{"id":"W4297996437","doi":"10.3389/fonc.2022.979336","title":"Functional and embedding feature analysis for pan-cancer classification","year":2022,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Chinese Academy of Sciences","keywords":"Feature selection; Computer science; Feature (linguistics); Artificial intelligence; Machine learning; KEGG; Word2vec; Pattern recognition (psychology); Computational biology; Embedding; Biology; Genetics; Gene ontology; Gene","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":[0.0002743533,0.00007299949,0.0001498625,0.0001497755,0.0001330834,0.000007815498,0.00009020951,0.0001057289,0.00003953298],"category_scores_gemma":[0.00006963433,0.00007800988,0.0000591055,0.0001987145,0.00004301027,0.000002806867,0.00009116924,0.0001579181,2.539148e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001045932,"about_ca_system_score_gemma":0.00007215036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006206525,"about_ca_topic_score_gemma":0.00002928738,"domain_scores_codex":[0.9993853,0.00007542442,0.0001380776,0.0001918434,0.00007058595,0.0001387994],"domain_scores_gemma":[0.9996988,0.00002114735,0.0001078475,0.000120106,0.00002769406,0.00002447467],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005607622,0.0000988503,0.6209083,0.00003656416,0.0006268927,0.000001282765,0.0003790196,0.04023971,0.008366758,0.0003558172,0.2751974,0.0532287],"study_design_scores_gemma":[0.0009118756,0.0003542458,0.1157056,0.000001270176,0.000145792,0.000007792875,0.001065963,0.155608,0.0001773638,0.0001706442,0.7256908,0.0001606419],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4752448,0.003077601,0.5106446,0.00529975,0.00249026,0.0006804221,0.0001678581,0.00002758633,0.002367102],"genre_scores_gemma":[0.930936,0.000226722,0.06315435,0.001017058,0.0002250628,0.0005229927,0.0009456194,0.00001663507,0.002955576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5052027,"threshold_uncertainty_score":0.3181151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01525595278101351,"score_gpt":0.3094189619132441,"score_spread":0.2941630091322306,"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."}}