{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T02:35:46Z","timestamp":1785724546176,"version":"3.56.0"},"reference-count":71,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T00:00:00Z","timestamp":1741737600000},"content-version":"vor","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["CA008748"],"award-info":[{"award-number":["CA008748"]}],"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":["CA214845"],"award-info":[{"award-number":["CA214845"]}],"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":["HG012124"],"award-info":[{"award-number":["HG012124"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Accurate sample classification using transcriptomics data is crucial for advancing personalized medicine. Achieving this goal necessitates determining a suitable sample size that ensures adequate classification accuracy without undue resource allocation. Current sample size calculation methods rely on assumptions and algorithms that may not align with supervised machine learning techniques for sample classification. Addressing this critical methodological gap, we present a novel computational approach that establishes the accuracy-versus-sample size relationship by employing a data augmentation strategy followed by fitting a learning curve. We comprehensively evaluated its performance for microRNA and RNA sequencing data, considering diverse data characteristics and algorithm configurations, based on a spectrum of evaluation metrics. To foster accessibility and reproducibility, the Python and R code for implementing our approach is available on GitHub. Its deployment will significantly facilitate the adoption of machine learning in transcriptomics studies and accelerate their translation into clinically useful classifiers for personalized treatment.<\/jats:p>","DOI":"10.1093\/bib\/bbaf097","type":"journal-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T15:13:43Z","timestamp":1741792423000},"source":"Crossref","is-referenced-by-count":1,"title":["Optimizing sample size for supervised machine learning with bulk transcriptomic sequencing: a learning curve approach"],"prefix":"10.1093","volume":"26","author":[{"given":"Yunhui","family":"Qi","sequence":"first","affiliation":[{"name":"Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center , 633 Third Avenue, New York, NY 10017 ,","place":["United States"]},{"name":"Department of Statistics, Iowa State University , 2438 Osborn Drive, Ames, IA, 50011-1090 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center , 633 Third Avenue, New York, NY 10017 ,","place":["United States"]},{"name":"Department of Statistics, The University of California , 1 Shields Ave, Davis, CA 95616 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9367-3807","authenticated-orcid":false,"given":"Li-Xuan","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center , 633 Third Avenue, New York, NY 10017 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,3,12]]},"reference":[{"key":"2025031215132580100_ref1","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1038\/nature06915","article-title":"Enabling personalized cancer medicine through analysis of gene-expression patterns","volume":"452","author":"Van\u2019t Veer","year":"2008","journal-title":"Nature"},{"key":"2025031215132580100_ref2","doi-asserted-by":"publisher","first-page":"S108","DOI":"10.1038\/527S108a","article-title":"Genetics: big hopes for big data","volume":"527","author":"Adams","year":"2015","journal-title":"Nature"},{"key":"2025031215132580100_ref3","doi-asserted-by":"publisher","first-page":"1685","DOI":"10.1016\/S0140-6736(05)66541-5","article-title":"Prediction of cancer outcome with microarrays","volume":"365","author":"Lee","year":"2005","journal-title":"Lancet"},{"key":"2025031215132580100_ref4","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1093\/jnci\/djs027","article-title":"Clinical outcome prediction by microRNAs in human cancer: a systematic review","volume":"104","author":"Nair","year":"2012","journal-title":"J Natl Cancer Inst"},{"key":"2025031215132580100_ref5","doi-asserted-by":"publisher","first-page":"1713","DOI":"10.1001\/jama.2016.4839","article-title":"Moving from clinical trials to precision medicine: the role for predictive modeling","volume":"315","author":"Pencina","year":"2016","journal-title":"JAMA"},{"key":"2025031215132580100_ref6","doi-asserted-by":"publisher","first-page":"417","DOI":"10.3389\/fgene.2014.00417","article-title":"Even modest prediction accuracy of genomic models can have large clinical utility","volume":"5","author":"Dhurandhar","year":"2014","journal-title":"Front Genet"},{"key":"2025031215132580100_ref7","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1038\/ncponc0287","article-title":"Primer: an evidence-based approach to prognostic markers","volume":"2","author":"Altman","year":"2005","journal-title":"Nat Clin Pract Oncol"},{"key":"2025031215132580100_ref8","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1126\/science.aaf5101","article-title":"Countering imprecision in precision medicine","volume":"353","author":"Hey","year":"2016","journal-title":"Science"},{"key":"2025031215132580100_ref9","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1093\/ejcts\/ezy169","article-title":"Statistical