Sindhura","family":"Kommu","sequence":"first","affiliation":[{"name":"Department of Computer Science, Virginia Tech , Blacksburg, VA 24060,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9456-0743","authenticated-orcid":false,"given":"Yizhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Virginia Tech , Arlington, VA 22203,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1788-1102","authenticated-orcid":false,"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Virginia Tech , Arlington, VA 22203,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1381-8958","authenticated-orcid":false,"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Virginia Tech , Blacksburg, VA 24060,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"2025071509032962300_btaf217-B1","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1242\/dev.084996","article-title":"Otx2 is an intrinsic determinant of the embryonic stem cell state and is required for transition to a stable epiblast stem cell condition","volume":"140","author":"Acampora","year":"2013","journal-title":"Development"},{"key":"2025071509032962300_btaf217-B2","doi-asserted-by":"publisher","author":"Akiba","year":"2019","DOI":"10.1145\/3292500.3330701"},{"key":"2025071509032962300_btaf217-B3","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1038\/nrg2102","article-title":"Network motifs: theory and experimental approaches","volume":"8","author":"Alon","year":"2007","journal-title":"Nat Rev Genet"},{"key":"2025071509032962300_btaf217-B4","author":"Bajaj","year":"2024"},{"key":"2025071509032962300_btaf217-B5","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1038\/cdd.2014.147","article-title":"Fra-1\/ap-1 induces epithelial-to-mesenchymal transition (emt) in mammary epithelial cells by modulating zeb1\/2 and tgf expression","volume":"22","author":"Bakiri","year":"2015","journal-title":"Cell Death Differ"},{"key":"2025071509032962300_btaf217-B6","doi-asserted-by":"crossref","first-page":"4522","DOI":"10.1093\/bioinformatics\/btac559","article-title":"Graph attention network for link prediction of gene regulations from single-cell RNA-sequencing data","volume":"38","author":"Chen","year":"2022","journal-title":"Bioinformatics"},{"key":"2025071509032962300_btaf217-B7","doi-asserted-by":"crossref","first-page":"bbab325","DOI":"10.1093\/bib\/bbab325","article-title":"Deepdrim: a deep neural network to reconstruct cell-type-specific gene regulatory network using single-cell RNA-seq data","volume":"22","author":"Chen","year":"2021","journal-title":"Brief Bioinform"},{"key":"2025071509032962300_btaf217-B8","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1038\/nature11247","article-title":"An integrated encyclopedia of DNA elements in the human genome","volume":"489","author":"Consortium","year":"2012","journal-title":"Nature"},{"key":"2025071509032962300_btaf217-B9","doi-asserted-by":"publisher","first-page":"1470","DOI":"10.1038\/s41592-024-02201-0","article-title":"Scgpt: toward building a foundation model for single-cell multi-omics using generative AI","volume":"21","author":"Cui","year":"2024","journal-title":"Nat Methods"},{"key":"2025071509032962300_btaf217-B10","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1186\/s12864-018-5370-x","article-title":"Gene2vec: distributed representation of genes based on co-expression","volume":"20","author":"Du","year":"2019","journal-title":"BMC Genomics"},{"key":"2025071509032962300_btaf217-B11","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1186\/s12859-015-0745-3","article-title":"Systematic noise degrades gene co-expression signals but can be corrected","volume":"16","author":"Freytag","year":"2015","journal-title":"BMC Bioinformatics"},{"key":"2025071509032962300_btaf217-B12","author":"Gong","year":"2024"},{"key":"2025071509032962300_btaf217-B13","author":"Hamilton","year":"2017"},{"key":"2025071509032962300_btaf217-B14","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.1038\/s41592-024-02305-7","article-title":"Large-scale foundation model on single-cell transcriptomics","volume":"21","author":"Hao","year":"2024","journal-title":"Nat Methods"},{"key":"2025071509032962300_btaf217-B15","doi-asserted-by":"crossref","first-page":"e12776","DOI":"10.1371\/journal.pone.0012776","article-title":"Inferring regulatory networks from expression data using tree-based methods","volume":"5","author":"Huynh-Thu","year":"2010","journal-title":"PLoS One"},{"key":"2025071509032962300_btaf217-B16","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1186\/s12918-019-0694-y","article-title":"Gne: a deep learning framework for gene network inference by aggregating biological information","volume":"13","author":"Kc","year":"2019","journal-title":"BMC Syst Biol"},{"key":"2025071509032962300_btaf217-B17","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1038\/nmeth.2967","article-title":"Bayesian