{"id":"W4393093446","doi":"10.1158/1538-7445.am2024-6548","title":"Abstract 6548: Leveraging compact feature sets for TCGA-based molecular subtype classification on new samples","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Analytical Chemistry and Chromatography","field":"Chemistry","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Spinal Cord Injury BC","funders":"","keywords":"Feature (linguistics); Computational biology; Pattern recognition (psychology); Computer science; Biology; Artificial intelligence","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000248283,0.0001686559,0.0001624675,0.0001089072,0.00016024,0.0002066527,0.0002936217,0.0001820373,0.00149548],"category_scores_gemma":[0.0001103468,0.0001530209,0.0001840766,0.0004045807,0.0001150412,0.00005669971,0.00001690574,0.0007099256,0.00004389462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002548944,"about_ca_system_score_gemma":0.000567658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001297389,"about_ca_topic_score_gemma":0.000006590625,"domain_scores_codex":[0.9983512,0.00001647072,0.0001485258,0.0004877005,0.0005189716,0.0004771016],"domain_scores_gemma":[0.9987776,0.0004468649,0.00002672328,0.0003737028,0.0001313382,0.0002438291],"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":[0.0001980206,0.00005941851,0.0006131243,0.001548659,0.0001249277,0.00004039103,0.00005732271,0.0002513928,0.8992395,0.001641922,0.09106892,0.0051564],"study_design_scores_gemma":[0.0004185463,0.00002627655,0.001077586,0.000729178,0.00003090453,0.000001502388,0.0001201723,0.003344673,0.8982336,0.001946482,0.09382872,0.0002423553],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9526464,0.004044507,0.001292746,0.01339524,0.0001306053,0.0003114181,0.0003635813,0.0003322977,0.02748316],"genre_scores_gemma":[0.9972478,0.00005035959,0.0001190935,0.0001067131,0.0003070385,0.00004994041,0.0002104061,0.00004343627,0.001865262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04460131,"threshold_uncertainty_score":0.9994173,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1539543933072297,"score_gpt":0.4257806480665253,"score_spread":0.2718262547592956,"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."}}