{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T22:24:26Z","timestamp":1787005466208,"version":"build-2736575974"},"posted":{"date-parts":[[2025,11,24]]},"group-title":"Bioinformatics","reference-count":59,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,8,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  Dissecting cell-state-specific changes in gene regulation induced by perturbations is crucial for understanding biological mechanisms. However, single-cell sequencing provides only unmatched snapshots of cells under different conditions. This destructive measurement process hinders the estimation of individualized treatment effects (ITEs), which are essential for pinpointing these heterogeneous mechanistic responses. We develop scDRP, a generative framework that leverages disentangled representation learning with asymptotic correctness guarantees to separate perturbation-induced and perturbation-invariant latent variables via a sparsity regularized\n                  <jats:bold>\n                    <jats:italic>\u03b2<\/jats:italic>\n                  <\/jats:bold>\n                  -VAE. Assuming quantile-preserving effects of perturbations conditional on confounders, scDRP performs conditional optimal transport in the disentangled latent space to infer counterfactual states and estimate ITEs. Applied to simulated and real single-cell perturbation data, scDRP accurately estimates treatment effects and individual counterfactual responses, with subsequent biclustering analysis further elucidating cell-type-specific functional gene module dynamics. Specifically, it captures distinct cellular patterns under rhinovirus and cigarette-smoke extract exposures, reveals heterogeneous responses to interferon stimulation across diverse immune cell types, and identifies distinct functional module activation in chronic myeloid leukemia cells following CRISPR activation targeting different genes. scDRP also generalizes to unseen perturbation doses and combinations. Our framework provides a principled computational approach to extracting heterogeneous causal relationships from single-cell perturbation data, enabling a deeper understanding of cellular and molecular mechanisms.\n                <\/jats:p>","DOI":"10.1101\/2025.11.21.689783","type":"posted-content","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T17:40:26Z","timestamp":1764006026000},"source":"Crossref","is-referenced-by-count":1,"title":["scDRP: Disentangled representation learning for predicting single-cell responses to perturbations and estimating individual treatment effects"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0001-0992","authenticated-orcid":false,"given":"Jianle","family":"Sun","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, 15213, PA, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petar","family":"Stojanov","sequence":"additional","affiliation":[{"name":"Broad institute of MIT and Harvard, Cambridge, 02142, MA, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, 15213, PA, United States of America"},{"name":"Mohamed bin Zayed University of Artificial Intelligence, Masdar City Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026081714301234000_2025.11.21.689783v3.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2016.11.038"},{"key":"2026081714301234000_2025.11.21.689783v3.2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aax6234"},{"issue":"3","key":"2026081714301234000_2025.11.21.689783v3.3","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1038\/s41592-023-02144-y","article-title":"scPerturb: harmonized single-cell perturbation data","volume":"21","year":"2024","journal-title":"Nature Methods"},{"issue":"8","key":"2026081714301234000_2025.11.21.689783v3.4","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1038\/s41592-019-0494-8","article-title":"scGen predicts single-cell perturbation responses","volume":"16","year":"2019","journal-title":"Nature Methods"},{"key":"2026081714301234000_2025.11.21.689783v3.5","doi-asserted-by":"crossref","unstructured":"Adduri, A.K. , Gautam, D. , Bevilacqua, B. , Imran, A. , Shah, R. , Naghipourfar, M. , Teyssier, N. , Ilango, R. , Nagaraj, S. , Dong, M. , et al.: Predicting cellular