{"id":"W1595684610","doi":"10.1186/1471-2105-5-61","title":"An approach to large scale identification of non-obvious structural similarities between proteins","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"Genome Prairie; Genome British Columbia; Michael Smith Health Research BC","keywords":"Threading (protein sequence); Computational biology; Biology; Genome; Sequence alignment; Genetics; Structural similarity; Peptide sequence; Protein structure; Sequence (biology); Protein sequencing; Gene; DNA microarray; Virulence; Gene expression","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":[0.0004164795,0.0002225704,0.0002457772,0.0001224889,0.0001432575,0.00007563033,0.0004859516,0.0002190087,0.000003470753],"category_scores_gemma":[0.000107986,0.0002072231,0.00009369758,0.0001917388,0.00008659189,0.00004139692,0.000156142,0.000150555,0.0000214816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000306086,"about_ca_system_score_gemma":0.0001288429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001933223,"about_ca_topic_score_gemma":0.00002166007,"domain_scores_codex":[0.9983461,0.00002802984,0.0008024014,0.0001737936,0.0003101303,0.0003395222],"domain_scores_gemma":[0.9986181,0.000007479103,0.0003537387,0.0007105623,0.0001580751,0.0001520874],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005197118,0.001363353,0.367834,0.009591426,0.0005337357,0.000001211931,0.06065965,0.3590982,0.1806142,0.004774516,0.001902697,0.01310731],"study_design_scores_gemma":[0.004375796,0.001911369,0.2801506,0.0001534675,0.0001636705,0.0000503086,0.009373805,0.3911506,0.3080755,0.0006319966,0.00218464,0.001778248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4908637,0.000009833522,0.5072505,0.00001345595,0.00005151111,0.000480317,0.0001418319,0.00002632135,0.001162592],"genre_scores_gemma":[0.6823338,0.000002928338,0.3166075,0.0001027063,0.0001067824,0.00002370803,0.0007451851,0.00001946558,0.00005794171],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1914701,"threshold_uncertainty_score":0.8450314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009320389599279316,"score_gpt":0.2698542294167605,"score_spread":0.2605338398174811,"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."}}