approach to single-cell differential expression analysis","volume":"11","author":"Kharchenko","year":"2014","journal-title":"Nat Methods"},{"key":"2025071509032962300_btaf217-B18","author":"Kipf","year":"2017"},{"key":"2025071509032962300_btaf217-B19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.stem.2014.11.001","article-title":"Cited2 is an essential regulator of adult hematopoietic stem cells and erythroid differentiation","volume":"16","author":"Kranc","year":"2015","journal-title":"Cell Stem Cell"},{"key":"2025071509032962300_btaf217-B20","doi-asserted-by":"publisher","first-page":"bbad414","DOI":"10.1093\/bib\/bbad414","article-title":"Predicting gene regulatory links from single-cell RNA-seq data using graph neural networks","volume":"24","author":"Mao","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025071509032962300_btaf217-B21","doi-asserted-by":"crossref","first-page":"2159","DOI":"10.1093\/bioinformatics\/bty916","article-title":"Grnboost2 and arboreto: efficient and scalable inference of gene regulatory networks","volume":"35","author":"Moerman","year":"2019","journal-title":"Bioinformatics"},{"key":"2025071509032962300_btaf217-B22","doi-asserted-by":"publisher","first-page":"e52171","DOI":"10.15252\/embr.202152171","article-title":"Chip-atlas: a data-mining suite powered by full integration of public chip-seq data","volume":"22","author":"Okanishi","year":"2021","journal-title":"EMBO Reports"},{"key":"2025071509032962300_btaf217-B23","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1038\/s41592-019-0690-6","article-title":"Benchmarking algorithms for gene regulatory network inference from single-cell transcriptomic data","volume":"17","author":"Pratapa","year":"2020","journal-title":"Nat Methods"},{"key":"2025071509032962300_btaf217-B24","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.compbiolchem.2015.04.012","article-title":"Reconstructing gene regulatory networks from knock-out data using Gaussian noise model and Pearson correlation coefficient","volume":"59 Pt B","author":"Salleh","year":"2015","journal-title":"Comput Biol Chem"},{"key":"2025071509032962300_btaf217-B25","doi-asserted-by":"crossref","first-page":"bbac389","DOI":"10.1093\/bib\/bbac389","article-title":"Boosting single-cell gene regulatory network reconstruction via bulk-cell transcriptomic data","volume":"23","author":"Shu","year":"2022","journal-title":"Brief Bioinform"},{"key":"2025071509032962300_btaf217-B26","doi-asserted-by":"crossref","first-page":"10294","DOI":"10.1073\/pnas.0506945103","article-title":"Nanog binds to smad1 and blocks bone morphogenetic protein-induced differentiation of embryonic stem cells","volume":"103","author":"Suzuki","year":"2006","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2025071509032962300_btaf217-B27","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1038\/s41586-023-06139-9","article-title":"Transfer learning enables predictions in network biology","volume":"618","author":"Theodoris","year":"2023","journal-title":"Nature"},{"key":"2025071509032962300_btaf217-B28","author":"Tsai","year":"2019"},{"key":"2025071509032962300_btaf217-B29","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"2025071509032962300_btaf217-B30","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"2025071509032962300_btaf217-B31","doi-asserted-by":"publisher","first-page":"D929","DOI":"10.1093\/nar\/gku1161","article-title":"Escape: database for integrating high-confidence human tf-target regulatory interactions","volume":"43","author":"Xu","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2025071509032962300_btaf217-B32","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1038\/s42256-022-00534-z","article-title":"Scbert as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data","volume":"4","author":"Yang","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2025071509032962300_btaf217-B33","doi-asserted-by":"crossref","first-page":"27151","DOI":"10.1073\/pnas.1911536116","article-title":"Deep learning for inferring gene relationships from single-cell expression data","volume":"116","author":"Yuan","year":"2019","journal-title":"Proc Natl Acad Sci U S A"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/Supplement_1\/i619\/63745599\/btaf217.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/Supplement_1\/i619\/63745599\/btaf217.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T13:03:37Z","timestamp":1752584617000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/41\/Supplement_1\/i619\/8199393"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":33,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2025,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf217","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,7]]},"published":{"date-parts":[[2025,7,1]]}}}