{"id":"W4365446189","doi":"10.1101/2023.04.12.536512","title":"Automated Protein Affinity Optimization using a 1D-CNN Deep Learning Model","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Zymeworks (Canada)","funders":"","keywords":"Computer science; Convolutional neural network; Protein design; Artificial intelligence; Deep learning; Sampling (signal processing); Protein structure prediction; Machine learning; Protein engineering; Protein structure; Filter (signal processing)","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"],"consensus_categories":[],"category_scores_codex":[0.0005625436,0.0005590555,0.000445051,0.0001948857,0.0002788821,0.0002614697,0.0005079104,0.0008140043,0.000009095749],"category_scores_gemma":[0.0003359263,0.0006169476,0.0001885763,0.0003336516,0.00005408538,0.00002182081,0.0009885639,0.0006210811,0.00002398526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001124511,"about_ca_system_score_gemma":0.0004891615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003977777,"about_ca_topic_score_gemma":0.000001742028,"domain_scores_codex":[0.9976764,0.0001139585,0.0006311558,0.0007571914,0.0002673892,0.0005539584],"domain_scores_gemma":[0.9978598,0.000008603207,0.0005585887,0.000988522,0.0004269485,0.000157583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002478488,0.00004333674,0.0002538531,0.0002388144,0.0001133747,0.000002727643,0.000008533802,0.559092,0.4401514,0.0000212761,0.0000490916,7.886432e-7],"study_design_scores_gemma":[0.0003819733,0.00005494181,0.000817436,0.000183219,0.00007205988,2.417901e-8,0.000008016465,0.8654154,0.1322965,0.000001066515,0.0001301961,0.0006391807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8682103,0.00046772,0.1292621,0.00004352258,0.0002876859,0.0009097584,0.00006090615,0.0007470585,0.00001099616],"genre_scores_gemma":[0.9134211,0.0002124031,0.08566559,0.00004401314,0.0002285074,0.0001830327,0.00001111945,0.0002044046,0.0000298414],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3078549,"threshold_uncertainty_score":0.9996282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02418768909804294,"score_gpt":0.2331073179399531,"score_spread":0.2089196288419101,"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."}}