{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006625907,0.0005433027,0.0006541187,0.0001060007,0.0003494122,0.00016617,0.0006346975,0.0007569985,0.00001396013],"category_scores_gemma":[0.0001329361,0.0006307211,0.0003127445,0.0002276853,0.0002671651,0.00001493155,0.0005938223,0.0004305776,0.0000104799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001270287,"about_ca_system_score_gemma":0.0003915543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003316806,"about_ca_topic_score_gemma":0.00006669168,"domain_scores_codex":[0.9971194,0.000157313,0.0007713765,0.0008867991,0.0003943836,0.000670697],"domain_scores_gemma":[0.9976726,0.00005456437,0.0005803261,0.000903904,0.000613549,0.0001750745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005144469,0.0002383253,0.01470829,0.0006158463,0.0001876077,0.000005902694,0.00002232207,0.001899189,0.9815884,0.00006951437,0.0006127717,4.090558e-7],"study_design_scores_gemma":[0.0007357502,0.0001147873,0.02051448,0.0004138233,0.0000977289,1.242239e-8,0.000008911794,0.002089042,0.9750475,0.00003149806,0.0001975975,0.0007489187],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9937122,0.0007391746,0.002626698,0.00004759373,0.0004288786,0.0004027788,0.001888942,0.0001419681,0.00001177541],"genre_scores_gemma":[0.9968636,0.0002071376,0.002008958,0.000100465,0.0002667276,0.000115502,0.00004126142,0.0001760649,0.0002202847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006540929,"threshold_uncertainty_score":0.9996144,"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."}}