{"doi":"10.1145/3459930.3469523","title":"Fast and memory-efficient scRNA-seq <i>k</i> -means clustering with various distances","abstract":"Single-cell RNA-sequencing (scRNA-seq) analyses typically begin by clustering a gene-by-cell expression matrix to empirically define groups of cells with similar expression profiles. We describe new methods and a new open source library, minicore, for efficient k-means++ center finding and k-means clustering of scRNA-seq data. Minicore works with sparse count data, as it emerges from typical scRNA-seq experiments, as well as with dense data from after dimensionality reduction. Minicore's novel vectorized weighted reservoir sampling algorithm allows it to find initial k-means++ centers for a 4-million cell dataset in 1.5 minutes using 20 threads. Minicore can cluster using Euclidean distance, but also supports a wider class of measures like Jensen-Shannon Divergence, Kullback-Leibler Divergence, and the Bhattacharyya distance, which can be directly applied to count data and probability distributions.","journal":"PubMed","year":2021,"id":215176,"datarank":0.31191623125197543,"base_score":2.0794415416798357,"endowment":2.0794415416798357,"self_citation_contribution":0.31191623125197543,"citation_network_contribution":0.0,"self_endowment_contribution":0.31191623125197543,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":7,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9542,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":240433,"name":"Nathan Dyjack","orcid":"0000-0001-6944-6252","position":1,"is_corresponding":false},{"id":553753,"name":"Vladimir Braverman","orcid":"0000-0001-7709-8753","position":2,"is_corresponding":false},{"id":1437,"name":"Stephanie C. Hicks","orcid":"0000-0002-7858-0231","position":3,"is_corresponding":false},{"id":18148,"name":"Ben Langmead","orcid":"0000-0003-2437-1976","position":4,"is_corresponding":false},{"id":563545,"name":"Daniel N. Baker","orcid":"0000-0002-0513-6893","position":0,"is_corresponding":true}],"reference_count":28,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-18T23:52:51.201033Z","pmid":"34778889","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}