{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T21:16:15Z","timestamp":1778879775475,"version":"3.51.4"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T00:00:00Z","timestamp":1717113600000},"content-version":"vor","delay-in-days":8,"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":["82273735"],"award-info":[{"award-number":["82273735"]}],"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":["82304252"],"award-info":[{"award-number":["82304252"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Single-cell RNA sequencing has revealed cellular heterogeneity in complex tissues, notably benefiting research on diseases such as cancer. However, the integration of single-cell data from small samples with extensive clinical features in bulk data remains underexplored. In this study, we introduce PIPET, an algorithmic method for predicting relevant subpopulations in single-cell data based on multivariate phenotypic information from bulk data. PIPET generates feature vectors for each phenotype from differentially expressed genes in bulk data and then identifies relevant cellular subpopulations by assessing the similarity between single-cell data and these vectors. Subsequently, phenotype-related cell states can be analyzed based on these subpopulations. In simulated datasets, PIPET showed robust performance in predicting multiclassification cellular subpopulations. Application of PIPET to lung adenocarcinoma single-cell RNA sequencing data revealed cellular subpopulations with poor survival and associations with TP53 mutations. Similarly, in breast cancer single-cell data, PIPET identified cellular subpopulations associated with the PAM50 clinical subtypes and triple-negative breast cancer subtypes. Overall, PIPET effectively identified relevant cellular subpopulations in single-cell data, guided by phenotypic information from bulk data. This approach comprehensively delineates the molecular characteristics of each cellular subpopulation, offering insights into disease-related subpopulations and guiding personalized treatment strategies.<\/jats:p>","DOI":"10.1093\/bib\/bbae260","type":"journal-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T20:23:34Z","timestamp":1717187014000},"source":"Crossref","is-referenced-by-count":6,"title":["PIPET: predicting relevant subpopulations in single-cell data using phenotypic information from bulk data"],"prefix":"10.1093","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2309-2641","authenticated-orcid":false,"given":"Xinjia","family":"Ruan","sequence":"first","affiliation":[{"name":"Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University , Nanjing 211198 , P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University , Nanjing 211198 , P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqing","family":"Ye","sequence":"additional","affiliation":[{"name":"Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University , Nanjing 211198 , P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Wang","sequence":"additional","affiliation":[{"name":"Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University , Nanjing 211198 , P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University , Nanjing 211198 , P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqing","family":"Yang","sequence":"additional","affiliation":[{"name":"Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University , Nanjing 211198 , P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiantian","family":"Liu","sequence":"additional","affiliation":[{"name":"Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University , Nanjing 211198 , P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangrong","family":"Yan","sequence":"additional","affiliation":[{"name":"Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University , Nanjing 211198 , P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,5,31]]},"reference":[{"key":"2024053112364199000_ref1","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1093\/bib\/bbz166","article-title":"SCDC: bulk gene expression deconvolution by multiple single-cell RNA sequencing references","volume":"22","author":"Dong","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024053112364199000_ref2","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.molcel.2019.05.003","article-title":"Single-cell RNA sequencing in cancer: lessons learned and emerging challenges","volume":"75","author":"Suv\u00e0","year":"2019","journal-title":"Mol