{"id":"W2896564278","doi":"10.1101/438291","title":"Selene: a PyTorch-based deep learning library for biological sequence-level data","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institutes of Health; Canadian Institute for Advanced Research; Princeton University","keywords":"Deep learning; Architecture; Deep neural networks; Artificial neural network; Data modeling","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":[0.001408832,0.002001082,0.001359003,0.001827249,0.0007102029,0.001696531,0.004138152,0.001811627,0.03291648],"category_scores_gemma":[0.006868782,0.001489302,0.001895258,0.00214876,0.0009383145,0.002387693,0.003070403,0.004267446,0.02080087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001163548,"about_ca_system_score_gemma":0.002714816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004614467,"about_ca_topic_score_gemma":0.009432448,"domain_scores_codex":[0.9991897,0.0001254255,0.0000497428,0.0001983051,0.0003295846,0.0001072782],"domain_scores_gemma":[0.9988676,0.0005119156,0.00006278486,0.0002556484,0.000209992,0.00009202261],"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":[0.00116675,0.0003551821,0.005033861,0.003187838,0.001022293,0.000724213,0.000340281,0.1326061,0.0211131,0.02898788,0.5507261,0.2547365],"study_design_scores_gemma":[0.0004347322,0.0001452735,0.001616996,0.0001920209,0.0001078628,0.0003126355,0.00005360647,0.7434847,0.04078016,0.05698583,0.1557152,0.0001709034],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.01089104,0.001060575,0.5535052,0.0005800355,0.0003388123,0.0002262952,0.03991145,0.387721,0.005765607],"genre_scores_gemma":[0.1258185,0.001941719,0.642457,0.001410191,0.0001572198,0.002066925,0.1439676,0.06144704,0.02073376],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.03291648,"threshold_uncertainty_score":0.1101166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05007217331074595,"score_gpt":0.2527194666706334,"score_spread":0.2026472933598875,"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."}}