{"id":"W4281940572","doi":"10.3389/fbinf.2022.896295","title":"ContactPFP: Protein Function Prediction Using Predicted Contact Information","year":2022,"lang":"en","type":"article","venue":"Frontiers in Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; National Science Foundation; National Institutes of Health; Division of Civil, Mechanical and Manufacturing Innovation; National Institute of General Medical Sciences; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Protein function prediction; Computer science; Protein structure prediction; Computational biology; Protein function; Structural genomics; Function (biology); Data mining; Sequence (biology); Protein structure database; Protein structure; Bioinformatics; Artificial intelligence; Biology; Gene; Genetics; Sequence database","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002593848,0.0001594126,0.0001565345,0.0002076431,0.0002121972,0.00004107664,0.0001764666,0.0001351231,0.00001850342],"category_scores_gemma":[0.00005143676,0.0001707578,0.00006098043,0.0002478117,0.00003081961,0.00007661547,0.0001525522,0.0002337253,0.00000147334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001677652,"about_ca_system_score_gemma":0.0001375671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002009177,"about_ca_topic_score_gemma":0.000003047553,"domain_scores_codex":[0.9988048,0.00005561342,0.0004939347,0.0001189425,0.0002752809,0.0002513927],"domain_scores_gemma":[0.9993703,0.000002385137,0.0002451644,0.0002630509,0.00006288232,0.00005622553],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01321518,0.0006252173,0.2756955,0.001802516,0.001568009,0.00002446264,0.009065988,0.1530448,0.2212784,0.006809811,0.1296238,0.1872464],"study_design_scores_gemma":[0.005298809,0.002271005,0.012164,0.00006157652,0.00009113819,0.00009590173,0.005462237,0.8072335,0.007162994,0.001842171,0.157449,0.000867689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4053804,0.0001600476,0.5901254,0.00002689826,0.001407929,0.001076403,0.0004310095,0.00005276394,0.001339127],"genre_scores_gemma":[0.9597605,0.00001911937,0.03697227,0.0004252186,0.000110373,0.0001498007,0.002454998,0.0000182221,0.00008948809],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6541886,"threshold_uncertainty_score":0.6963303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004371013926252199,"score_gpt":0.1913359052639602,"score_spread":0.186964891337708,"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."}}