{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01148772,0.002965489,0.004158633,0.01177217,0.001537736,0.005632166,0.006107227,0.002204838,0.00377688],"category_scores_gemma":[0.03613519,0.001624326,0.002912988,0.01180376,0.0007880225,0.004363888,0.003157458,0.002456422,0.002919558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001471038,"about_ca_system_score_gemma":0.002783747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004006509,"about_ca_topic_score_gemma":0.00676035,"domain_scores_codex":[0.9939501,0.001967621,0.001320762,0.001000769,0.001547939,0.0002127534],"domain_scores_gemma":[0.9817452,0.01141849,0.001201846,0.003145688,0.00202703,0.000461862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002378507,0.002305349,0.01732512,0.007592474,0.002158861,0.001317081,0.0007962739,0.09353271,0.01456093,0.03183339,0.1302808,0.6959185],"study_design_scores_gemma":[0.0009870924,0.0005040983,0.005406357,0.001052781,0.001022358,0.001167645,0.001022722,0.723499,0.02520026,0.1057708,0.134027,0.0003398723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02135498,0.004246933,0.8245066,0.002413153,0.0002693804,0.002493014,0.07842272,0.06136671,0.004926621],"genre_scores_gemma":[0.04286174,0.002378821,0.8652104,0.0004131198,0.00009155023,0.002092537,0.08525502,0.001001307,0.0006956361],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01177217,"threshold_uncertainty_score":0.06075358,"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."}}