responses to perturbation across diverse contexts with state. bioRxiv, 2025\u201306 (2025)","DOI":"10.1101\/2025.06.26.661135"},{"issue":"11","key":"2026081714301234000_2025.11.21.689783v3.6","doi-asserted-by":"crossref","first-page":"1769","DOI":"10.1038\/s41592-023-02040-5","article-title":"Causal identification of single-cell experimental perturbation effects with cinema-ot","volume":"20","year":"2023","journal-title":"Nature Methods"},{"key":"2026081714301234000_2025.11.21.689783v3.7","doi-asserted-by":"crossref","unstructured":"Chewi, S. , Niles-Weed, J. , Rigollet, P. : Statistical optimal transport (2024)","DOI":"10.1007\/978-3-031-85160-5"},{"key":"2026081714301234000_2025.11.21.689783v3.8","first-page":"73","article-title":"Dimensionality reduction for supervised learning with reproducing kernel hilbert spaces","volume":"5","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"2026081714301234000_2025.11.21.689783v3.9","doi-asserted-by":"publisher","DOI":"10.5555\/3648699.3648779"},{"key":"2026081714301234000_2025.11.21.689783v3.10","unstructured":"Louizos, C. , Welling, M. , Kingma, D.P. : Learning sparse neural networks through l 0 regularization. In: International Conference on Learning Representations (2018)"},{"key":"2026081714301234000_2025.11.21.689783v3.11","unstructured":"Khemakhem, I. , Kingma, D. , Monti, R. , Hyvarinen, A. : Variational autoen-coders and nonlinear ica: A unifying framework. In: International Conference on Artificial Intelligence and Statistics, pp. 2207\u20132217 (2020). PMLR"},{"key":"2026081714301234000_2025.11.21.689783v3.12","first-page":"13326","article-title":"Generalizing nonlinear ica beyond structural sparsity","volume":"36","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"2026081714301234000_2025.11.21.689783v3.13","doi-asserted-by":"crossref","first-page":"20230071","DOI":"10.1515\/jci-2023-0071","article-title":"Conservative inference for counterfactuals","volume":"13","year":"2025","journal-title":"Journal of Causal Inference"},{"key":"2026081714301234000_2025.11.21.689783v3.14","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.4042"},{"key":"2026081714301234000_2025.11.21.689783v3.15","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0657-2"},{"key":"2026081714301234000_2025.11.21.689783v3.16","doi-asserted-by":"publisher","DOI":"10.1126\/science.aax4438"},{"issue":"1","key":"2026081714301234000_2025.11.21.689783v3.17","doi-asserted-by":"crossref","first-page":"1010159","DOI":"10.1371\/journal.ppat.1010159","article-title":"Rhinovirus c replication is associated with the endoplasmic reticulum and triggers cytopathic effects in an in vitro model of human airway epithelium","volume":"18","year":"2022","journal-title":"PLoS pathogens"},{"key":"2026081714301234000_2025.11.21.689783v3.18","doi-asserted-by":"publisher","DOI":"10.1165\/rcmb.2013-0363OC"},{"issue":"12","key":"2026081714301234000_2025.11.21.689783v3.19","first-page":"1355","article-title":"Airway basal cells","volume":"190","year":"2014","journal-title":"the \u201csmoking gun\u201d of chronic obstructive pulmonary disease. American journal of respiratory and critical care medicine"},{"key":"2026081714301234000_2025.11.21.689783v3.20","doi-asserted-by":"publisher","DOI":"10.2500\/ajr.2007.21.2966"},{"key":"2026081714301234000_2025.11.21.689783v3.21","doi-asserted-by":"crossref","unstructured":"Gong, Y. , Xu, J. , Wu, M. , Gao, R. , Sun, J. , Yu, Z. , Zhang, Y. : Single-cell biclustering for cell-specific transcriptomic perturbation detection in ad progression. Cell Reports Methods 4(4) (2024)","DOI":"10.1016\/j.crmeth.2024.100742"},{"issue":"11","key":"2026081714301234000_2025.11.21.689783v3.22","doi-asserted-by":"crossref","first-page":"3292","DOI":"10.1038\/s41596-024-01020-z","article-title":"Using clusterprofiler to characterize multiomics data","volume":"19","year":"2024","journal-title":"Nature Protocols"},{"key":"2026081714301234000_2025.11.21.689783v3.