{"doi":"10.1145/3765612.3767789","title":"A novel approach to highly variable genes selection for scRNA-Seq analysis","abstract":"Single cell RNA-sequencing (scRNA-Seq) data are typically represented as cell-by-gene count matrices, which capture the expression of each gene as detected in the sampled cells; often a heterogeneous population of multiple different cell types or cell states. Almost all scRNA-Seq analysis workflows have a gene selection step prior to applying clustering algorithms which helps remove genes with low variability and hence reduce the high-dimensional gene space. A defacto method for achieving this selection of highly variable genes (HVG) uses dispersion and mean expression scores to evaluate the variability of each individual gene [3]. However, methods based on mean-variance relationship for gene selection suffer from arbitrary determination of number of genes to use and are susceptible to variance instability.","journal":null,"year":2025,"id":584823,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9477,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1497943,"name":"Tuan Nguyen","orcid":"0009-0006-5196-635X","position":1,"is_corresponding":false},{"id":1497935,"name":"Suryaveer Kapoor","orcid":"0009-0004-7995-6896","position":2,"is_corresponding":false},{"id":38392,"name":"Marmar R. Moussa","orcid":"0000-0003-0574-6656","position":3,"is_corresponding":false},{"id":1497942,"name":"Enos Dk Kakwambi","orcid":"0009-0008-1404-5118","position":0,"is_corresponding":true}],"reference_count":5,"raw_metadata":null,"created_at":"2026-07-19T02:59:16.166424Z","pmid":null,"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":[]}