{"id":"W2897692191","doi":"10.1101/441337","title":"Estimation of allele-specific fitness effects across human protein-coding sequences and implications for disease","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institutes of Health; University of Toronto","keywords":"Genomics; Single-nucleotide polymorphism; Biology; Allele; Genome; Genetics; Population genomics; Human genome; Balancing selection; Computational biology; Population; Selection (genetic algorithm); Gene; Genotype; Computer science; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001742124,0.000504409,0.0007223523,0.00165977,0.0003568024,0.000714398,0.0004167358,0.000673118,0.001362287],"category_scores_gemma":[0.00580786,0.000183369,0.000516193,0.0008054855,0.0006531009,0.0004752433,0.0006994025,0.0008967744,0.0001544773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002720742,"about_ca_system_score_gemma":0.0002303279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002135352,"about_ca_topic_score_gemma":0.001513952,"domain_scores_codex":[0.9993735,0.0002898602,0.00002389842,0.0002093669,0.00006675558,0.00003660902],"domain_scores_gemma":[0.996524,0.002881258,0.000246515,0.0001835177,0.0000790099,0.00008565016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000862546,0.0001404527,0.4793425,0.0001670281,0.0008318723,0.000955563,0.0003922775,0.3655757,0.07889996,0.0102193,0.001112369,0.06150049],"study_design_scores_gemma":[0.00007669428,0.0001682814,0.1933823,0.00003482437,0.0001974386,0.0006131275,0.0002267802,0.7508548,0.0142396,0.03868924,0.001449738,0.00006731618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9007032,0.0002993911,0.09707421,0.0002271933,0.0000105052,0.00001191555,0.0009099316,0.0001976186,0.0005660187],"genre_scores_gemma":[0.9885681,0.00008272186,0.0105163,0.00005098568,0.000009975188,0.00001227386,0.0005350119,0.00002961597,0.0001949828],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002135352,"threshold_uncertainty_score":0.009213328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01544670468147681,"score_gpt":0.2661974099307631,"score_spread":0.2507507052492863,"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."}}