{"id":"W2328398973","doi":"10.2174/092986612798472910","title":"CRYSpred: Accurate Sequence-Based Protein Crystallization Propensity Prediction Using Sequence-Derived Structural Characteristics","year":2012,"lang":"en","type":"article","venue":"Protein and Peptide Letters","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Structural genomics; Computer science; Protein structure prediction; Benchmark (surveying); Protein crystallization; Context (archaeology); Test set; Genomics; Protein sequencing; Classifier (UML); Selection (genetic algorithm); In silico; Sequence (biology); Rule of thumb; Artificial intelligence; Data mining; Machine learning; Crystallization; Protein structure; Algorithm; Peptide sequence; Biology; Genetics; Chemistry; Genome","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":[0.0002720242,0.0002471297,0.0001745889,0.00005425186,0.0002317896,0.0001006038,0.0001292578,0.0001522632,0.00002270186],"category_scores_gemma":[0.0001639527,0.0002273527,0.00006082717,0.00008525035,0.0001523468,0.00005321401,0.00008730578,0.0002095872,0.000003807002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005005589,"about_ca_system_score_gemma":0.0000608635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005469032,"about_ca_topic_score_gemma":0.000003782455,"domain_scores_codex":[0.9986938,0.0001406342,0.0003275248,0.0002545446,0.0001992746,0.0003842329],"domain_scores_gemma":[0.9992402,0.000006288727,0.0002740806,0.0002679486,0.00008117547,0.0001303412],"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":[0.00008717452,0.0000105748,0.01656729,0.0001592089,0.00002544473,0.000001578398,0.0001440809,0.0005244557,0.9819207,0.00002071667,0.00003394164,0.0005048685],"study_design_scores_gemma":[0.001586989,0.0003821786,0.03991114,0.0003578631,0.000092519,0.0001088903,0.00006535462,0.09252509,0.8594865,0.00003858306,0.004362274,0.001082637],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9671357,0.0000330853,0.03122106,0.0003472256,0.0000951828,0.001010187,0.00006122111,0.00005057609,0.00004573321],"genre_scores_gemma":[0.978743,0.000004140157,0.01950986,0.0007824656,0.000354907,0.00005771913,0.0004634737,0.00003054853,0.00005393116],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1224342,"threshold_uncertainty_score":0.9271172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03495640096962885,"score_gpt":0.2668198993332025,"score_spread":0.2318634983635737,"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."}}