{"id":"W4281557145","doi":"10.1038/s42003-022-03445-2","title":"PepNN: a deep attention model for the identification of peptide binding sites","year":2022,"lang":"en","type":"article","venue":"Communications Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":92,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"CIHR Skin Research Training Centre; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Compute Canada","keywords":"Peptide; Flexibility (engineering); Computer science; Identification (biology); Computational biology; Artificial intelligence; Chemistry; Biology; Biochemistry; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003535319,0.00005983959,0.0000713784,0.00003848131,0.0004663155,0.000006300909,0.0007466183,0.00005585355,0.000004492082],"category_scores_gemma":[0.0001016084,0.00005130608,0.00007889001,0.0000877917,0.0001498078,0.000002256936,0.0005267342,0.00008757208,8.496426e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001474295,"about_ca_system_score_gemma":0.00003435064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006225343,"about_ca_topic_score_gemma":0.00005512713,"domain_scores_codex":[0.9993897,0.0001054604,0.0002393365,0.0001353788,0.0000345925,0.00009552708],"domain_scores_gemma":[0.9986039,0.00006411866,0.0001928622,0.001044882,0.00008268525,0.00001155041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002849979,0.00003558941,0.001731295,0.000006125802,0.00004720717,8.719688e-9,0.00008845403,0.00343846,0.9802527,0.01174548,0.0002970907,0.002329021],"study_design_scores_gemma":[0.0005003225,0.0002144525,0.001517824,0.000002384575,0.00008621805,0.00001271418,0.0006165683,0.9472581,0.01495242,0.01078935,0.02384974,0.0001999256],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4180595,0.004945224,0.5728318,0.002452956,0.0001424309,0.000827231,0.000387564,0.00001924618,0.0003340116],"genre_scores_gemma":[0.9924222,0.0003075543,0.004711322,0.00009783121,0.00002483484,0.0004082659,0.001649712,0.000008767681,0.0003694756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9653004,"threshold_uncertainty_score":0.3586569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0307933646825013,"score_gpt":0.307629222510941,"score_spread":0.2768358578284397,"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."}}