{"id":"W2059926522","doi":"10.1016/j.bbrc.2007.02.040","title":"Prediction of protein crystallization using collocation of amino acid pairs","year":2007,"lang":"en","type":"article","venue":"Biochemical and Biophysical Research Communications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":118,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"In silico; Protein crystallization; Naive Bayes classifier; Computer science; Crystallization; Classifier (UML); Sequence (biology); Protein Data Bank (RCSB PDB); Artificial intelligence; Threading (protein sequence); Protein sequencing; Peptide sequence; Computational biology; Pattern recognition (psychology); Protein structure; Algorithm; Chemistry; Biology; Biochemistry; Support vector machine","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":[0.0007792594,0.00007626984,0.0001099447,0.00008516377,0.0001167727,0.000009660816,0.0003260703,0.000133137,0.000002911447],"category_scores_gemma":[0.0006515912,0.00007033968,0.00004305224,0.0003527348,0.0006850079,0.000007915434,0.0003179792,0.0001809006,7.472916e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002094609,"about_ca_system_score_gemma":0.00007054573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004066433,"about_ca_topic_score_gemma":0.000004672077,"domain_scores_codex":[0.9989595,0.0001139372,0.0003313788,0.0001344495,0.0002913109,0.0001693581],"domain_scores_gemma":[0.9986571,0.00007232353,0.0001217684,0.0006026113,0.0004697735,0.00007643588],"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":[0.00005637936,0.0001774583,0.0006632044,0.00009572658,0.00001572679,3.206513e-8,0.00005871607,0.000003353205,0.9957882,0.001671213,0.00006216107,0.001407899],"study_design_scores_gemma":[0.0001955163,0.0002510461,0.003100189,0.00006110971,0.000008763617,0.00000141814,0.0001248136,0.005190875,0.9896389,0.0001930015,0.001172769,0.00006164497],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9861175,0.0002890688,0.01246228,0.000134521,0.000008086823,0.0003082096,0.00003487421,0.000008192904,0.000637243],"genre_scores_gemma":[0.9856464,0.0001356985,0.01387256,0.000007096449,0.00004333585,0.00001117645,0.0002328611,0.000008203447,0.000042641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006149277,"threshold_uncertainty_score":0.2868369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07206198932686944,"score_gpt":0.3613267705409309,"score_spread":0.2892647812140614,"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."}}