Cell"},{"key":"2024053112364199000_ref3","doi-asserted-by":"crossref","first-page":"1330","DOI":"10.1016\/j.cell.2019.03.005","article-title":"A single-cell atlas of the tumor and immune ecosystem of human breast cancer","volume":"177","author":"Wagner","year":"2019","journal-title":"Cell"},{"key":"2024053112364199000_ref4","doi-asserted-by":"crossref","first-page":"1396","DOI":"10.1126\/science.1254257","article-title":"Single-cell RNA-seq highlights intratumoral heterogeneity in primary glioblastoma","volume":"344","author":"Patel","year":"2014","journal-title":"Science"},{"key":"2024053112364199000_ref5","doi-asserted-by":"crossref","first-page":"1172","DOI":"10.1016\/j.cell.2019.03.025","article-title":"Adaptive immune resistance emerges from tumor-initiating stem cells","volume":"177","author":"Miao","year":"2019","journal-title":"Cell"},{"key":"2024053112364199000_ref6","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The cancer genome atlas pan-cancer analysis project","volume":"45","author":"Weinstein","year":"2013","journal-title":"Nat Genet"},{"key":"2024053112364199000_ref7","doi-asserted-by":"crossref","first-page":"D955","DOI":"10.1093\/nar\/gks1111","article-title":"Genomics of drug sensitivity in cancer (GDSC): a resource for therapeutic biomarker discovery in cancer cells","volume":"41","author":"Yang","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2024053112364199000_ref8","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/978-1-4939-3578-9_5","article-title":"The gene expression omnibus database","volume":"1418","author":"Clough","year":"2016","journal-title":"Methods Mol Biol"},{"key":"2024053112364199000_ref9","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.1101\/gr.228080.117","article-title":"Linking transcriptional and genetic tumor heterogeneity through allele analysis of single-cell RNA-seq data","volume":"28","author":"Fan","year":"2018","journal-title":"Genome Res"},{"key":"2024053112364199000_ref10","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1158\/2326-6066.CIR-22-0283","article-title":"iBRIDGE: a data integration method to identify inflamed tumors from single-cell RNA-Seq data and differentiate cell type\u2013specific markers of immune-cell infiltration","volume":"11","author":"Turan","year":"2023","journal-title":"Cancer Immunol Res"},{"key":"2024053112364199000_ref11","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1038\/s41587-021-01091-3","article-title":"Identifying phenotype-associated subpopulations by integrating bulk and single-cell sequencing data","volume":"40","author":"Sun","year":"2022","journal-title":"Nat Biotechnol"},{"key":"2024053112364199000_ref12","doi-asserted-by":"crossref","first-page":"12112","DOI":"10.1093\/nar\/gkac1109","article-title":"scAB detects multiresolution cell states with clinical significance by integrating single-cell genomics and bulk sequencing data","volume":"50","author":"Zhang","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2024053112364199000_ref13","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1186\/s13059-021-02546-1","article-title":"splatPop: simulating population scale single-cell RNA sequencing data","volume":"22","author":"Azodi","year":"2021","journal-title":"Genome Biol"},{"key":"2024053112364199000_ref14","doi-asserted-by":"crossref","first-page":"ii141","DOI":"10.1093\/bioinformatics\/btac499","article-title":"SimBu: bias-aware simulation of bulk RNA-seq data with variable cell-type composition","volume":"38","author":"Dietrich","year":"2022","journal-title":"Bioinformatics"},{"key":"2024053112364199000_ref15","doi-asserted-by":"crossref","first-page":"e71","DOI":"10.1093\/nar\/gkv1507","article-title":"TCGAbiolinks: an R\/Bioconductor package for integrative analysis of TCGA data","volume":"44","author":"Colaprico","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2024053112364199000_ref16","doi-asserted-by":"crossref","first-page":"2285","DOI":"10.1038\/s41467-020-16164-1","article-title":"Single-cell RNA sequencing demonstrates the molecular and cellular reprogramming of metastatic lung adenocarcinoma","volume":"11","author":"Kim","year":"2020","journal-title":"Nat Commun"},{"key":"2024053112364199000_ref17","doi-asserted-by":"crossref","first-page":"1334","DOI":"10.1038\/s41588-021-00911-1","article-title":"A single-cell and spatially resolved atlas of human breast cancers","volume":"53","author":"Wu","year":"2021","journal-title":"Nat Genet"},{"key":"2024053112364199000_ref18","doi-asserted-by":"crossref","first-page":"3573","DOI":"10.1016\/j.cell.2021.04.048","article-title":"Integrated