{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T00:47:07Z","timestamp":1773881227244,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014054","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000}}],"reference-count":49,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T00:00:00Z","timestamp":1773187200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20257"],"award-info":[{"award-number":["U24A20257"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62532017"],"award-info":[{"award-number":["62532017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Innovation Program","doi-asserted-by":"publisher","award":["JCYJ20241202130212016"],"award-info":[{"award-number":["JCYJ20241202130212016"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["KQTD20200820113106007"],"award-info":[{"award-number":["KQTD20200820113106007"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20230807140709020"],"award-info":[{"award-number":["JCYJ20230807140709020"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Precise prediction of perturbation responses is essential in systems biology research, as it plays a pivotal role in characterizing cellular identities and elucidating the regulatory mechanisms of biological pathways. Existing perturbation-responses prediction approaches are predominantly confined to single-modality transcriptomic data, limiting their capacity to capture cross-layer molecular effects. Here, we present MultiPert, a deep learning framework specifically designed for predicting perturbation responses in single-cell multi-omics data. MultiPert employs modality-specific encoders with dedicated pretraining, integrates perturbation through a dual-attention mechanism, and achieves cross-modal alignment via adversarial training. Benchmarking on human THP-1 and kidney multi-omics datasets demonstrates that MultiPert reliably predicts both perturbed gene expression and protein abundance profiles, achieving superior accuracy and stability compared to state-of-the-art strategies. MultiPert generalizes to unseen perturbations and uncovers regulatory mechanisms of immune checkpoint molecules based on perturbed proteomic predictions. In addition, enrichment analyses of perturbed transcriptomic predictions reveal immune-related pathways. By providing an integrated and interpretable framework, MultiPert expands the scope of perturbation modeling at the multi-omics level, thereby offering a robust methodological foundation for comprehensive research into pathogenesis and drug discovery.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1014054","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T17:41:24Z","timestamp":1773250884000},"page":"e1014054","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["MultiPert: An adversarial alignment and dual attention framework for single-cell multi-omics perturbation prediction"],"prefix":"10.1371","volume":"22","author":[{"given":"Mengyuan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyue","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jijun","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8346-0798","authenticated-orcid":true,"given":"Fei","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,3,11]]},"reference":[{"issue":"3","key":"pcbi.1014054.ref001","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1038\/s41592-023-02144-y","article-title":"scPerturb: harmonized single-cell perturbation data","volume":"21","author":"S Peidli","year":"2024","journal-title":"Nat Methods"},{"issue":"6","key":"pcbi.1014054.ref002","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1016\/j.cels.2021.05.016","article-title":"Machine learning for perturbational single-cell omics","volume":"12","author":"Y Ji","year":"2021","journal-title":"Cell Syst"},{"issue":"16","key":"pcbi.1014054.ref003","article-title":"Large-scale multiplexed mosaic CRISPR perturbation in the whole organism","volume":"185","author":"B Liu","year":"2022","journal-title":"Cell"},{"issue":"3","key":"pcbi.1014054.ref004","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41556-025-01626-9","article-title":"Decoding heterogeneous single-cell perturbation responses","volume":"27","author":"B Song","year":"2025","journal-title":"Nat Cell Biol"},{"key":"pcbi.1014054.ref005","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1016\/j.csbj.2025.02.028","article-title":"Machine learning to dissect perturbations in complex cellular