{"id":"W2171325548","doi":"10.1002/prot.10340","title":"Data mining crystallization databases: Knowledge‐based approaches to optimize protein crystal screens","year":2003,"lang":"en","type":"article","venue":"Proteins Structure Function and Bioinformatics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research","keywords":"Crystallization; Protein crystallization; Bottleneck; Nucleation; Database; Proteomics; Crystal (programming language); Computer science; Data mining; Computational biology; Crystallography; Chemistry; Biology; Biochemistry","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005261451,0.00035511,0.0002897371,0.0002261444,0.000446956,0.0002854811,0.0002871555,0.0001557186,0.0005558015],"category_scores_gemma":[0.0003611968,0.0002843369,0.00003660264,0.0004725274,0.0001032846,0.001077099,0.0001935186,0.0001851802,0.00002791534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005013669,"about_ca_system_score_gemma":0.0001666143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001227188,"about_ca_topic_score_gemma":0.0001337014,"domain_scores_codex":[0.9980344,0.0001156611,0.000562177,0.0005016535,0.0003783935,0.0004077803],"domain_scores_gemma":[0.9984943,0.00003966319,0.0002506691,0.0008660494,0.0001177034,0.0002316031],"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":[0.001534882,0.0003762342,0.001065533,0.003579588,0.0001768252,0.000006207343,0.003847073,0.009557927,0.8885092,0.03750806,0.0111986,0.04263984],"study_design_scores_gemma":[0.008360597,0.002403331,0.001533002,0.0009528578,0.0005956219,0.0002209281,0.008001286,0.305674,0.3678049,0.002586548,0.2977766,0.004090374],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0516407,0.0001318494,0.94093,0.0001329017,0.0005655979,0.001828059,0.0008524154,0.000241445,0.003677042],"genre_scores_gemma":[0.4547634,0.00000233522,0.543481,0.0002917146,0.0001794197,0.00005810549,0.0009993792,0.00003179387,0.0001928176],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5207043,"threshold_uncertainty_score":0.9999609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1004926654413479,"score_gpt":0.2570565720959526,"score_spread":0.1565639066546048,"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."}}