{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T19:35:20Z","timestamp":1768505720717,"version":"3.49.0"},"posted":{"date-parts":[[2023,3,25]]},"group-title":"Bioinformatics","reference-count":57,"publisher":"openRxiv","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2023,3,25]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Accurately identifying phenotype-relevant cell subsets from heterogeneous cell populations is crucial for delineating the underlying mechanisms driving biological or clinical phenotypes. Here, by deploying a learning with rejection strategy, we developed a novel supervised learning framework called PENCIL to identify subpopulations associated with categorical or continuous phenotypes from single-cell data. By embedding a feature selection function into this flexible framework, for the first time, we were able to select informative features and identify cell subpopulations simultaneously, which enables the accurate identification of phenotypic subpopulations otherwise missed by methods incapable of concurrent gene selection. Furthermore, the regression mode of PENCIL presents a novel ability for supervised phenotypic trajectory learning of subpopulations from single-cell data. We conducted comprehensive simulations to evaluate PENCIL\u2019s versatility in simultaneous gene selection, subpopulation identification and phenotypic trajectory prediction. PENCIL is fast and scalable to analyze 1 million cells within 1 hour. Using the classification mode, PENCIL detected T-cell subpopulations associated with melanoma immunotherapy outcomes. Moreover, when applied to scRNA-seq of a mantle cell lymphoma patient with drug treatment across multiple time points, the regression mode of PENCIL revealed a transcriptional treatment response trajectory. Collectively, our work introduces a scalable and flexible infrastructure to accurately identify phenotype-associated subpopulations from single-cell data.<\/jats:p>","DOI":"10.1101\/2023.03.23.533712","type":"posted-content","created":{"date-parts":[[2023,3,25]],"date-time":"2023-03-25T17:15:15Z","timestamp":1679764515000},"source":"Crossref","is-referenced-by-count":3,"title":["Supervised learning of high-confidence phenotypic subpopulations from single-cell data"],"prefix":"10.64898","author":[{"given":"Tao","family":"Ren","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Canping","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexey V.","family":"Danilov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Susan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangnan","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunyi","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiwei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mara H.","family":"Sherman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4810-0022","authenticated-orcid":false,"given":"Paul T.","family":"Spellman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lisa M.","family":"Coussens","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew C.","family":"Adey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gordon B.","family":"Mills","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9487-0215","authenticated-orcid":false,"given":"Ling-Yun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3364-8324","authenticated-orcid":false,"given":"Zheng","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2023032903250500000_2023.03.23.533712v1.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2019.03.025"},{"key":"2023032903250500000_2023.03.23.533712v1.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2019.03.005"},{"key":"2023032903250500000_2023.03.23.533712v1.3","doi-asserted-by":"publisher","DOI":"10.1101\/gr.190595.115"},{"key":"2023032903250500000_2023.03.23.533712v1.4","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01329-2"},{"key":"2023032903250500000_2023.03.23.533712v1.5","doi-asserted-by":"crossref","unstructured":"Ekiz, H.A. et al. MicroRNA-155 coordinates the immunological landscape within murine melanoma and correlates with immunity in human cancers. JCI Insight 4 (2019).","DOI":"10.1172\/jci.insight.126543"},{"key":"2023032903250500000_2023.03.23.533712v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.10.038"},{"key":"2023032903250500000_2023.03.23.533712v1.7","doi-asserted-by":"crossref","first-page":"7292","DOI":"10.1038\/s41467-021-27615-8","article-title":"Epigenetic loss of heterogeneity from low to high grade localized prostate tumours","volume":"12","year":"2021","journal-title":"Nat Commun"},{"key":"2023032903250500000_2023.03.23.533712v1.8","doi-asserted-by":"crossref","first-page":"1628","DOI":"10.1038\/s41467-021-21884-z","article-title":"Single-cell transcriptional changes associated with drug tolerance and response to combination therapies in cancer","volume":"12","year":"2021","journal-title":"Nat Commun"},{"key":"2023032903250500000_2023.03.23.533712v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.4295"},{"key":"2023032903250500000_2023.03.23.533712v1.10","doi-asserted-by":"crossref","unstructured":"Zhao, J. et al. Detection of differentially abundant cell subpopulations in scRNA-seq data. Proc Natl Acad Sci U S A 118 (2021).","DOI":"10.1073\/pnas.2100293118"},{"key":"2023032903250500000_2023.03.23.533712v1.11","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1038\/s41587-021-01033-z","article-title":"Differential abundance testing on single-cell data using k-nearest neighbor graphs","volume":"40","year":"2022","journal-title":"Nat Biotechnol"},{"key":"2023032903250500000_2023.03.23.533712v1.12","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1038\/s41587-020-00803-5","article-title":"Quantifying the effect of experimental perturbations at single-cell resolution","volume":"39","year":"2021","journal-title":"Nat Biotechnol"},{"key":"2023032903250500000_2023.03.23.533712v1.13","doi-asserted-by":"crossref","unstructured":"Sheng, J. & Li, W.V . Selecting gene features for unsupervised analysis of single-cell gene expression data. Brief Bioinform 22 (2021).","DOI":"10.1093\/bib\/bbab295"},{"key":"2023032903250500000_2023.03.23.533712v1.14","doi-asserted-by":"crossref","unstructured":"Townes, F.W. , Hicks, S.C. , Aryee, M.J. & Irizarry, R.A . Feature selection and dimension reduction for single-cell RNA-Seq based on a multinomial model. Genome Biol 20, 295 (2019).","DOI":"10.1186\/s13059-019-1861-6"},{"key":"2023032903250500000_2023.03.23.533712v1.15","doi-asserted-by":"crossref","unstructured":"Farrell, J.A. et al. Single-cell reconstruction of developmental trajectories during zebrafish embryogenesis. Science 360 (2018).","DOI":"10.1126\/science.aar3131"},{"key":"2023032903250500000_2023.03.23.533712v1.16","doi-asserted-by":"publisher","DOI":"10.1038\/nature25980"},{"key":"2023032903250500000_2023.03.23.533712v1.17","doi-asserted-by":"crossref","unstructured":"Baran-Gale, J. et al. Ageing compromises mouse thymus function and remodels epithelial cell differentiation. Elife 9 (2020).","DOI":"10.7554\/eLife.56221"},{"key":"2023032903250500000_2023.03.23.533712v1.18","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.4402"},{"key":"2023032903250500000_2023.03.23.533712v1.19","doi-asserted-by":"crossref","first-page":"1903","DOI":"10.1038\/s41467-019-09670-4","article-title":"Single-cell trajectories reconstruction, exploration and mapping of omics data with STREAM","volume":"10","year":"2019","journal-title":"Nat Commun"},{"key":"2023032903250500000_2023.03.23.533712v1.20","doi-asserted-by":"crossref","unstructured":"Street, K. et al. Slingshot: cell lineage and pseudotime inference for single-cell transcriptomics. BMC Genomics 19, 477 (2018).","DOI":"10.1186\/s12864-018-4772-0"},{"key":"2023032903250500000_2023.03.23.533712v1.21","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1038\/s41592-021-01346-6","article-title":"CellRank for directed single-cell fate mapping","volume":"19","year":"2022","journal-title":"Nat Methods"},{"key":"2023032903250500000_2023.03.23.533712v1.22","doi-asserted-by":"crossref","unstructured":"Becht, E. et al. Dimensionality reduction for visualizing single-cell data using UMAP. Nat Biotechnol (2018).","DOI":"10.1038\/nbt.4314"},{"key":"2023032903250500000_2023.03.23.533712v1.23","doi-asserted-by":"crossref","first-page":"3942","DOI":"10.1038\/s41467-021-24152-2","article-title":"Spearheading future omics analyses using dyngen, a multi-modal simulator of single cells","volume":"12","year":"2021","journal-title":"Nat Commun"},{"key":"2023032903250500000_2023.03.23.533712v1.24","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1038\/s41587-020-00748-9","article-title":"A multicenter study benchmarking single-cell RNA sequencing technologies using reference samples","volume":"39","year":"2021","journal-title":"Nat Biotechnol"},{"key":"2023032903250500000_2023.03.23.533712v1.25","doi-asserted-by":"publisher","DOI":"10.1016\/J.CELL.2021.04.048"},{"key":"2023032903250500000_2023.03.23.533712v1.26","doi-asserted-by":"crossref","unstructured":"Zappia, L. , Phipson, B. & Oshlack, A . Splatter: simulation of single-cell RNA sequencing data. Genome Biology 18, 174 (2017).","DOI":"10.1186\/s13059-017-1305-0"},{"key":"2023032903250500000_2023.03.23.533712v1.27","doi-asserted-by":"crossref","unstructured":"Ruan, X. et al. Progenitor cell diversity in the developing mouse neocortex. Proc Natl Acad Sci U S A 118 (2021).","DOI":"10.1073\/pnas.2018866118"},{"key":"2023032903250500000_2023.03.23.533712v1.28","doi-asserted-by":"crossref","unstructured":"Wolf, F.A. , Angerer, P. & Theis, F.J . SCANPY: large-scale single-cell gene expression data analysis. Genome Biol 19, 15 (2018).","DOI":"10.1186\/s13059-017-1382-0"},{"key":"2023032903250500000_2023.03.23.533712v1.29","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-0969-x"},{"key":"2023032903250500000_2023.03.23.533712v1.30","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar4060"},{"key":"2023032903250500000_2023.03.23.533712v1.31","doi-asserted-by":"publisher","DOI":"10.1158\/2159-8290.CD-18-0367"},{"key":"2023032903250500000_2023.03.23.533712v1.32","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1016\/j.cell.2018.11.043","article-title":"Dysfunctional CD8 T Cells Form a Proliferative, Dynamically Regulated Compartment within Human Melanoma","volume":"176","year":"2019","journal-title":"Cell"},{"key":"2023032903250500000_2023.03.23.533712v1.33","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1038\/s41586-019-1324-y","article-title":"TOX is a critical regulator of tumour-specific T cell differentiation","volume":"571","year":"2019","journal-title":"Nature"},{"key":"2023032903250500000_2023.03.23.533712v1.34","doi-asserted-by":"publisher","DOI":"10.1126\/science.aad0501"},{"key":"2023032903250500000_2023.03.23.533712v1.35","unstructured":"Tickle, T. , Tirosh, I. , Georgescu, C. , Brown, M. & Haas, B . inferCNV of the Trinity CTAT Project. Klarman Cell Observatory , Broad Institute of MIT and Harvard (2019)."