{"id":"W3123914750","doi":"10.21203/rs.3.rs-95704/v2","title":"SnpRecode: A Versatile and Fast Genotype Recoding and Correlation Function","year":2021,"lang":"en","type":"preprint","venue":"Research Square (Research Square)","topic":"Genetic Mapping and Diversity in Plants and Animals","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Agriculture and Agri-Food Canada","keywords":"Python (programming language); Imputation (statistics); Computer science; Software; Genotype; Residual; Data mining; Programming language; Biology; Missing data; Algorithm; Machine learning; Genetics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005360066,0.002056272,0.002030212,0.002392234,0.001061297,0.001947145,0.004142151,0.001243095,0.0304805],"category_scores_gemma":[0.01544674,0.001874482,0.002230546,0.002620072,0.0007696325,0.001814105,0.002768439,0.002904631,0.02731599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006867618,"about_ca_system_score_gemma":0.002093719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002844212,"about_ca_topic_score_gemma":0.002703781,"domain_scores_codex":[0.9965867,0.0007142576,0.0002657817,0.001017428,0.001169044,0.0002468524],"domain_scores_gemma":[0.9949754,0.00225724,0.0004929101,0.001106173,0.0009312081,0.0002369987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001591013,0.0002641485,0.00994167,0.001202243,0.0008443784,0.0008979245,0.0006403587,0.0167873,0.03037265,0.0123851,0.500205,0.4248682],"study_design_scores_gemma":[0.0009086995,0.0003010563,0.01802427,0.0003560348,0.0003032665,0.002499376,0.0001784271,0.3383923,0.1491579,0.04765064,0.4415426,0.000685519],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004062227,0.0001667988,0.6772116,0.0002079975,0.0002020916,0.0001514144,0.01631707,0.2997984,0.001882462],"genre_scores_gemma":[0.041622,0.0002102951,0.7941394,0.0006389136,0.0001204138,0.001395718,0.04031047,0.1129117,0.008651036],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0304805,"threshold_uncertainty_score":0.1019675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08057096194633058,"score_gpt":0.3603874593000444,"score_spread":0.2798164973537138,"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."}}