{"id":"W4313544751","doi":"10.1089/cmb.2022.0395","title":"A Novel Information-Theory-Based Genetic Distance That Approximates Phenotypic Differences","year":2023,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network","funders":"Centers for Disease Control and Prevention; National Institutes of Health","keywords":"Biology; Genetics; Phenotype; Entropy (arrow of time); Computational biology; Major histocompatibility complex; In silico; Distance matrix; Pairwise comparison; Mathematics; Combinatorics; Gene; Statistics","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":[0.00035544,0.0001222901,0.0001742309,0.0001610525,0.00007586856,0.00003320396,0.0002570565,0.0001013918,0.00002308981],"category_scores_gemma":[0.0002751818,0.00009635545,0.00009329498,0.00015075,0.0001188549,0.00001409869,0.00005225367,0.0001279222,0.0000299297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001218864,"about_ca_system_score_gemma":0.0001429353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001071169,"about_ca_topic_score_gemma":8.39004e-7,"domain_scores_codex":[0.999081,0.00007206968,0.0004346785,0.00007926249,0.0001644101,0.0001686433],"domain_scores_gemma":[0.9989465,0.0001758143,0.0004898882,0.0001003441,0.0002298159,0.00005764646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.001124852,0.0002698191,0.2011738,0.0003398999,0.000618955,0.00000752474,0.0008951035,0.6840904,0.02445005,0.04364287,0.005871525,0.03751517],"study_design_scores_gemma":[0.005735485,0.002445128,0.5240243,0.0001432698,0.0001090979,0.0004218616,0.0004938451,0.3064905,0.003928926,0.07663309,0.07854313,0.001031406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3700641,0.00009623402,0.628957,0.000330267,0.0002219573,0.00006768962,0.00004343111,0.00001423609,0.0002050934],"genre_scores_gemma":[0.9561005,0.0000203812,0.04289198,0.0004961757,0.000127995,0.000004151698,0.0003118892,0.000007489106,0.00003943648],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5860651,"threshold_uncertainty_score":0.3929261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01166445177286535,"score_gpt":0.2586015842894526,"score_spread":0.2469371325165873,"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."}}