Single-cell data integration involves removing unwanted technical variations across multiple datasets. We introduce expiMap, an intepretable generative model that maps single cells to reference atlas1 and gene programs. Here, we describe a protocol for building an initial reference atlas, mapping new datasets as queries, and identifying gene programs that split between populations. This protocol is associated with our Nature Cell Biology paper describing this model: Biologically informed deep learning to query gene programs in single-cell atlases.
","journal":"Research Square","year":2023,"id":213,"datarank":0.10397207708399181,"base_score":0.6931471805599453,"endowment":0.6931471805599453,"self_citation_contribution":0.10397207708399181,"citation_network_contribution":0.0,"self_endowment_contribution":0.10397207708399181,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":1,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.0658,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-02-07","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1695,"name":"Sergei Rybakov","orcid":"0000-0002-4944-6586","position":1,"is_corresponding":false},{"id":1696,"name":"Karin Hrovatin","orcid":"0000-0003-3319-9645","position":2,"is_corresponding":false},{"id":1697,"name":"Soroor Hediyeh-zadeh","orcid":"0000-0001-7513-6779","position":3,"is_corresponding":false},{"id":1699,"name":"Alexander V. Misharin","orcid":"0000-0003-2879-3789","position":5,"is_corresponding":false},{"id":42,"name":"Fabian Joachim Theis","orcid":"0000-0002-2419-1943","position":6,"is_corresponding":false},{"id":1700,"name":"Carlos Talavera‐López","orcid":"0000-0001-8590-2393","position":7,"is_corresponding":false},{"id":1694,"name":"Mohammad Lotfollahi","orcid":"0000-0001-6858-7985","position":0,"is_corresponding":true}],"reference_count":1,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-03-01T18:20:47.508186Z","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":[]}