systems","volume":"27","author":"P Monfort-Lanzas","year":"2025","journal-title":"Comput Struct Biotechnol J"},{"issue":"8","key":"pcbi.1014054.ref006","doi-asserted-by":"crossref","first-page":"1742","DOI":"10.1038\/s41592-025-02753-9","article-title":"Morphological map of under- and overexpression of genes in human cells","volume":"22","author":"SN Chandrasekaran","year":"2025","journal-title":"Nat Methods"},{"issue":"5","key":"pcbi.1014054.ref007","doi-asserted-by":"crossref","first-page":"1076","DOI":"10.1016\/j.cell.2024.01.042","article-title":"Past, present, and future of CRISPR genome editing technologies","volume":"187","author":"M Pacesa","year":"2024","journal-title":"Cell"},{"issue":"1","key":"pcbi.1014054.ref008","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1093\/bfgp\/elw025","article-title":"CRISPR-Cas9 technology: applications and human disease modelling","volume":"16","author":"R Torres-Ruiz","year":"2017","journal-title":"Brief Funct Genomics"},{"issue":"4","key":"pcbi.1014054.ref009","article-title":"Massively parallel CRISPR-based genetic perturbation screening at single-cell resolution","volume":"10","author":"J Cheng","year":"2023","journal-title":"Adv Sci (Weinh)"},{"issue":"1","key":"pcbi.1014054.ref010","doi-asserted-by":"crossref","first-page":"4785","DOI":"10.1038\/s41467-025-60154-0","article-title":"Worm Perturb-Seq: massively parallel whole-animal RNAi and RNA-seq","volume":"16","author":"H Zhang","year":"2025","journal-title":"Nat Commun"},{"issue":"2","key":"pcbi.1014054.ref011","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1007587","article-title":"Host factor prioritization for pan-viral genetic perturbation screens using random intercept models and network propagation","volume":"16","author":"S Dirmeier","year":"2020","journal-title":"PLoS Comput Biol"},{"issue":"4","key":"pcbi.1014054.ref012","doi-asserted-by":"crossref","first-page":"101245","DOI":"10.1016\/j.cels.2025.101245","article-title":"Explainable modeling of single-cell perturbation data using attention and sparse dictionary learning","volume":"16","author":"Y Xu","year":"2025","journal-title":"Cell Syst"},{"issue":"10","key":"pcbi.1014054.ref013","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1038\/s43588-024-00698-1","article-title":"Toward subtask-decomposition-based learning and benchmarking for predicting genetic perturbation outcomes and beyond","volume":"4","author":"Y Gao","year":"2024","journal-title":"Nat Comput Sci"},{"issue":"8","key":"pcbi.1014054.ref014","doi-asserted-by":"crossref","first-page":"960","DOI":"10.1038\/s44320-025-00131-3","article-title":"PerturbNet predicts single-cell responses to unseen chemical and genetic perturbations","volume":"21","author":"H Yu","year":"2025","journal-title":"Mol Syst Biol"},{"issue":"1","key":"pcbi.1014054.ref015","doi-asserted-by":"crossref","first-page":"5423","DOI":"10.1038\/s41467-025-61165-7","article-title":"GPerturb: Gaussian process modelling of single-cell perturbation data","volume":"16","author":"H Xing","year":"2025","journal-title":"Nat Commun"},{"issue":"6","key":"pcbi.1014054.ref016","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1038\/s41587-023-01905-6","article-title":"Predicting transcriptional outcomes of novel multigene perturbations with GEARS","volume":"42","author":"Y Roohani","year":"2024","journal-title":"Nat Biotechnol"},{"issue":"8","key":"pcbi.1014054.ref017","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1038\/s41592-019-0494-8","article-title":"scGen predicts single-cell perturbation responses","volume":"16","author":"M Lotfollahi","year":"2019","journal-title":"Nat Methods"},{"issue":"2","key":"pcbi.1014054.ref018","article-title":"CoupleVAE: coupled variational autoencoders for predicting perturbational single-cell RNA sequencing data","volume":"26","author":"Y Wu","year":"2025","journal-title":"Brief Bioinform"},{"issue":"6","key":"pcbi.1014054.ref019","doi-asserted-by":"crossref","DOI":"10.15252\/msb.202211517","article-title":"Predicting cellular responses to complex perturbations in high-throughput screens","volume":"19","author":"M Lotfollahi","year":"2023","journal-title":"Mol Syst Biol"},{"issue":"5","key":"pcbi.1014054.ref020","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae265","article-title":"scPRAM accurately predicts single-cell gene expression perturbation response based on attention mechanism","volume":"40","author":"Q