{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T06:50:29Z","timestamp":1784357429092,"version":"3.55.0"},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T00:00:00Z","timestamp":1725408000000},"content-version":"vor","delay-in-days":3,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P30 CA068485"],"award-info":[{"award-number":["P30 CA068485"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U24 CA163056"],"award-info":[{"award-number":["U24 CA163056"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P50 CA236733"],"award-info":[{"award-number":["P50 CA236733"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P50 CA098131"],"award-info":[{"award-number":["P50 CA098131"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U54 CA163072"],"award-info":[{"award-number":["U54 CA163072"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U2C CA233291"],"award-info":[{"award-number":["U2C CA233291"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P01 CA229123"],"award-info":[{"award-number":["P01 CA229123"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P01 AI139449"],"award-info":[{"award-number":["P01 AI139449"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U54 CA274367"],"award-info":[{"award-number":["U54 CA274367"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Differential expression analysis in single-cell transcriptomics unveils cell type-specific responses to various treatments or biological conditions. To ensure the robustness and reliability of the analysis, it is essential to have a solid experimental design with ample statistical power and sample size. However, existing methods for power and sample size calculation often assume a specific distribution for single-cell transcriptomics data, potentially deviating from the true data distribution. Moreover, they commonly overlook cell\u2013cell correlations within individual samples, posing challenges in accurately representing biological phenomena. Additionally, due to the complexity of deriving an analytic formula, most methods employ time-consuming simulation-based strategies.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We propose an analytic-based method named scPS for calculating power and sample sizes based on generalized estimating equations. scPS stands out by making no assumptions about the data distribution and considering cell\u2013cell correlations within individual samples. scPS is a rapid and powerful approach for designing experiments in single-cell differential expression analysis.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>scPS is freely available at https:\/\/github.com\/cyhsuTN\/scPS and Zenodo https:\/\/zenodo.org\/records\/13375996.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae540","type":"journal-article","created":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T07:37:49Z","timestamp":1725521869000},"source":"Crossref","is-referenced-by-count":1,"title":["A distribution-free and analytic method for power and sample size calculation in single-cell differential expression"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8325-2112","authenticated-orcid":false,"given":"Chih-Yuan","family":"Hsu","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Vanderbilt University Medical Center , Nashville, TN 37203, United States"},{"name":"Center for Quantitative Sciences, Vanderbilt University Medical Center , Nashville, TN 37203, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8892-7078","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Vanderbilt University Medical Center , Nashville, TN 37203, United States"},{"name":"Center for Quantitative Sciences, Vanderbilt University Medical Center , Nashville, TN 37203, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Shyr","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Vanderbilt University Medical Center , Nashville, TN 37203, United States"},{"name":"Center for Quantitative Sciences, Vanderbilt University Medical Center , Nashville, TN 37203, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,9,4]]},"reference":[{"key":"2024091720473959800_btae540-B1","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: a practical and powerful approach to multiple hypothesis testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J R Stat Soc B"},{"key":"2024091720473959800_btae540-B2","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1186\/s12915-023-01613-2","article-title":"Single-cell and spatial transcriptomics reveal changes in cell heterogeneity during progression of human tendinopathy","volume":"21","author":"Fu","year":"2023","journal-title":"BMC Biol"},{"key":"2024091720473959800_btae540-B3","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1038\/s41586-020-03148-w","article-title":"Circuits between infected macrophages and T cells in SARS-CoV-2 pneumonia","volume":"590","author":"Grant","year":"2021","journal-title":"Nature"},{"key":"2024091720473959800_btae540-B5","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1186\/s13059-019-1874-1","article-title":"Normalization and variance stabilization of single-cell RNA-seq data using regularized negative binomial regression","volume":"20","author":"Hafemeister","year":"2019","journal-title":"Genome Biol"},{"key":"2024091720473959800_btae540-B6","doi-asserted-by":"crossref","first-page":"btae008","DOI":"10.1093\/bioinformatics\/btae008","article-title":"scKWARN: kernel-weighted-average robust normalization for single-cell RNA-seq data","volume":"40","author":"Hsu","year":"2024","journal-title":"Bioinformatics"},{"key":"2024091720473959800_btae540-B7","doi-asserted-by":"crossref","first-page":"221","DOI":"10.3390\/biom13020221","article-title":"Statistical power analysis for designing bulk, single-cell, and spatial transcriptomics experiments: review, tutorial, and perspectives","volume":"13","author":"Jeon","year":"2023","journal-title":"Biomolecules"},{"key":"2024091720473959800_btae540-B8","doi-asserted-by":"crossref","first-page":"3097","DOI":"10.1093\/bioinformatics\/bti456","article-title":"Sample size for FDR-control