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.immuni.2014.05.003"},{"issue":"1","key":"2026081714301234000_2025.11.21.689783v3.24","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1186\/s13073-018-0589-3","article-title":"Genome-wide analyses reveal the ire1a-xbp1 pathway promotes t helper cell differentiation by resolving secretory stress and accelerating proliferation","volume":"10","year":"2018","journal-title":"Genome Medicine"},{"key":"2026081714301234000_2025.11.21.689783v3.25","doi-asserted-by":"crossref","first-page":"932388","DOI":"10.3389\/fimmu.2022.932388","article-title":"Type i interferons promote germinal centers through b cell intrinsic signaling and dendritic cell dependent th1 and tfh cell lineages","volume":"13","year":"2022","journal-title":"Frontiers in Immunology"},{"issue":"2","key":"2026081714301234000_2025.11.21.689783v3.26","first-page":"447","article-title":"mir-125b regulates cell progression in chronic myeloid leukemia via targeting bak1","volume":"8","year":"2016","journal-title":"American Journal of Translational Research"},{"key":"2026081714301234000_2025.11.21.689783v3.27","doi-asserted-by":"publisher","DOI":"10.1002\/iub.404"},{"issue":"613","key":"2026081714301234000_2025.11.21.689783v3.28","doi-asserted-by":"crossref","first-page":"5016","DOI":"10.1126\/scitranslmed.abd5016","article-title":"Ulk1 inhibition promotes oxidative stress\u2013induced differentiation and sensitizes leukemic stem cells to targeted therapy","volume":"13","year":"2021","journal-title":"Science Translational Medicine"},{"issue":"23","key":"2026081714301234000_2025.11.21.689783v3.29","first-page":"2507","article-title":"Identification of a novel enhancer of cebpe essential for granulocytic differentiation","volume":"133","year":"2019","journal-title":"Blood, The Journal of the American Society of Hematology"},{"issue":"1","key":"2026081714301234000_2025.11.21.689783v3.30","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1186\/s40364-020-00242-z","article-title":"The significant role of redox system in myeloid leukemia: from pathogenesis to therapeutic applications","volume":"8","year":"2020","journal-title":"Biomarker Research"},{"key":"2026081714301234000_2025.11.21.689783v3.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2009.04.020"},{"key":"2026081714301234000_2025.11.21.689783v3.32","doi-asserted-by":"publisher","DOI":"10.1101\/gr.138776.112"},{"key":"2026081714301234000_2025.11.21.689783v3.33","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae623"},{"key":"2026081714301234000_2025.11.21.689783v3.34","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-17-2834"},{"issue":"8","key":"2026081714301234000_2025.11.21.689783v3.35","doi-asserted-by":"crossref","first-page":"1491","DOI":"10.1007\/s11064-018-2570-3","article-title":"Akr1b1 upregulation contributes to neuroinflammation and astrocytes proliferation by regulating the energy metabolism in rat spinal cord injury","volume":"43","year":"2018","journal-title":"Neurochemical Research"},{"key":"2026081714301234000_2025.11.21.689783v3.36","doi-asserted-by":"publisher","DOI":"10.1038\/s41573-021-00367-2"},{"key":"2026081714301234000_2025.11.21.689783v3.37","article-title":"scmrdr: A scalable and flexible framework for unpaired single-cell multi-omics data integration","year":"2025","journal-title":"arXiv preprint"},{"key":"2026081714301234000_2025.11.21.689783v3.38","doi-asserted-by":"crossref","unstructured":"Tejada-Lapuerta, A. , Bertin, P. , Bauer, S. , Aliee, H. , Bengio, Y. , Theis, F.J. : Causal machine learning for single-cell genomics. Nature Genetics, 1\u201312 (2025)","DOI":"10.1038\/s41588-025-02124-2"},{"key":"2026081714301234000_2025.11.21.689783v3.39","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08453-2"},{"key":"2026081714301234000_2025.11.21.689783v3.40","doi-asserted-by":"crossref","unstructured":"Metzner, E. , Southard, K.M. , Norman, T.M. : Multiome perturb-seq unlocks scalable discovery of integrated perturbation effects on the transcriptome and epigenome. Cell systems 16(1) (2025)","DOI":"10.1016\/j.cels.2024.12.002"},{"issue":"12","key":"2026081714301234000_2025.11.21.689783v3.41","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","year":"2018","journal-title":"Nature Methods"},{"key":"2026081714301234000_2025.11.21.689783v3.42","unstructured":"Higgins, I. , Matthey, L. , Pal, A. , Burgess, C. , Glorot, X. , Botvinick, M. , Mohamed, S. , Lerchner, A. : beta-VAE: Learning basic visual concepts