{"id":"W4307507889","doi":"10.1101/2022.10.24.513593","title":"EUGENe: A Python toolkit for predictive analyses of regulatory sequences","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institutes of Health; Deutsche Forschungsgemeinschaft; Canadian Institute for Advanced Research","keywords":"Computer science; Workflow; Python (programming language); Interoperability; Initialization; Artificial intelligence; Compiler; File format; Machine learning; Software; Deep learning; Programming language; World Wide Web; Database","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":[0.002114596,0.002044633,0.00101101,0.001398474,0.0007595392,0.001811032,0.004657064,0.0009683814,0.02329077],"category_scores_gemma":[0.005489822,0.001523923,0.002423884,0.001007975,0.001082965,0.002837187,0.003641128,0.004508418,0.01149784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001099272,"about_ca_system_score_gemma":0.002905493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006461895,"about_ca_topic_score_gemma":0.008552094,"domain_scores_codex":[0.9991753,0.0001509017,0.00008145826,0.000198517,0.0002899191,0.0001038913],"domain_scores_gemma":[0.9987078,0.0007278968,0.00009968958,0.0002272442,0.0001341378,0.0001032342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001293345,0.0004686498,0.008601066,0.00382422,0.001099155,0.00123771,0.0008548477,0.167611,0.02559263,0.06388732,0.5442376,0.1812926],"study_design_scores_gemma":[0.0003042828,0.00009713991,0.003329191,0.0003215189,0.000109888,0.0002741618,0.00009097582,0.7080221,0.02328697,0.07486264,0.1890506,0.0002505552],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.005048528,0.0002822744,0.4371962,0.000362548,0.0001473183,0.0002692153,0.02684549,0.5255799,0.004268563],"genre_scores_gemma":[0.1050572,0.0009818721,0.6773371,0.001384673,0.0000891743,0.002814551,0.07675592,0.124436,0.01114358],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.02329077,"threshold_uncertainty_score":0.07791543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02523602146619429,"score_gpt":0.2663557777165491,"score_spread":0.2411197562503548,"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."}}