primer: sample size and power calculations-why, when and how?","volume":"54","author":"Hickey","year":"2018","journal-title":"Eur J Cardiothorac Surg"},{"key":"2025031215132580100_ref10","doi-asserted-by":"publisher","first-page":"904","DOI":"10.1177\/0962280217738807","article-title":"Sample size requirements for learning to classify with high-dimensional biomarker panels","volume":"28","author":"McKeigue","year":"2019","journal-title":"Stat Methods Med Res"},{"key":"2025031215132580100_ref11","doi-asserted-by":"publisher","first-page":"2701","DOI":"10.1001\/jama.283.20.2701","article-title":"What makes clinical research ethical?","volume":"283","author":"Emanuel","year":"2000","journal-title":"JAMA"},{"key":"2025031215132580100_ref12","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1016\/S0140-6736(02)07882-0","article-title":"Sample size slippages in randomised trials: exclusions and the lost and wayward","volume":"359","author":"Schulz","year":"2002","journal-title":"Lancet"},{"key":"2025031215132580100_ref13","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1093\/bib\/bbr004","article-title":"Design and validation issues in RNA-seq experiments","volume":"12","author":"Fang","year":"2011","journal-title":"Brief Bioinform"},{"key":"2025031215132580100_ref14","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1186\/1471-2105-14-357","article-title":"Sample size calculation based on exact test for assessing differential expression analysis in RNA-seq data","volume":"14","author":"Li","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"2025031215132580100_ref15","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1093\/bioinformatics\/btt015","article-title":"Scotty: a web tool for designing RNA-seq experiments to measure differential gene expression","volume":"29","author":"Busby","year":"2013","journal-title":"Bioinformatics"},{"key":"2025031215132580100_ref16","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1186\/s12859-016-0994-9","article-title":"Sample size calculation while controlling false discovery rate for differential expression analysis with RNA-sequencing experiments","volume":"17","author":"Bi","year":"2016","journal-title":"BMC Bioinformatics"},{"key":"2025031215132580100_ref17","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1093\/bioinformatics\/btu640","article-title":"PROPER: comprehensive power evaluation for differential expression using RNA-seq","volume":"31","author":"Wu","year":"2015","journal-title":"Bioinformatics"},{"key":"2025031215132580100_ref18","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1186\/s12859-017-1648-2","article-title":"Power analysis for RNA-Seq differential expression studies","volume":"18","author":"Yu","year":"2017","journal-title":"BMC Bioinformatics"},{"key":"2025031215132580100_ref19","doi-asserted-by":"publisher","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":"2025031215132580100_ref20","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1093\/biostatistics\/kxj036","article-title":"Sample size planning for developing classifiers using high-dimensional DNA microarray data","volume":"8","author":"Dobbin","year":"2007","journal-title":"Biostatistics"},{"key":"2025031215132580100_ref21","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1158\/1078-0432.CCR-07-0443","article-title":"How large a training set is needed to develop a classifier for microarray data?","volume":"14","author":"Dobbin","year":"2008","journal-title":"Clin Cancer Res"},{"key":"2025031215132580100_ref22","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1093\/biostatistics\/kxp001","article-title":"A simulation-approximation approach to sample size planning for high-dimensional classification studies","volume":"10","author":"Valpine","year":"2009","journal-title":"Biostatistics"},{"key":"2025031215132580100_ref23","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1089\/106652703321825928","article-title":"Estimating dataset size requirements for classifying DNA microarray data","volume":"10","author":"Mukherjee","year":"2003","journal-title":"J Comput Biol"},{"key":"2025031215132580100_ref24","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/1472-6947-12-8","article-title":"Predicting sample size required for classification performance","volume":"12","author":"Figueroa","year":"2012","journal-title":"BMC Med Inform Decis Mak"},{"key":"2025031215132580100_ref25","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-18539-2","volume-title":"Fundamentals of Clinical Trials","author":"Friedman","year":"2015"},{"key":"2025031215132580100_ref26","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1038\/ncomms1033","article-title":"Identification of high-quality cancer prognostic markers and metastasis network modules","volume":"1","author":"Li","year":"2010","journal-title":"Nat Commun"},{"key":"2025031215132580100_ref27","doi-asserted-by":"publisher","first-page":"E2970","DOI":"10.1073\/pnas.1717139115","article-title":"Predicting cancer outcomes from histology and genomics using convolutional networks","volume":"115","author":"Mobadersany","year":"2018","journal-title":"Proc Natl Acad Sci USA"},{"key":"2025031215132580100_ref28","doi-asserted-by":"publisher","first-page":"20170387","DOI":"10.1098\/rsif.2017.0387","article-title":"Opportunities