Jiang","year":"2024","journal-title":"Bioinformatics"},{"issue":"8","key":"pcbi.1014054.ref021","doi-asserted-by":"crossref","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":"H Cui","year":"2024","journal-title":"Nat Methods"},{"key":"pcbi.1014054.ref022","doi-asserted-by":"crossref","first-page":"1886","DOI":"10.1016\/j.csbj.2024.04.058","article-title":"A mini-review on perturbation modelling across single-cell omic modalities","volume":"23","author":"GI Gavriilidis","year":"2024","journal-title":"Comput Struct Biotechnol J"},{"issue":"3","key":"pcbi.1014054.ref023","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1038\/s41588-021-00778-2","article-title":"Characterizing the molecular regulation of inhibitory immune checkpoints with multimodal single-cell screens","volume":"53","author":"E Papalexi","year":"2021","journal-title":"Nat Genet"},{"issue":"10","key":"pcbi.1014054.ref024","doi-asserted-by":"crossref","first-page":"1246","DOI":"10.1038\/s41587-021-00927-2","article-title":"Scalable, multimodal profiling of chromatin accessibility, gene expression and protein levels in single cells","volume":"39","author":"EP Mimitou","year":"2021","journal-title":"Nat Biotechnol"},{"issue":"7","key":"pcbi.1014054.ref025","doi-asserted-by":"crossref","DOI":"10.1016\/j.cell.2022.02.015","article-title":"Spatial CRISPR genomics identifies regulators of the tumor microenvironment","volume":"185","author":"M Dhainaut","year":"2022","journal-title":"Cell"},{"issue":"5","key":"pcbi.1014054.ref026","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1038\/s41592-019-0392-0","article-title":"Multiplexed detection of proteins, transcriptomes, clonotypes and CRISPR perturbations in single cells","volume":"16","author":"EP Mimitou","year":"2019","journal-title":"Nat Methods"},{"issue":"6","key":"pcbi.1014054.ref027","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pgen.1001393","article-title":"Comparative analysis of proteome and transcriptome variation in mouse","volume":"7","author":"A Ghazalpour","year":"2011","journal-title":"PLoS Genet"},{"issue":"19","key":"pcbi.1014054.ref028","doi-asserted-by":"crossref","first-page":"2533","DOI":"10.1002\/pmic.201600140","article-title":"Integrating transcriptome and proteome profiling: strategies and applications","volume":"16","author":"D Kumar","year":"2016","journal-title":"Proteomics"},{"issue":"8","key":"pcbi.1014054.ref029","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1038\/s41576-023-00586-w","article-title":"Best practices for single-cell analysis across modalities","volume":"24","author":"L Heumos","year":"2023","journal-title":"Nat Rev Genet"},{"issue":"5","key":"pcbi.1014054.ref030","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1016\/j.gpb.2022.11.013","article-title":"Computational methods for single-cell multi-omics integration and alignment","volume":"20","author":"S Stanojevic","year":"2022","journal-title":"Genomics Proteomics Bioinformatics"},{"issue":"10","key":"pcbi.1014054.ref031","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1038\/s41587-021-00895-7","article-title":"Computational principles and challenges in single-cell data integration","volume":"39","author":"R Argelaguet","year":"2021","journal-title":"Nat Biotechnol"},{"issue":"12","key":"pcbi.1014054.ref032","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1038\/s41592-018-0229-2","article-title":"Deep generative modeling for single-cell transcriptomics","volume":"15","author":"R Lopez","year":"2018","journal-title":"Nat Methods"},{"key":"pcbi.1014054.ref033","article-title":"The Gene Ontology (GO) database and informatics resource","volume":"32","author":"MA Harris","year":"2004","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"pcbi.1014054.ref034","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1038\/s41592-022-01705-x","article-title":"Efficient combinatorial targeting of RNA transcripts in single cells with Cas13 RNA Perturb-seq","volume":"20","author":"H-H Wessels","year":"2023","journal-title":"Nat Methods"},{"issue":"10","key":"pcbi.1014054.ref035","doi-asserted-by":"crossref","first-page":"1246","DOI":"10.1038\/s41587-021-00927-2","article-title":"Scalable, multimodal profiling of chromatin accessibility, gene expression and protein levels in single cells","volume":"39","author":"EP Mimitou","year":"2021","journal-title":"Nat Biotechnol"},{"issue":"5","key":"pcbi.1014054.ref036","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1016\/j.jiph.2024.02.018","article-title":"Blueprint