{"id":"W4392344407","doi":"10.1101/2024.02.25.581975","title":"Cluster decomposition-based anomaly detection for rare cell identification in single-cell expression data","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; Central South University; National Natural Science Foundation of China","keywords":"Computational biology; Cell type; Cluster analysis; Identification (biology); Cell; Biology; Benchmark (surveying); Biclustering; Computer science; Artificial intelligence; Genetics; Fuzzy clustering","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":[0.0004890487,0.0004534613,0.0003209665,0.0002411979,0.000119095,0.0002701071,0.0007183134,0.0007677643,0.000005967487],"category_scores_gemma":[0.00007341887,0.0005138974,0.0001606824,0.0002059498,0.00005618608,0.00001711592,0.0004864538,0.0004257472,0.00001645474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001388326,"about_ca_system_score_gemma":0.0003392041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003808172,"about_ca_topic_score_gemma":0.00003970534,"domain_scores_codex":[0.9972136,0.0001248592,0.0006078604,0.001469707,0.0002015563,0.000382408],"domain_scores_gemma":[0.9976162,0.00004141049,0.0002882315,0.001676269,0.0002530653,0.0001247843],"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":[0.0001919542,0.000339992,0.0007346875,0.001015643,0.00002202591,0.00000513937,0.000004409779,0.0005601114,0.9967372,0.000001366299,0.0003796837,0.000007832228],"study_design_scores_gemma":[0.0009621801,0.0001180333,0.001435305,0.0002956302,0.00009864256,1.296495e-8,0.00000232048,0.009196687,0.9847909,0.000002639743,0.00252838,0.0005692234],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9293821,0.001669898,0.06508026,0.00008463884,0.001627925,0.001095614,0.0009470995,0.00010401,0.000008468311],"genre_scores_gemma":[0.9928821,0.00006297303,0.005825047,0.0001432862,0.0005674898,0.0002689206,0.00008056723,0.0001545789,0.00001508159],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06349996,"threshold_uncertainty_score":0.9997312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01934104379950553,"score_gpt":0.2385341343176536,"score_spread":0.219193090518148,"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."}}