{"id":"W4250742804","doi":"10.21203/rs.3.rs-95704/v1","title":"SnpRecode: A Versatile and Fast Genotype Recoding and Correlation Function","year":2020,"lang":"en","type":"preprint","venue":"Research Square (Research Square)","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"","keywords":"Executable; Python (programming language); Computer science; Software; Imputation (statistics); Source code; Operating system; Download; Programming language; Genotype; Correlation; Data mining; Biology; Mathematics; Missing data; Machine learning","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":[0.006125074,0.002215059,0.002375043,0.002781655,0.001328491,0.002972881,0.004212605,0.001553329,0.06877197],"category_scores_gemma":[0.02220561,0.002469528,0.002421038,0.003368583,0.0008025943,0.002206867,0.003977552,0.00361839,0.07974481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007252293,"about_ca_system_score_gemma":0.002471491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002901826,"about_ca_topic_score_gemma":0.002928538,"domain_scores_codex":[0.9958786,0.0009618903,0.0003452356,0.001060894,0.001415711,0.0003377266],"domain_scores_gemma":[0.9944122,0.002408746,0.0004711081,0.001514493,0.0009345544,0.0002588302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008190898,0.0001328793,0.005376606,0.0009527131,0.0005219016,0.0004914323,0.0003654987,0.006904101,0.009694768,0.0103349,0.7653055,0.1991007],"study_design_scores_gemma":[0.0008333107,0.0001693917,0.01136255,0.000506127,0.0002950625,0.002340853,0.0001525833,0.1301431,0.06200643,0.0773854,0.7141263,0.0006789619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002741775,0.0003083353,0.5687889,0.0003353391,0.0003634561,0.0001746171,0.05253845,0.3710255,0.003723628],"genre_scores_gemma":[0.03345465,0.0003802558,0.5977415,0.001023809,0.0002362034,0.001548755,0.1152789,0.2355566,0.01477925],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06877197,"threshold_uncertainty_score":0.2300652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1179622860265776,"score_gpt":0.4029561817233349,"score_spread":0.2849938956967574,"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."}}