{"id":"W1987231763","doi":"10.2174/092986608786071085","title":"Function Prediction of Hypothetical Proteins Without Sequence Similarity to Proteins of Known Function (SUPPLEMENTARY MATERIALS)","year":2008,"lang":"en","type":"article","venue":"Protein and Peptide Letters","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Similarity (geometry); Sequence (biology); Computational biology; Function (biology); Computer science; Protein sequencing; Protein function; Genome; Domain (mathematical analysis); Bioinformatics; Biology; Genetics; Artificial intelligence; Peptide sequence; Mathematics; Gene; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0002736998,0.0001741267,0.0001996856,0.00007593544,0.00009622669,0.0000103585,0.0001036182,0.0001145033,0.00008056482],"category_scores_gemma":[0.00008859464,0.0001631354,0.00005079108,0.00008772031,0.0001729296,0.00001323625,0.00009644727,0.0001244065,0.000003372974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001741703,"about_ca_system_score_gemma":0.00003573686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001766422,"about_ca_topic_score_gemma":0.00001835936,"domain_scores_codex":[0.998799,0.0000979434,0.000413794,0.0002580139,0.0002323106,0.00019892],"domain_scores_gemma":[0.9993699,0.000006222122,0.0001926584,0.0002809892,0.00007321274,0.00007706716],"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":[0.0005825408,0.00005053365,0.01170033,0.0002273531,0.00004236236,8.733297e-7,0.000142531,0.00007548487,0.9860257,0.00006098329,0.0005027825,0.000588529],"study_design_scores_gemma":[0.0008952142,0.002087775,0.02420403,0.0001136477,0.00004308087,0.00004169763,0.00003917224,0.0001736999,0.9637185,0.00007342419,0.008384292,0.0002254688],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9785103,0.00001874885,0.01894375,0.0006937414,0.00007561749,0.001422062,0.000186092,0.00001779781,0.0001319339],"genre_scores_gemma":[0.9842626,0.00001145623,0.01445964,0.0005681421,0.0001818333,0.0001765497,0.0002231615,0.0000198569,0.00009669222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0223072,"threshold_uncertainty_score":0.665247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01682132926567926,"score_gpt":0.2345678212300503,"score_spread":0.2177464919643711,"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."}}