{"id":"W4410356881","doi":"10.1145/3672608.3707901","title":"GSHAPA: Gene Set Analysis for Single-Cell RNAseq Using Random Forest and SHAP Values","year":2025,"lang":"en","type":"article","venue":"","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Random forest; Set (abstract data type); Computer science; Gene; Computational biology; Biology; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001594835,0.00017781,0.0002721992,0.0001180093,0.0001426123,0.00006274075,0.0001221886,0.0001573615,0.00001409277],"category_scores_gemma":[0.00004145621,0.0001605755,0.0002319379,0.0002009057,0.00006959258,0.000004071354,0.00005464933,0.00004411878,5.352386e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001358258,"about_ca_system_score_gemma":0.00004730936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001010176,"about_ca_topic_score_gemma":0.000198272,"domain_scores_codex":[0.9990309,0.00003280169,0.0002387801,0.0003942613,0.00006802693,0.0002352691],"domain_scores_gemma":[0.9995185,0.00003314337,0.00005294729,0.0002365454,0.00009350169,0.00006541838],"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":[0.0002903638,0.00008676691,0.01728947,0.00004855302,0.0004224187,0.000001024358,0.00002353539,0.001870087,0.9791743,0.00003442077,0.0003841441,0.0003749048],"study_design_scores_gemma":[0.004519778,0.0002310137,0.0008063687,0.000015301,0.001170675,0.000004477286,0.00009065708,0.04412816,0.9434856,0.0002998153,0.004875781,0.0003723475],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7742628,0.001178171,0.2230012,0.00005231314,0.0001066258,0.000228493,0.00006074338,0.00001495171,0.00109461],"genre_scores_gemma":[0.9903589,0.0001130197,0.007228912,0.0004041654,0.0001076297,0.00001407159,0.0002964424,0.00001765848,0.001459217],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.216096,"threshold_uncertainty_score":0.6548079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02929059279790705,"score_gpt":0.2646958145643071,"score_spread":0.2354052217664,"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."}}