with a constrained variational framework. In: International Conference on Learning Representations (2017)"},{"key":"2026081714301234000_2025.11.21.689783v3.43","unstructured":"Lopez, R. , Regier, J. , Jordan, M.I. , Yosef, N. : Information constraints on auto-encoding variational bayes. Advances in Neural Information Processing Systems 31 (2018)"},{"key":"2026081714301234000_2025.11.21.689783v3.44","unstructured":"Fukumizu, K. , Gretton, A. , Sun, X. , Sch\u00f6lkopf, B. : Kernel measures of conditional dependence. Advances in neural information processing systems 20 (2007)"},{"key":"2026081714301234000_2025.11.21.689783v3.45","first-page":"16411","article-title":"On the identifiability of nonlinear ica: Sparsity and beyond","volume":"35","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"2026081714301234000_2025.11.21.689783v3.46","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.csda.2004.02.003","article-title":"Improved biclustering of microarray data demonstrated through systematic performance tests","volume":"48","year":"2005","journal-title":"Computational Statistics & Data Analysis"},{"issue":"1","key":"2026081714301234000_2025.11.21.689783v3.47","first-page":"723","article-title":"A kernel two-sample test","volume":"13","year":"2012","journal-title":"The Journal of Machine Learning Research"},{"key":"2026081714301234000_2025.11.21.689783v3.48","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2009.04.020"},{"key":"2026081714301234000_2025.11.21.689783v3.49","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-biochem-032620-104508"},{"key":"2026081714301234000_2025.11.21.689783v3.50","doi-asserted-by":"publisher","DOI":"10.1101\/gr.138776.112"},{"key":"2026081714301234000_2025.11.21.689783v3.51","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae623"},{"key":"2026081714301234000_2025.11.21.689783v3.52","first-page":"16411","article-title":"On the identifiability of nonlinear ICA: Sparsity and beyond","volume":"35","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"2026081714301234000_2025.11.21.689783v3.53","first-page":"13326","article-title":"Generalizing nonlinear ICA beyond structural sparsity","volume":"36","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026081714301234000_2025.11.21.689783v3.54","unstructured":"Li, Z. , Fan, S. , Zheng, Y. , Ng, I. , Xie, S. , Chen, G. , \u2026 & Zhang, K. (2025). Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning. In The Thirteenth International Conference on Learning Representations."},{"key":"2026081714301234000_2025.11.21.689783v3.55","unstructured":"Khemakhem, I. , Kingma, D. , Monti, R. , & Hyvarinen, A. (2020). Variational autoencoders and nonlinear ica: A unifying framework. In International conference on artificial intelligence and statistics (pp. 2207\u20132217). PMLR."},{"key":"2026081714301234000_2025.11.21.689783v3.56","unstructured":"Louizos, C. , Welling, M. , & Kingma, D. P. (2018). Learning Sparse Neural Networks through L0 Regularization. In International Conference on Learning Representations."},{"key":"2026081714301234000_2025.11.21.689783v3.57","unstructured":"Xie, S. , Kong, L. , Gong, M. , & Zhang, K. (2023). Multi-domain image generation and translation with identifiability guarantees. In The Eleventh international conference on learning representations."},{"key":"2026081714301234000_2025.11.21.689783v3.58","doi-asserted-by":"crossref","unstructured":"Chewi, S. , Niles-Weed, J. , & Rigollet, P. (2024). Statistical optimal transport. Springer.","DOI":"10.1007\/978-3-031-85160-5"},{"issue":"1","key":"2026081714301234000_2025.11.21.689783v3.59","doi-asserted-by":"crossref","first-page":"20230071","DOI":"10.1515\/jci-2023-0071","article-title":"Conservative inference for counterfactuals","volume":"13","year":"2025","journal-title":"Journal of Causal Inference"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.11.21.689783","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T21:30:23Z","timestamp":1787002223000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.11.21.689783"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1101\/2025.11.21.689783","relation":{},"subject":[],"published":{"date-parts":[[2025,11,24]]},"subtype":"preprint"}}