in microarray data analysis","volume":"21","author":"Jung","year":"2005","journal-title":"Bioinformatics"},{"key":"2024091720473959800_btae540-B10","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.cell.2023.11.032","article-title":"Time-resolved single-cell transcriptomics defines immune trajectories in glioblastoma","volume":"187","author":"Kirschenbaum","year":"2024","journal-title":"Cell"},{"key":"2024091720473959800_btae540-B11","doi-asserted-by":"crossref","first-page":"i41","DOI":"10.1093\/bioinformatics\/btz321","article-title":"A statistical simulator scDesign for rational scRNA-seq experimental design","volume":"35","author":"Li","year":"2019","journal-title":"Bioinformatics"},{"key":"2024091720473959800_btae540-B12","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1093\/biomet\/73.1.13","article-title":"Longitudinal data analysis using generalized linear models","volume":"73","author":"Liang","year":"1986","journal-title":"Biometrika"},{"key":"2024091720473959800_btae540-B13","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1080\/10618600.2017.1321552","article-title":"One-step generalized estimating equations with large cluster sizes","volume":"26","author":"Lipsitz","year":"2017","journal-title":"J Comput Graph Stat"},{"key":"2024091720473959800_btae540-B14","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1186\/s13059-016-0947-7","article-title":"Pooling across cells to normalize single-cell RNA sequencing data with many zero counts","volume":"17","author":"Lun","year":"2016","journal-title":"Genome Biol"},{"key":"2024091720473959800_btae540-B15","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1111\/j.0006-341X.2001.00126.x","article-title":"A covariance estimator for GEE with improved small-sample properties","volume":"57","author":"Mancl","year":"2001","journal-title":"Biometrics"},{"key":"2024091720473959800_btae540-B16","author":"McDavid","year":"2024"},{"key":"2024091720473959800_btae540-B17","doi-asserted-by":"crossref","first-page":"344","DOI":"10.3390\/genes15030344","article-title":"Computing power and sample size for the false discovery rate in multiple applications","volume":"15","author":"Ni","year":"2024","journal-title":"Genes (Basel)"},{"key":"2024091720473959800_btae540-B18","doi-asserted-by":"crossref","first-page":"E47","DOI":"10.1093\/nar\/gkv007","article-title":"Limma powers differential expression analyses for RNA-sequencing and microarray studies","volume":"43","author":"Ritchie","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2024091720473959800_btae540-B19","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1093\/bioinformatics\/btp616","article-title":"edgeR: a bioconductor package for differential expression analysis of digital gene expression data","volume":"26","author":"Robinson","year":"2010","journal-title":"Bioinformatics"},{"key":"2024091720473959800_btae540-B20","doi-asserted-by":"crossref","first-page":"998","DOI":"10.1016\/j.cell.2018.10.038","article-title":"Defining T cell states associated with response to checkpoint immunotherapy in melanoma","volume":"175","author":"Sade-Feldman","year":"2018","journal-title":"Cell"},{"key":"2024091720473959800_btae540-B21","doi-asserted-by":"crossref","first-page":"6625","DOI":"10.1038\/s41467-021-26779-7","article-title":"scPower accelerates and optimizes the design of multi-sample single cell transcriptomic studies","volume":"12","author":"Schmid","year":"2021","journal-title":"Nat Commun"},{"key":"2024091720473959800_btae540-B23","doi-asserted-by":"crossref","first-page":"4860","DOI":"10.1093\/bioinformatics\/btaa607","article-title":"Simulation, power evaluation and sample size recommendation for single-cell RNA-seq","volume":"36","author":"Su","year":"2020","journal-title":"Bioinformatics"},{"key":"2024091720473959800_btae540-B24","doi-asserted-by":"crossref","first-page":"3486","DOI":"10.1093\/bioinformatics\/btx435","article-title":"powsimR: power analysis for bulk and single cell RNA-seq experiments","volume":"33","author":"Vieth","year":"2017","journal-title":"Bioinformatics"},{"key":"2024091720473959800_btae540-B25","doi-asserted-by":"crossref","first-page":"958","DOI":"10.1136\/gutjnl-2021-326070","article-title":"Single-cell RNA-seq analysis reveals BHLHE40-driven pro-tumour neutrophils with hyperactivated glycolysis in pancreatic tumour microenvironment","volume":"72","author":"Wang","year":"2023","journal-title":"Gut"},{"key":"2024091720473959800_btae540-B26","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1002\/sim.5947","article-title":"Sample size calculation for comparing two negative binomial rates","volume":"33","author":"Zhu","year":"2014","journal-title":"Stat Med"},{"key":"2024091720473959800_btae540-B27","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1186\/s12864-021-07635-w","article-title":"Hierarchicell: an R-package for estimating power for tests of differential expression with single-cell data","volume":"22","author":"Zimmerman","year":"2021","journal-title":"BMC Genomics"},{"key":"2024091720473959800_btae540-B28","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1038\/s41467-021-21038-1","article-title":"A practical solution to pseudoreplication bias in single-cell studies","volume":"12","author":"Zimmerman","year":"2021","journal-title":"Nat Commun"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae540\/59020452\/btae540.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/9\/btae540\/59157753\/btae540.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/9\/btae540\/59157753\/btae540.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T20:48:03Z","timestamp":1726606083000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae540\/7749386"}},"subtitle":[],"editor":[{"given":"Anthony","family":"Mathelier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":25,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,9,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae540","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,9]]},"published":{"date-parts":[[2024,9]]},"article-number":"btae540"}}