{"id":"W6912602229","doi":"10.5281/zenodo.7657016","title":"Antibody library design with Transformer and Deep Reinforcement Learning -- source code and data","year":2023,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"","field":"","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Source code; Workflow; Transformer; Reinforcement learning; Code (set theory); Open source","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":[0.0008647842,0.001916061,0.0009929782,0.0008707419,0.0004515471,0.001248956,0.002273114,0.001131608,0.06753286],"category_scores_gemma":[0.002943571,0.0009558703,0.001277316,0.001165549,0.0003308062,0.001076013,0.001069681,0.001879301,0.05684036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001245197,"about_ca_system_score_gemma":0.001569553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006445995,"about_ca_topic_score_gemma":0.008949426,"domain_scores_codex":[0.9994821,0.00005274509,0.00003019701,0.0001449848,0.0002199879,0.0000700987],"domain_scores_gemma":[0.9993686,0.0001918938,0.00003573714,0.0001713599,0.0001909917,0.00004141024],"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":[0.0005426969,0.0002533697,0.002444885,0.001688359,0.0001859544,0.0001732247,0.00006755225,0.09140611,0.01146236,0.01177862,0.748553,0.1314438],"study_design_scores_gemma":[0.0006369479,0.0002045697,0.001541343,0.0001729333,0.00008186024,0.0002854499,0.00004271216,0.5207435,0.05953575,0.03339756,0.3832525,0.0001048845],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.01763206,0.001366315,0.370246,0.0008670351,0.0004956179,0.0006346959,0.2573495,0.3034917,0.04791706],"genre_scores_gemma":[0.08086858,0.001037242,0.4702975,0.001001653,0.00006661682,0.002070305,0.3618825,0.04819619,0.03457936],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.06753286,"threshold_uncertainty_score":0.22592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04985724701322176,"score_gpt":0.2664929195745031,"score_spread":0.2166356725612813,"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."}}