analysis of multimodal single-cell data","volume":"184","author":"Hao","year":"2021","journal-title":"Cell"},{"key":"2024053112364199000_ref19","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1186\/s13059-014-0550-8","article-title":"Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2","volume":"15","author":"Love","year":"2014","journal-title":"Genome Biol"},{"key":"2024053112364199000_ref20","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1089\/omi.2011.0118","article-title":"clusterProfiler: an R package for comparing biological themes among gene clusters","volume":"16","author":"Yu","year":"2012","journal-title":"OMICS"},{"key":"2024053112364199000_ref21","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.cels.2015.12.004","article-title":"The molecular signatures database hallmark gene set collection","volume":"1","author":"Liberzon","year":"2015","journal-title":"Cell Syst"},{"key":"2024053112364199000_ref22","doi-asserted-by":"crossref","first-page":"276","DOI":"10.11613\/BM.2012.031","article-title":"Interrater reliability: the kappa statistic","volume":"22","author":"McHugh","year":"2012","journal-title":"Biochem Med (Zagreb)"},{"key":"2024053112364199000_ref23","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/j.intimp.2018.03.005","article-title":"Targeting macrophage immunometabolism: Dawn in the darkness of sepsis","volume":"58","author":"Kumar","year":"2018","journal-title":"Int Immunopharmacol"},{"key":"2024053112364199000_ref24","doi-asserted-by":"crossref","first-page":"100219","DOI":"10.1016\/j.xcrm.2021.100219","article-title":"A single-cell atlas of the healthy breast tissues reveals clinically relevant clusters of breast epithelial cells","volume":"2","author":"Bhat-Nakshatri","year":"2021","journal-title":"Cell Rep Med"},{"key":"2024053112364199000_ref25","doi-asserted-by":"crossref","first-page":"198","DOI":"10.18632\/oncotarget.26559","article-title":"Molecular subtypes of triple-negative breast cancer in women of different race and ethnicity","volume":"10","author":"Ding","year":"2019","journal-title":"Oncotarget"},{"key":"2024053112364199000_ref26","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1158\/1078-0432.CCR-14-0432","article-title":"Comprehensive genomic analysis identifies novel subtypes and targets of triple-negative breast cancer","volume":"21","author":"Burstein","year":"2015","journal-title":"Clin Cancer Res"},{"key":"2024053112364199000_ref27","doi-asserted-by":"crossref","first-page":"bbab024","DOI":"10.1093\/bib\/bbab024","article-title":"Advances in bulk and single-cell multi-omics approaches for systems biology and precision medicine","volume":"22","author":"Li","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024053112364199000_ref28","doi-asserted-by":"crossref","first-page":"1293","DOI":"10.1016\/j.cell.2018.05.060","article-title":"Single-cell map of diverse immune phenotypes in the breast tumor microenvironment","volume":"174","author":"Azizi","year":"2018","journal-title":"Cell"},{"key":"2024053112364199000_ref29","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s13073-022-01012-2","article-title":"Diagnostic evidence GAuge of single cells (DEGAS): a flexible deep transfer learning framework for prioritizing cells in relation to disease","volume":"14","author":"Johnson","year":"2022","journal-title":"Genome Med"},{"key":"2024053112364199000_ref30","article-title":"inferCNV of the Trinity CTAT Project 2019","author":"Tickle"},{"key":"2024053112364199000_ref31","doi-asserted-by":"crossref","first-page":"e15543","DOI":"10.1371\/journal.pone.0015543","article-title":"Nearest template prediction: a single-sample-based flexible class prediction with confidence assessment","volume":"5","author":"Hoshida","year":"2010","journal-title":"PloS One"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/4\/bbae260\/58030337\/bbae260.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/4\/bbae260\/58030337\/bbae260.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T20:23:49Z","timestamp":1717187029000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbae260\/7685752"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,23]]},"references-count":31,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,5,23]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbae260","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,7]]},"published":{"date-parts":[[2024,5,23]]},"article-number":"bbae260"}}