{"id":"W2136992683","doi":"10.1186/1471-2105-7-41","title":"Discovering semantic features in the literature: a foundation for building functional associations","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":92,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Context (archaeology); DNA microarray; Non-negative matrix factorization; Data mining; Semantic similarity; Interpretation (philosophy); Information retrieval; Computational biology; Natural language processing; Gene; Artificial intelligence; Biology; Matrix decomposition; Gene expression; Genetics","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":[0.0002780238,0.00008229551,0.00007272838,0.00004318744,0.0001167692,0.0001055692,0.0001090326,0.0001212683,0.000001160335],"category_scores_gemma":[0.0002414189,0.00005646704,0.00006499448,0.0001313571,0.00003855697,0.000009470302,0.00002737435,0.00007342872,0.000001908878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001594413,"about_ca_system_score_gemma":0.00004065238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001358654,"about_ca_topic_score_gemma":0.0001846922,"domain_scores_codex":[0.9994231,0.00002054849,0.0002012471,0.00008351658,0.0001166998,0.0001548552],"domain_scores_gemma":[0.9996646,0.00007944268,0.00008307071,0.0001241646,0.00003679088,0.00001193591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.001032348,0.001767647,0.2198442,0.003556841,0.0005426916,0.0000104321,0.01509328,0.04186331,0.07719495,0.1270834,0.3340451,0.1779657],"study_design_scores_gemma":[0.004672131,0.0006632239,0.7202955,0.000346908,0.0001286025,0.0001206073,0.004456914,0.08077957,0.007816113,0.01196421,0.1676006,0.001155581],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3091743,0.0007048431,0.6872745,0.000715945,0.0004084955,0.0004870201,0.00007863371,0.00003511543,0.001121079],"genre_scores_gemma":[0.8810456,0.00002584675,0.1160169,0.0004040307,0.0005345407,0.00007899509,0.001484726,0.00001052252,0.0003987704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5718713,"threshold_uncertainty_score":0.2302659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01682319253337033,"score_gpt":0.2701781252555171,"score_spread":0.2533549327221468,"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."}}