{"id":"W2155675444","doi":"10.1186/1471-2164-15-1091","title":"Categorizer: a tool to categorize genes into user-defined biological groups based on semantic similarity","year":2014,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Research Foundation of Korea; Natural Sciences and Engineering Research Council of Canada; Chung-Ang University; National Research Foundation","keywords":"Categorization; Semantic similarity; Similarity (geometry); Context (archaeology); Computer science; Gene ontology; Ontology; Semantics (computer science); Biological data; Information retrieval; Gene; Computational biology; Natural language processing; Biology; Artificial intelligence; Bioinformatics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00329159,0.00244122,0.001711783,0.01169297,0.001076918,0.002330963,0.002174128,0.001434648,0.01364605],"category_scores_gemma":[0.01002672,0.0007567331,0.001842038,0.004792114,0.001044345,0.002512751,0.002308333,0.001401552,0.004360121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001182298,"about_ca_system_score_gemma":0.001078814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009985969,"about_ca_topic_score_gemma":0.00145918,"domain_scores_codex":[0.9985926,0.000325002,0.0001423933,0.000431258,0.0003977067,0.00011103],"domain_scores_gemma":[0.9938916,0.004488332,0.0005201251,0.0003838201,0.0004888621,0.0002272587],"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":[0.00365115,0.000855981,0.04648823,0.005392659,0.001220362,0.001531005,0.003017269,0.01047978,0.07345209,0.02219881,0.1942353,0.6374773],"study_design_scores_gemma":[0.001402586,0.001449836,0.06469109,0.001632874,0.0009540297,0.00418479,0.00221282,0.3727794,0.1438108,0.1543647,0.2516573,0.000859835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04406123,0.001537455,0.6897966,0.000777372,0.0002633861,0.0009232156,0.02805858,0.2286978,0.005884348],"genre_scores_gemma":[0.1570206,0.0007783197,0.7949589,0.0007260558,0.0001184286,0.002829533,0.02989705,0.0104401,0.003231039],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01364605,"threshold_uncertainty_score":0.04565054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01544071469148741,"score_gpt":0.2287537617253164,"score_spread":0.213313047033829,"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."}}