{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003546388,0.00006351851,0.00005719902,0.0001056021,0.0001350083,0.00005356482,0.0002258093,0.00002595044,0.000007679747],"category_scores_gemma":[0.00005450732,0.00005971383,0.00005119242,0.00007083656,0.00007860004,0.00002996455,0.0001621567,0.0000965541,2.160571e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005245872,"about_ca_system_score_gemma":0.00007298302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002121418,"about_ca_topic_score_gemma":0.000003011069,"domain_scores_codex":[0.9990271,0.00007223218,0.0002047147,0.0001460286,0.0004701588,0.00007974711],"domain_scores_gemma":[0.9995128,0.000004272114,0.0002607407,0.00005234248,0.0001371204,0.0000327058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006076785,0.00002040578,0.006720428,0.000001599496,0.00004003016,0.00002143459,0.00003544497,0.006052501,0.9849471,0.00007729925,0.00000940409,0.002013522],"study_design_scores_gemma":[0.003579985,0.003579654,0.01332985,0.0001922029,0.0001162932,0.007242921,0.001821406,0.1102394,0.8455352,0.005087967,0.008588235,0.0006868553],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9735889,0.0002431519,0.02533979,0.0001524153,0.0005237078,0.00008029606,0.00002110025,0.000002289629,0.0000483801],"genre_scores_gemma":[0.9955903,0.0000207681,0.004119451,0.0001295677,0.00009904518,0.000004170887,0.00001460523,0.000004358065,0.00001773173],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.139412,"threshold_uncertainty_score":0.2435059,"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."}}