{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003797548,0.0003229371,0.0003591859,0.00050677,0.0009323041,0.0006620651,0.000347378,0.0007438388,0.0002497642],"category_scores_gemma":[0.00105554,0.0003334635,0.0001171226,0.0003529767,0.0005370351,0.00001655737,0.002729676,0.001681831,0.00003399744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008814722,"about_ca_system_score_gemma":0.0005602561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007446837,"about_ca_topic_score_gemma":0.0002672972,"domain_scores_codex":[0.9948922,0.001236549,0.0003293259,0.001315206,0.001247536,0.0009791965],"domain_scores_gemma":[0.997191,0.0002806705,0.00008825089,0.0006746118,0.001343185,0.0004223468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004422448,0.001456974,0.142301,0.01151772,0.001826017,0.0004110557,0.01108271,0.002937075,0.3889898,0.001893419,0.1433918,0.2897699],"study_design_scores_gemma":[0.009805019,0.01558929,0.3836693,0.00881516,0.0004329979,0.0003387636,0.07387174,0.0410175,0.03329245,0.0113005,0.4157181,0.006149169],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9829756,0.009137565,0.001578704,0.000695929,0.0003892799,0.001035715,0.0002085348,0.00003623861,0.003942415],"genre_scores_gemma":[0.9851508,0.01015009,0.0004884207,0.00003636047,0.000513961,0.00007893489,0.001102385,0.00004110446,0.002437908],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3556973,"threshold_uncertainty_score":0.9999117,"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."}}