and obstacles for deep learning in biology and medicine","volume":"15","author":"Ching","year":"2018","journal-title":"J R Soc Interface"},{"key":"2025031215132580100_ref29","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"2025031215132580100_ref30","volume-title":"Generative Deep Learning","author":"Foster","year":"2022"},{"key":"2025031215132580100_ref31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2288-10-1","article-title":"A tutorial on pilot studies: the what, why and how","volume":"10","author":"Thabane","year":"2010","journal-title":"BMC Med Res Methodol"},{"key":"2025031215132580100_ref32","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1126\/science.3175664","article-title":"A graph-dynamic model of the power law of practice and the problem-solving fan-effect","volume":"242","author":"Shrager","year":"1988","journal-title":"Science"},{"key":"2025031215132580100_ref33","article-title":"Learning curves: asymptotic values and rate of convergence","volume":"6","author":"Cortes","year":"1993","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2025031215132580100_ref34","doi-asserted-by":"publisher","first-page":"101552","DOI":"10.1016\/j.media.2019.101552","article-title":"Generative adversarial network in medical imaging: a review","volume":"58","author":"Yi","year":"2019","journal-title":"Med Image Anal"},{"key":"2025031215132580100_ref35","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1038\/s41467-019-14018-z","article-title":"Realistic in silico generation and augmentation of single-cell RNA-seq data using generative adversarial networks","volume":"11","author":"Marouf","year":"2020","journal-title":"Nat Commun"},{"key":"2025031215132580100_ref36","doi-asserted-by":"publisher","first-page":"9403","DOI":"10.1038\/s41598-021-88875-4","article-title":"Synthetic single cell RNA sequencing data from small pilot studies using deep generative models","volume":"11","author":"Treppner","year":"2021","journal-title":"Sci Rep"},{"key":"2025031215132580100_ref37","doi-asserted-by":"publisher","first-page":"2194","DOI":"10.1093\/bioinformatics\/btac095","article-title":"ACTIVA: realistic single-cell RNA-seq generation with automatic cell-type identification using introspective variational autoencoders","volume":"38","author":"Heydari","year":"2022","journal-title":"Bioinformatics"},{"key":"2025031215132580100_ref38","first-page":"1530","volume-title":"International Conference on Machine Learning","author":"Rezende","year":"2015"},{"key":"2025031215132580100_ref39","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2025031215132580100_ref40","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"2025031215132580100_ref41","article-title":"Nice: non-linear independent components estimation","author":"Dinh","year":"2014"},{"key":"2025031215132580100_ref42","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/S0092-8674(04)00045-5","article-title":"MicroRNAs: genomics, biogenesis, mechanism, and function","volume":"116","author":"Bartel","year":"2004","journal-title":"Cell"},{"key":"2025031215132580100_ref43","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/nature02871","article-title":"The functions of animal microRNAs","volume":"431","author":"Ambros","year":"2004","journal-title":"Nature"},{"key":"2025031215132580100_ref44","doi-asserted-by":"publisher","first-page":"107836","DOI":"10.1016\/j.asoc.2021.107836","article-title":"Deep learning with small datasets: using autoencoders to address limited datasets in construction management","volume":"112","author":"Davila Delgado","year":"2021","journal-title":"Appl Soft Comput"},{"key":"2025031215132580100_ref45","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1002\/aic.690370209","article-title":"Nonlinear principal component analysis using autoassociative neural networks","volume":"37","author":"Kramer","year":"1991","journal-title":"AICHE J"},{"key":"2025031215132580100_ref46","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1162\/neco.1995.7.1.108","article-title":"Training with noise is equivalent to Tikhonov regularization","volume":"7","author":"Bishop","year":"1995","journal-title":"Neural Comput"},{"key":"2025031215132580100_ref47","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/72.105415","article-title":"Using additive noise in back-propagation training","volume":"3","author":"Holmstrom","year":"1992","journal-title":"IEEE Trans Neural Netw"},{"key":"2025031215132580100_ref48","doi-asserted-by":"crossref","DOI":"10.4324\/9781003177616","volume-title":"Engineering Psychology and Human Performance","author":"Wickens","year":"2021"},{"key":"2025031215132580100_ref49","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.1038\/nature07385","article-title":"Comprehensive genomic characterization defines human glioblastoma genes and core pathways","volume":"455","author":"Network","year":"2008","journal-title":"Nature"},{"key":"2025031215132580100_ref50","doi-asserted-by":"publisher","first-page":"e3","DOI":"10.1093\/nar\/gkv808","article-title":"Large-scale profiling of microRNAs for The Cancer Genome