{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003436887,0.0003644452,0.0003526329,0.0006588318,0.0007452726,0.0004497895,0.0004613949,0.0008216984,0.0001809386],"category_scores_gemma":[0.001407622,0.0003710208,0.0001138488,0.0006448028,0.000599788,0.00002376894,0.00230847,0.002321084,0.00007736564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000201288,"about_ca_system_score_gemma":0.0007864245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002394952,"about_ca_topic_score_gemma":0.0001165648,"domain_scores_codex":[0.9936861,0.001699337,0.0004443524,0.001685095,0.001567232,0.0009178147],"domain_scores_gemma":[0.9968152,0.000235704,0.0001395497,0.0009241813,0.001300053,0.0005852859],"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":[0.003149933,0.0003217905,0.01286698,0.003181109,0.0003426039,0.00002716535,0.002876089,0.0005395304,0.64923,0.001819481,0.1207656,0.2048797],"study_design_scores_gemma":[0.006210638,0.008931737,0.1461864,0.00315856,0.0001644738,0.00005321189,0.01476245,0.04929808,0.07284018,0.02711679,0.668014,0.003263468],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9261965,0.02204217,0.02172482,0.01127118,0.001444547,0.006307814,0.0003935382,0.0002096516,0.01040975],"genre_scores_gemma":[0.9881006,0.007522174,0.0003855774,0.00006661569,0.0008763882,0.0004918185,0.0009312666,0.00008776694,0.001537811],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5763898,"threshold_uncertainty_score":0.9999806,"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."}}