biostudies-literatureGao CHoward Hughes Medical InstituteNIAID NIH HHSNIMH NIH HHSNHGRI NIH HHSNCI NIH HHSU.S. Department of Health & Human Services | NIH | National Human Genome Research InstituteU.S. Department of Health & Human Services | NIH | National Institute of Mental HealthDivision of Intramural Research, National Institute of Allergy and Infectious Diseases1000-1007https://www.ebi.ac.uk/biostudies/studies/S-EPMC8355612biostudies-literatureUnknown39(8)Integrating large single-cell gene expression, chromatin accessibility and DNA methylation datasets requires general and scalable computational approaches. Here we describe online integrative non-negative matrix factorization (iNMF), an algorithm for integrating large, diverse and continually arriving single-cell datasets. Our approach scales to arbitrarily large numbers of cells using fixed memory, iteratively incorporates new datasets as they are generated and allows many users to simultaneously analyze a single copy of a large dataset by streaming it over the internet. Iterative data addition can also be used to map new data to a reference dataset. Comparisons with previous methods indicate that the improvements in efficiency do not sacrifice dataset alignment and cluster preservation pNature biotechnologyIterative single-cell multi-omic integration using online learning.PMC8355612RF1 MH123199U19MH114831R01 AI149669R01 HG010883P30 CA014195T32 HG000040U19 MH114831Kriebel ARLiu JSandoval JBehrens MMPreissl SLuo CRivkin AGao CRen BCastanon RNery JREcker JRWelch JDfalseIterative single-cell multi-omic integration using online learning.Integrating large single-cell gene expression, chromatin accessibility and DNA methylation datasets requires general and scalable computational approaches. Here we describe online integrative non-negative matrix factorization (iNMF), an algorithm for integrating large, diverse and continually arriving single-cell datasets. Our approach scales to arbitrarily large numbers of cells using fixed memory, iteratively incorporates new datasets as they are generated and allows many users to simultaneously analyze a single copy of a large dataset by streaming it over the internet. Iterative data addition can also be used to map new data to a reference dataset. Comparisons with previous methods indicate that the improvements in efficiency do not sacrifice dataset alignment and cluster preservation p2021-01-01T00:00:00Z2021 Aug2025-04-04T21:30:39.751Z2025-04-04T21:30:39.751ZS-EPMC83556123387586610.1038/s41587-021-00867-x