{"id":"W2749642841","doi":"10.1101/181222","title":"Identifying genetic determinants of complex phenotypes from whole genome sequence data","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Proteome; Phenotype; Boosting (machine learning); Genome; Chunking (psychology); Random forest; Whole genome sequencing; Workflow","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001970472,0.0007690745,0.0006826733,0.001111885,0.0003255674,0.0004806728,0.0005154551,0.0007550173,0.0008413867],"category_scores_gemma":[0.003351024,0.0003326195,0.0009684524,0.0008289511,0.0002296976,0.0006241596,0.0004110286,0.000836983,0.0004494615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004098967,"about_ca_system_score_gemma":0.0007548918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004347694,"about_ca_topic_score_gemma":0.00482256,"domain_scores_codex":[0.9995725,0.0001315361,0.000027864,0.000165328,0.0000544263,0.00004831191],"domain_scores_gemma":[0.997812,0.001342625,0.0002181682,0.0002231496,0.0003043423,0.00009957186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001734984,0.0007811954,0.1861149,0.0007577298,0.001093339,0.0007127983,0.000245399,0.5220257,0.1511593,0.001227326,0.0049091,0.1292381],"study_design_scores_gemma":[0.00004222412,0.0002415607,0.03592901,0.00002492366,0.00006838451,0.0001400573,0.0000701452,0.9457741,0.01493073,0.001798027,0.000950794,0.00002996463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9046358,0.0006580909,0.08728205,0.0001656129,0.00006112775,0.0001360285,0.004537914,0.002059921,0.0004635098],"genre_scores_gemma":[0.8474029,0.0001712926,0.1427708,0.00008658518,0.00001853507,0.0001025021,0.009013487,0.0001078551,0.0003261511],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004347694,"threshold_uncertainty_score":0.01042098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05324352506404843,"score_gpt":0.2979008119735182,"score_spread":0.2446572869094698,"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."}}