{"doi":"10.1016/j.cell.2023.11.026","title":"Automatic cell-type harmonization and integration across Human Cell Atlas datasets","abstract":"Harmonizing cell types across the single-cell community and assembling them into a common framework is central to building a standardized Human Cell Atlas. Here, we present CellHint, a predictive clustering tree-based tool to resolve cell-type differences in annotation resolution and technical biases across datasets. CellHint accurately quantifies cell-cell transcriptomic similarities and places cell types into a relationship graph that hierarchically defines shared and unique cell subtypes. Application to multiple immune datasets recapitulates expert-curated annotations. CellHint also reveals underexplored relationships between healthy and diseased lung cell states in eight diseases. Furthermore, we present a workflow for fast cross-dataset integration guided by harmonized cell types and cell hierarchy, which uncovers underappreciated cell types in adult human hippocampus. Finally, we apply CellHint to 12 tissues from 38 datasets, providing a deeply curated cross-tissue database with ∼3.7 million cells and various machine learning models for automatic cell annotation across human tissues.","journal":"Cell","year":2023,"id":315011,"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":253,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.8079,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":52910,"name":"Martin Prete","orcid":"0000-0002-5946-821X","position":1,"is_corresponding":false},{"id":36227,"name":"Simone Webb","orcid":"0000-0003-3058-8952","position":2,"is_corresponding":false},{"id":36226,"name":"Laura Jardine","orcid":"0000-0003-4495-8205","position":3,"is_corresponding":false},{"id":305502,"name":"Benjamin J. Stewart","orcid":"0000-0003-4522-0085","position":4,"is_corresponding":false},{"id":1014793,"name":"Regina Hoo","orcid":"0000-0002-0295-9472","position":5,"is_corresponding":false},{"id":246335,"name":"Peng He","orcid":"0000-0002-2457-3554","position":6,"is_corresponding":false},{"id":552633,"name":"Kerstin B. Meyer","orcid":"0000-0001-5906-1498","position":7,"is_corresponding":false},{"id":3586,"name":"Sarah A. Teichmann","orcid":"0000-0002-6294-6366","position":8,"is_corresponding":false},{"id":12135,"name":"Chuan Xu","orcid":"0000-0002-6265-999X","position":0,"is_corresponding":true}],"reference_count":81,"raw_metadata":null,"created_at":"2026-07-19T01:06:02.898877Z","pmid":"38134877","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":[]}