},{"key":"2023032903250500000_2023.03.23.533712v1.36","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2010-01-263806"},{"key":"2023032903250500000_2023.03.23.533712v1.37","doi-asserted-by":"publisher","DOI":"10.1093\/emboj\/cdf389"},{"key":"2023032903250500000_2023.03.23.533712v1.38","doi-asserted-by":"publisher","DOI":"10.3109\/10428194.2015.1034704"},{"key":"2023032903250500000_2023.03.23.533712v1.39","doi-asserted-by":"crossref","unstructured":"Balaji, S. et al. NF-kappaB signaling and its relevance to the treatment of mantle cell lymphoma. J Hematol Oncol 11, 83 (2018).","DOI":"10.1186\/s13045-018-0621-5"},{"key":"2023032903250500000_2023.03.23.533712v1.40","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-13-0987"},{"key":"2023032903250500000_2023.03.23.533712v1.41","doi-asserted-by":"crossref","unstructured":"Dus-Szachniewicz, K. , Gdesz-Birula, K. , Zduniak, K. & Wisniewski, J.R . Proteomic-Based Analysis of Hypoxia- and Physioxia-Responsive Proteins and Pathways in Diffuse Large B-Cell Lymphoma. Cells 10 (2021).","DOI":"10.3390\/cells10082025"},{"key":"2023032903250500000_2023.03.23.533712v1.42","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.4112"},{"key":"2023032903250500000_2023.03.23.533712v1.43","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau0730"},{"key":"2023032903250500000_2023.03.23.533712v1.44","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1038\/s41587-019-0290-0","article-title":"High-throughput sequencing of the transcriptome and chromatin accessibility in the same cell","volume":"37","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2023032903250500000_2023.03.23.533712v1.45","first-page":"1823","article-title":"Classification with a Reject Option using a Hinge Loss","volume":"9","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2023032903250500000_2023.03.23.533712v1.46","first-page":"67","article-title":"Learning with Rejection","volume":"9925","year":"2016","journal-title":"Lect Notes Artif Int"},{"key":"2023032903250500000_2023.03.23.533712v1.47","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1002\/cjs.5550340410","article-title":"Classification with reject option","volume":"34","year":"2006","journal-title":"Can J Stat"},{"key":"2023032903250500000_2023.03.23.533712v1.48","doi-asserted-by":"crossref","unstructured":"Asif, A. & Minhas, F.U.A . Generalized Neural Framework for Learning with Rejection. Ieee Ijcnn (2020).","DOI":"10.1109\/IJCNN48605.2020.9206612"},{"key":"2023032903250500000_2023.03.23.533712v1.49","unstructured":"Charoenphakdee, N. , Cui, Z.H. , Zhang, Y.A. & Sugiyama, M . Classification with Rejection Based on Cost-sensitive Classification. Pr Mach Learn Res 139 (2021)."},{"key":"2023032903250500000_2023.03.23.533712v1.50","unstructured":"Misra, D. Mish: A self regularized non-monotonic activation function. arXiv preprint arXiv :1908.08681 (2019)."},{"key":"2023032903250500000_2023.03.23.533712v1.51","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2019.05.031"},{"key":"2023032903250500000_2023.03.23.533712v1.52","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btp616"},{"key":"2023032903250500000_2023.03.23.533712v1.53","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.4150"},{"key":"2023032903250500000_2023.03.23.533712v1.54","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.cels.2015.12.004","article-title":"The Molecular Signatures Database (MSigDB) hallmark gene set collection","volume":"1","year":"2015","journal-title":"Cell Syst"},{"key":"2023032903250500000_2023.03.23.533712v1.55","doi-asserted-by":"crossref","first-page":"2068","DOI":"10.18632\/oncotarget.28063","article-title":"NEDD8-activating enzyme inhibition induces cell cycle arrest and anaphase catastrophe in malignant T-cells","volume":"12","year":"2021","journal-title":"Oncotarget"},{"key":"2023032903250500000_2023.03.23.533712v1.56","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/j.cels.2019.03.003","article-title":"DoubletFinder: Doublet Detection in Single-Cell RNA Sequencing Data Using Artificial Nearest Neighbors","volume":"8","year":"2019","journal-title":"Cell Syst"},{"key":"2023032903250500000_2023.03.23.533712v1.57","doi-asserted-by":"publisher","DOI":"10.1038\/s41590-018-0276-y"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2023.03.23.533712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T04:27:38Z","timestamp":1768451258000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2023.03.23.533712"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,25]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1101\/2023.03.23.533712","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1038\/s42256-023-00656-y","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2023,3,25]]},"subtype":"preprint"}}