{"id":"W4255375458","doi":"10.21203/rs.3.rs-95704/v3","title":"SnpRecode: A versatile and fast genotype recoding and correlation function","year":2021,"lang":"en","type":"preprint","venue":"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":"","funders":"Agriculture and Agri-Food Canada","keywords":"Python (programming language); Imputation (statistics); Computer science; Software; Genotype; Data mining; Programming language; Biology; Missing data; Machine learning; Genetics; Gene","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":[0.005308888,0.00210143,0.002062217,0.002405328,0.001056124,0.001973449,0.00414335,0.001276123,0.03068127],"category_scores_gemma":[0.01566303,0.001886247,0.002267301,0.002650002,0.0007696197,0.001821521,0.002795646,0.00296032,0.02859707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006808735,"about_ca_system_score_gemma":0.002117985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002819482,"about_ca_topic_score_gemma":0.002625832,"domain_scores_codex":[0.9965206,0.0007330198,0.0002750555,0.00102794,0.001187678,0.0002556691],"domain_scores_gemma":[0.994945,0.002271028,0.0004790151,0.001134134,0.0009354458,0.0002353199],"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":[0.00156853,0.0002601915,0.00936477,0.001233306,0.0008520574,0.0009118838,0.0006354733,0.01669138,0.03000881,0.0123989,0.4962196,0.429855],"study_design_scores_gemma":[0.0008937791,0.000302621,0.0174332,0.0003648546,0.0003091243,0.002628529,0.000175286,0.3294598,0.1490009,0.04864057,0.4500958,0.0006955715],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003885579,0.0001753643,0.6789676,0.0002063665,0.000205003,0.0001508641,0.01617322,0.298382,0.001853963],"genre_scores_gemma":[0.04085781,0.0002251892,0.7926154,0.0006513731,0.000123119,0.001416787,0.04227779,0.113078,0.008754645],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03068127,"threshold_uncertainty_score":0.1026391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04434593880627481,"score_gpt":0.3165122765364702,"score_spread":0.2721663377301954,"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."}}