{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T20:08:48Z","timestamp":1790626128244,"version":"4.1.0"},"reference-count":16,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"vor","delay-in-days":16,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372165"],"award-info":[{"award-number":["62372165"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Conventional drug perturbation prediction models typically employ end-to-end encoder-decoder architectures, directly mapping control samples and perturbation conditions to post-perturbation gene expression profiles. However, these approaches widely overlook the severe class imbalance inherent in perturbation datasets, leading to a predictive bias toward weakly responsive samples.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>To address this bottleneck, we propose scBalFlow, a decoupled two-stage training framework. The first stage predicts the perturbation response intensity under given conditions, employing a Gaussian-Augmented Inference (GAI) strategy to counteract data imbalance. Crucially, the second stage bypasses weakly responsive conditions, while utilizing a Flow Matching model to synthesize highly responsive samples. Comprehensive evaluations on large-scale benchmarks, including SciPlex3 and McFarland, demonstrate that scBalFlow effectively overcomes the imbalance issue and significantly outperforms existing state-of-the-art methods on imbalanced datasets, particularly in capturing complex distribution shifts and maintaining single-cell distributional consistency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The source code and datasets are available at GitHub https:\/\/github.com\/hanwenlv-cmd\/scBalFlow and Figshare with doi:10.6084\/m9.figshare.33137447. The datasets of SciPlex3, ComboSciPlex, and McFarland underlying this study are available via the pertpy package. Alternatively, they can be downloaded manually from https:\/\/exampledata.scverse.org\/pertpy\/srivatsan_2020_sciplex3.h5ad for SciPlex3, https:\/\/exampledata.scverse.org\/pertpy\/combosciplex.h5ad for combosciplex, and https:\/\/exampledata.scverse.org\/pertpy\/mcfarland_2020.h5ad for McFarland.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag682","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T12:00:16Z","timestamp":1789473616000},"source":"Crossref","is-referenced-by-count":0,"title":["scBalFlow: a staged flow matching framework for imbalanced single-cell drug perturbation prediction"],"prefix":"10.1093","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0046-7876","authenticated-orcid":false,"given":"Hanwen","family":"Lyu","sequence":"first","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University , Hunan 410082,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2385-8272","authenticated-orcid":false,"given":"Jiawei","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University , Hunan 410082,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"2026092815530586800_btag682-B1","doi-asserted-by":"publisher","first-page":"2524","DOI":"10.1021\/acs.molpharmaceut.6b00248","article-title":"Deep learning applications for predicting pharmacological properties of drugs and drug repurposing using transcriptomic data","volume":"13","author":"Aliper","year":"2016","journal-title":"Mol Pharm"},{"key":"2026092815530586800_btag682-B2","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1007\/s12094-006-0048-2","article-title":"High throughput screening in drug discovery","volume":"8","author":"Carnero","year":"2006","journal-title":"Clin Transl Oncol"},{"key":"2026092815530586800_btag682-B3","doi-asserted-by":"crossref","first-page":"26711","DOI":"10.52202\/068431-1937","article-title":"Predicting cellular responses to novel drug perturbations at a single-cell resolution","volume":"35","author":"Hetzel","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026092815530586800_btag682-B4","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026092815530586800_btag682-B5","author":"Kingma"},{"key":"2026092815530586800_btag682-B6","doi-asserted-by":"publisher","author":"Klein","year":"2025","DOI":"10.1101\/2025.04.11.648220"},{"key":"2026092815530586800_btag682-B7","author":"Lipman","year":"2023"},{"key":"2026092815530586800_btag682-B8","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1038\/s41592-018-0229-2","article-title":"Deep generative modeling for single-cell transcriptomics","volume":"15","author":"Lopez","year":"2018","journal-title":"Nat Methods"},{"key":"2026092815530586800_btag682-B9","doi-asserted-by":"publisher","first-page":"e11517","DOI":"10.15252\/msb.202211517","article-title":"Predicting cellular responses to complex perturbations in high-throughput screens","volume":"19","author":"Lotfollahi","year":"2023","journal-title":"Mol Syst Biol"},{"key":"2026092815530586800_btag682-B10","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1038\/s41592-019-0494-8","article-title":"Scgen predicts single-cell perturbation responses","volume":"16","author":"Lotfollahi","year":"2019","journal-title":"Nat Methods"},{"key":"2026092815530586800_btag682-B11","doi-asserted-by":"publisher","first-page":"2674","DOI":"10.1038\/s41467-019-09799-2","article-title":"Community assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen","volume":"10","author":"Menden","year":"2019","journal-title":"Nat Commun"},{"key":"2026092815530586800_btag682-B12","author":"Peebles","year":"2023"},{"key":"2026092815530586800_btag682-B13","doi-asserted-by":"publisher","first-page":"1678","DOI":"10.1038\/s41587-023-02079-x","article-title":"Disentanglement of single-cell data with biolord","volume":"42","author":"Piran","year":"2024","journal-title":"Nat Biotechnol"},{"key":"2026092815530586800_btag682-B14","doi-asserted-by":"publisher","first-page":"9256","DOI":"10.1038\/s41467-024-53457-1","article-title":"Predicting transcriptional responses to novel chemical perturbations using deep generative model for drug discovery","volume":"15","author":"Qi","year":"2024","journal-title":"Nat Commun"},{"key":"2026092815530586800_btag682-B15","author":"Ren","year":"2022"},{"key":"2026092815530586800_btag682-B16","author":"Yu","year":"2026"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag682\/71110213\/btag682.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/9\/btag682\/71110213\/btag682.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/9\/btag682\/71110213\/btag682.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T19:53:14Z","timestamp":1790625194000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag682\/8800081"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":16,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,8,31]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag682","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,8,31]]},"article-number":"btag682"}}