of differentially expressed genes reveals the dynamic gene expression landscape and the gender biases in long COVID","volume":"17","author":"C Chakraborty","year":"2024","journal-title":"J Infect Public Health"},{"issue":"17","key":"pcbi.1014054.ref037","article-title":"Methylation-related differentially expressed genes as potential prognostic biomarkers for cervical cancer","volume":"10","author":"Y Chen","year":"2024","journal-title":"Heliyon"},{"issue":"1","key":"pcbi.1014054.ref038","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s13059-017-1382-0","article-title":"SCANPY: large-scale single-cell gene expression data analysis","volume":"19","author":"FA Wolf","year":"2018","journal-title":"Genome Biol"},{"key":"pcbi.1014054.ref039","first-page":"723","article-title":"A Kernel two-sample test","volume":"13","author":"A Gretton","year":"2012","journal-title":"J Mach Learn Res"},{"issue":"1","key":"pcbi.1014054.ref040","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1146\/annurev-statistics-030718-104938","article-title":"Statistical aspects of Wasserstein distances","volume":"6","author":"VM Panaretos","year":"2019","journal-title":"Annual Review of Statistics and Its Application"},{"issue":"4","key":"pcbi.1014054.ref041","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1038\/nrc3239","article-title":"The blockade of immune checkpoints in cancer immunotherapy","volume":"12","author":"DM Pardoll","year":"2012","journal-title":"Nat Rev Cancer"},{"key":"pcbi.1014054.ref042","doi-asserted-by":"crossref","first-page":"5023","DOI":"10.2147\/OTT.S105862","article-title":"PD-L1 expression in human cancers and its association with clinical outcomes","volume":"9","author":"X Wang","year":"2016","journal-title":"Onco Targets Ther"},{"issue":"11","key":"pcbi.1014054.ref043","article-title":"Cyclic adenosine monophosphate potentiates immune checkpoint blockade therapy in acute myeloid leukemia","volume":"13","author":"P Mao","year":"2023","journal-title":"Clin Transl Med"},{"issue":"17","key":"pcbi.1014054.ref044","doi-asserted-by":"crossref","first-page":"2302","DOI":"10.1038\/s41388-018-0125-3","article-title":"Decitibine improve the efficiency of anti-PD-1 therapy via activating the response to IFN\/PD-L1 signal of lung cancer cells","volume":"37","author":"Q Lai","year":"2018","journal-title":"Oncogene"},{"issue":"6","key":"pcbi.1014054.ref045","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1016\/j.celrep.2017.04.031","article-title":"Interferon Receptor Signaling Pathways Regulating PD-L1 and PD-L2 Expression","volume":"19","author":"A Garcia-Diaz","year":"2017","journal-title":"Cell Rep"},{"issue":"21","key":"pcbi.1014054.ref046","article-title":"Prognostic signature and immunotherapeutic relevance of Focal adhesion signaling pathway-related genes in osteosarcoma","volume":"10","author":"Z Wu","year":"2024","journal-title":"Heliyon"},{"issue":"7","key":"pcbi.1014054.ref047","doi-asserted-by":"crossref","first-page":"1062","DOI":"10.1002\/mc.23546","article-title":"Ubiquitin ligase MARCH8 promotes the malignant progression of hepatocellular carcinoma through PTEN ubiquitination and degradation","volume":"62","author":"Y Xu","year":"2023","journal-title":"Mol Carcinog"},{"issue":"2","key":"pcbi.1014054.ref048","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.3892\/ol.2020.11647","article-title":"PD-L1 expression increased by IFN-\u03b3 via JAK2-STAT1 signaling and predicts a poor survival in colorectal cancer","volume":"20","author":"T Zhao","year":"2020","journal-title":"Oncol Lett"},{"issue":"10","key":"pcbi.1014054.ref049","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1038\/s41388-021-02173-x","article-title":"Demethylase JMJD2D induces PD-L1 expression to promote colorectal cancer immune escape by enhancing IFNGR1-STAT3-IRF1 signaling","volume":"41","author":"Q Chen","year":"2022","journal-title":"Oncogene"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1014054","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T17:52:11Z","timestamp":1773856331000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014054"}},"subtitle":[],"editor":[{"given":"Zhaoyuan","family":"Fang","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,11]]},"references-count":49,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014054","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,11]]}}}