Atlas","volume":"44","author":"Chu","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2025031215132580100_ref51","doi-asserted-by":"publisher","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":"2025031215132580100_ref52","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1186\/1471-2105-11-94","article-title":"Evaluation of statistical methods for normalization and differential expression in mRNA-seq experiments","volume":"11","author":"Bullard","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2025031215132580100_ref53","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1200\/CCI.19.00118","article-title":"Statistical assessment of depth normalization for small RNA sequencing","volume":"4","author":"Qin","year":"2020","journal-title":"JCO Clin Cancer Inform"},{"key":"2025031215132580100_ref54","doi-asserted-by":"publisher","first-page":"823431","DOI":"10.3389\/fgene.2021.823431","article-title":"PRECISION.Seq: an R package for benchmarking depth normalization in microRNA sequencing","volume":"12","author":"Zou","year":"2021","journal-title":"Front Genet"},{"key":"2025031215132580100_ref55","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"Guyon","year":"2003","journal-title":"J Mach Learn Res"},{"key":"2025031215132580100_ref56","doi-asserted-by":"publisher","DOI":"10.1002\/9781118445112.stat06232","article-title":"Median absolute deviation","author":"Howell","year":"2014","journal-title":"Wiley StatsRef"},{"key":"2025031215132580100_ref57","doi-asserted-by":"publisher","first-page":"e56","DOI":"10.1093\/nar\/gkac064","article-title":"Depth normalization of small RNA sequencing: using data and biology to select a suitable method","volume":"50","author":"D\u00fcren","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2025031215132580100_ref58","doi-asserted-by":"publisher","first-page":"255","DOI":"10.2307\/2532051","article-title":"A concordance correlation coefficient to evaluate reproducibility","volume":"45","author":"Lawrence","year":"1989","journal-title":"Biometrics"},{"key":"2025031215132580100_ref59","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1080\/01621459.1971.10482356","article-title":"Objective criteria for the evaluation of clustering methods","volume":"66","author":"Rand","year":"1971","journal-title":"J Am Stat Assoc"},{"key":"2025031215132580100_ref60","article-title":"Umap: uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018"},{"key":"2025031215132580100_ref61","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1038\/s41591-020-0839-y","article-title":"Interplay of somatic alterations and immune infiltration modulates response to PD-1 blockade in advanced clear cell renal cell carcinoma","volume":"26","author":"Braun","year":"2020","journal-title":"Nat Med"},{"key":"2025031215132580100_ref62","article-title":"Optimizing the latent space of generative networks","author":"Bojanowski","year":"2017"},{"key":"2025031215132580100_ref63","first-page":"214","volume-title":"Wasserstein Generative Adversarial Networks","author":"Arjovsky"},{"key":"2025031215132580100_ref64","article-title":"Improved training of Wasserstein GANs","volume":"30","author":"Gulrajani","year":"2017","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2025031215132580100_ref65","article-title":"Masked autoregressive flow for density estimation","volume":"30","author":"Papamakarios","year":"2017","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2025031215132580100_ref66","article-title":"Density estimation using real NVP","author":"Dinh","year":"2016"},{"key":"2025031215132580100_ref67","article-title":"Glow: generative flow with invertible 1x1 convolutions","volume":"31","author":"Kingma","year":"2018","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2025031215132580100_ref68","article-title":"A gentle introduction to early stopping to avoid overtraining neural networks","author":"Brownlee","year":"2019","journal-title":"Mach Learn Mastery"},{"key":"2025031215132580100_ref69","doi-asserted-by":"publisher","first-page":"199440","DOI":"10.1109\/ACCESS.2020.3034828","article-title":"Balancing reconstruction error and Kullback-Leibler divergence in variational autoencoders","volume":"8","author":"Asperti","year":"2020","journal-title":"IEEE Access"},{"key":"2025031215132580100_ref70","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1080\/095400996116866","article-title":"A survey of transfer between connectionist networks","volume":"8","author":"Pratt","year":"1996","journal-title":"Connect Sci"},{"key":"2025031215132580100_ref71","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1038\/s41592-019-0537-1","article-title":"Data denoising with transfer learning in single-cell transcriptomics","volume":"16","author":"Wang","year":"2019","journal-title":"Nat Methods"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf097\/62386203\/bbaf097.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf097\/62386203\/bbaf097.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T15:13:48Z","timestamp":1741792428000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf097\/8071685"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":71,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,3,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf097","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,3]]},"published":{"date-parts":[[2025,3]]},"article-number":"bbaf097"}}