{"id":"W4384821687","doi":"10.1101/2023.07.18.549537","title":"Scalable querying of human cell atlases via a foundational model reveals commonalities across fibrosis-associated macrophages","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Roche (Canada)","funders":"","keywords":"Computer science; Computational biology; Cell; Cell type; Annotation; Scalability; Representation (politics); Data integration; Biology; Artificial intelligence; Information retrieval; Data mining; Database; Genetics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002495461,0.0007063086,0.0009563863,0.002022378,0.0008018027,0.002158776,0.001812208,0.001244242,0.001660742],"category_scores_gemma":[0.008892613,0.0004258399,0.001635002,0.002210061,0.001109004,0.002000883,0.002535795,0.001084259,0.0006176953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001644963,"about_ca_system_score_gemma":0.001691545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0108781,"about_ca_topic_score_gemma":0.01348985,"domain_scores_codex":[0.9979553,0.0005607572,0.0001138686,0.0007807712,0.0004614141,0.0001277731],"domain_scores_gemma":[0.9970033,0.001544041,0.0002280866,0.0006993882,0.0004091001,0.0001161077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007409286,0.0002718566,0.01881496,0.0005994817,0.0002558028,0.0006604577,0.000570762,0.7365484,0.03942941,0.04768816,0.02484391,0.1295759],"study_design_scores_gemma":[0.00001273756,0.00004565142,0.001006158,0.00001062631,0.00001426127,0.00008487452,0.00006451693,0.9732158,0.004060396,0.01736793,0.004101036,0.00001608117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1442254,0.001044458,0.8223654,0.001561056,0.00009476693,0.0001729484,0.01464678,0.0121932,0.003696036],"genre_scores_gemma":[0.5796753,0.0006088077,0.3812992,0.0006848215,0.00008509734,0.0004586257,0.03451505,0.0007072093,0.00196602],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0108781,"threshold_uncertainty_score":0.02162957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02980416434075059,"score_gpt":0.2560575299656971,"score_spread":0.2262533656249465,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}