{"id":"W2147702777","doi":"10.1093/bioinformatics/btr229","title":"Sequence-based prediction of protein crystallization, purification and production propensity","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":77,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Crystallization; Protein crystallization; Computer science; Process (computing); Production (economics); Set (abstract data type); In silico; Selection (genetic algorithm); Sequence (biology); Quality (philosophy); Diffraction; Algorithm; Data mining; Biological system; Artificial intelligence; Chemistry; Biology; Physics; Genetics","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":[0.0002543844,0.00007129598,0.00008522147,0.00006106473,0.00007952403,0.00001786348,0.00005302166,0.00005765753,0.00005545479],"category_scores_gemma":[0.00008456478,0.00005784281,0.00001271805,0.0001256299,0.00009378711,0.0004802285,0.00001262475,0.00003549779,0.000009589921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002054355,"about_ca_system_score_gemma":0.00004940602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002137958,"about_ca_topic_score_gemma":0.000005089767,"domain_scores_codex":[0.9993512,0.00002205637,0.000293827,0.00009531559,0.0001545632,0.00008302616],"domain_scores_gemma":[0.9993705,0.000003359721,0.000226393,0.0001757168,0.0001948589,0.00002918396],"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":[0.00006233856,0.00003907156,0.001594396,0.0003014833,0.00000379167,1.322585e-7,0.001732395,0.00005488892,0.9902826,0.001595499,0.0001623337,0.004171081],"study_design_scores_gemma":[0.0001662622,0.0001876969,0.01015085,0.00005352145,0.00001659873,0.000005761709,0.0001335489,0.0035916,0.9846752,0.0006325722,0.0003071574,0.00007921025],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9525743,0.00001534176,0.04490661,0.00003964431,0.0002437143,0.0006038366,0.00002445255,0.0000910517,0.001501107],"genre_scores_gemma":[0.9591786,0.000005544365,0.04064202,0.00001427433,0.00003833043,0.00001974739,0.00003395139,0.000004932559,0.00006259422],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008556457,"threshold_uncertainty_score":0.2358761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0539457064322674,"score_gpt":0.2132408168633426,"score_spread":0.1592951104310752,"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."}}