{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004794148,0.0005303216,0.0006329182,0.0001094042,0.0002188142,0.0002514219,0.003231894,0.0005800491,0.00003835169],"category_scores_gemma":[0.0005347735,0.0005890494,0.0001238162,0.00007761171,0.0002965272,0.00002474328,0.004181074,0.0005003789,0.0000459177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004775744,"about_ca_system_score_gemma":0.0004915519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003274149,"about_ca_topic_score_gemma":0.0000276453,"domain_scores_codex":[0.9971814,0.0001251459,0.0007739855,0.001071822,0.0003783591,0.0004692875],"domain_scores_gemma":[0.9927786,0.00002522573,0.001271895,0.005418029,0.0003265534,0.0001796993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002198273,0.00004429366,0.02577345,0.0004529794,0.0001673206,0.00001793755,0.0000110292,0.0001601109,0.9731145,0.000004297617,0.0002063906,0.00002571384],"study_design_scores_gemma":[0.0008991247,0.0001330793,0.6551317,0.0007295609,0.0003772657,1.348904e-7,0.000005626326,0.01547683,0.2741722,0.000007370705,0.05126522,0.001801901],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9817179,0.002010808,0.008961088,0.00003352076,0.0008792396,0.0004775529,0.005831268,0.00007026278,0.00001834015],"genre_scores_gemma":[0.9432648,0.0004461334,0.05543444,0.00008250558,0.0005477985,0.00002626838,0.0000716238,0.000111441,0.00001495951],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6989423,"threshold_uncertainty_score":0.9996561,"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."}}