{"id":"W4307370003","doi":"10.3390/ijms232112814","title":"PITHIA: Protein Interaction Site Prediction Using Multiple Sequence Alignments and Attention","year":2022,"lang":"en","type":"article","venue":"International Journal of Molecular Sciences","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Sequence (biology); Machine learning; Artificial intelligence; Protein–protein interaction; Exploit; Protein sequencing; Data mining; Computational biology; Peptide sequence; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008713781,0.001997563,0.001293312,0.001395037,0.0007059261,0.00100277,0.003075437,0.002124924,0.003237514],"category_scores_gemma":[0.002133531,0.0006880764,0.001217718,0.00132772,0.000511015,0.002329104,0.001772062,0.002857004,0.002359168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001298312,"about_ca_system_score_gemma":0.001550837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01467778,"about_ca_topic_score_gemma":0.02030542,"domain_scores_codex":[0.9994687,0.00009925109,0.00002038384,0.000238741,0.0001046073,0.00006829578],"domain_scores_gemma":[0.999334,0.0002821937,0.0000723288,0.000128126,0.0001005038,0.00008281047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001722924,0.001073106,0.01515305,0.001346187,0.0008349016,0.0006979271,0.000178231,0.358454,0.02710098,0.01337947,0.1754443,0.404615],"study_design_scores_gemma":[0.0000506856,0.00008545829,0.001224053,0.00001727229,0.00003136944,0.00008729019,0.0000110654,0.9853833,0.003373547,0.005521532,0.004198439,0.00001597735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2760457,0.01120799,0.5687147,0.00286898,0.0006956868,0.0007672922,0.04042396,0.0830288,0.01624692],"genre_scores_gemma":[0.5960524,0.00230668,0.3069711,0.001279404,0.0002601933,0.0008250588,0.07776752,0.001135242,0.01340238],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01467778,"threshold_uncertainty_score":0.0291847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01526815167816862,"score_gpt":0.2877508803874956,"score_spread":0.2724827287093269,"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."}}