{"id":"W2026648849","doi":"10.1002/prot.22057","title":"Discriminative learning for protein conformation sampling","year":2008,"lang":"en","type":"article","venue":"Proteins Structure Function and Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Institute of General Medical Sciences; University of Chicago","keywords":"Discriminative model; Conditional random field; Folding (DSP implementation); Computer science; Graphical model; Protein structure prediction; Protein folding; Sequence (biology); Artificial intelligence; Bottleneck; Pattern recognition (psychology); Probabilistic logic; Sampling (signal processing); Feature (linguistics); Machine learning; Protein structure; Biology; Engineering","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":[0.0001002935,0.0002102595,0.0001585802,0.00007401893,0.0004767154,0.00003284064,0.0000810819,0.0002019376,0.00001048892],"category_scores_gemma":[0.0001536838,0.000172211,0.00006521257,0.00008542502,0.0001106131,0.00003783065,0.00006468625,0.000163866,0.000001701162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001573362,"about_ca_system_score_gemma":0.00006046574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004287329,"about_ca_topic_score_gemma":0.000008451018,"domain_scores_codex":[0.9991054,0.00002031385,0.0003119396,0.0001775891,0.0001480874,0.0002366621],"domain_scores_gemma":[0.9993863,0.000007193265,0.0002057856,0.0001553291,0.0001649258,0.00008049033],"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":[0.001857335,0.00006497638,0.002919895,0.001523011,0.0003267016,0.000001218955,0.003320294,0.001549153,0.8253953,0.01098819,0.0008398684,0.1512141],"study_design_scores_gemma":[0.01345688,0.0102755,0.02438046,0.0003372213,0.0003300003,0.0009190679,0.00554529,0.1169104,0.5498655,0.02757153,0.2463197,0.004088425],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3543738,0.0001491558,0.643252,0.00006609811,0.0001326698,0.001387091,0.00004740307,0.00004766955,0.0005441217],"genre_scores_gemma":[0.9345641,0.00004993041,0.06389556,0.000189208,0.0001982153,0.0001039025,0.0006242095,0.00001883757,0.0003560014],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5801903,"threshold_uncertainty_score":0.7022561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01385411634994375,"score_gpt":0.2353133464004395,"score_spread":0.2214592300504957,"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."}}