{"id":"W4390793818","doi":"10.1093/bioinformatics/btad738","title":"Seq-InSite: sequence supersedes structure for protein interaction site prediction","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Sequence (biology); Source code; Matching (statistics); Code (set theory); Quality (philosophy); Data mining; Artificial intelligence; Machine learning; Programming language; 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":[0.00008261247,0.0001517036,0.00009549886,0.00006035239,0.00008239617,0.0001155931,0.00009633497,0.0001940334,0.000011197],"category_scores_gemma":[0.00005736763,0.0001288203,0.00008287285,0.00009081454,0.00004013475,0.00003450864,0.00004631926,0.0001057018,0.00001041027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003645978,"about_ca_system_score_gemma":0.00008586821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005564416,"about_ca_topic_score_gemma":0.00001566045,"domain_scores_codex":[0.9992784,0.000009892823,0.0002537411,0.000166339,0.0001098743,0.0001817632],"domain_scores_gemma":[0.9995998,0.000006678201,0.00005279681,0.0002148426,0.00007527174,0.00005065544],"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":[0.00009517755,0.000008417675,0.0001604924,0.0007944998,0.00008201548,0.000001590524,0.0005561915,0.0003515891,0.9740693,0.00126591,0.003020097,0.0195947],"study_design_scores_gemma":[0.0007464988,0.000940124,0.0001953382,0.0003259081,0.000100823,0.0002487712,0.0006347291,0.3074878,0.4575074,0.002467071,0.2286703,0.0006752741],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.872546,0.0003281987,0.1229594,0.0001433088,0.0008856001,0.001033259,0.001317715,0.0001312588,0.000655257],"genre_scores_gemma":[0.9737004,0.00003424981,0.02367113,0.0001280693,0.0003175374,0.0000493555,0.001630742,0.00002245047,0.000446029],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5165619,"threshold_uncertainty_score":0.5253139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01073657310424628,"score_gpt":0.2563578867487379,"score_spread":0.2456213136444917,"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."}}