{"id":"W1982088273","doi":"10.1016/j.ymeth.2014.10.027","title":"Text as data: Using text-based features for proteins representation and for computational prediction of their characteristics","year":2014,"lang":"en","type":"review","venue":"Methods","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Sinai Hospital; University of Toronto; Queen's University","funders":"U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Representation (politics); Function (biology); Computational biology; Protein sequencing; Value (mathematics); Protein structure database; Process (computing); Genome; Sequence (biology); Protein function prediction; Protein function; Data mining; Information retrieval; Bioinformatics; Biology; Machine learning; Gene; Sequence database; Genetics; Peptide sequence","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":[0.00101841,0.00018942,0.0006509096,0.00006003327,0.0000735802,0.00002162295,0.0002017538,0.0003962386,0.000001299366],"category_scores_gemma":[0.001572376,0.0001431635,0.0001507163,0.00006031871,0.0001396676,0.000002523802,0.00009579657,0.00008347437,1.024354e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009571625,"about_ca_system_score_gemma":0.0001903913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005943622,"about_ca_topic_score_gemma":9.437956e-7,"domain_scores_codex":[0.9986575,0.0003155335,0.0003836644,0.0004407708,0.00007426539,0.0001282376],"domain_scores_gemma":[0.9985252,0.0005487176,0.0004091533,0.0003636938,0.0001135166,0.00003971647],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004053807,0.00002322117,0.000003969014,0.004647787,0.0001072144,8.074843e-8,0.000007546188,0.000005869003,0.0008218364,0.00002585149,0.0004101984,0.9939059],"study_design_scores_gemma":[0.0003346448,0.0003362898,0.00004370357,0.0008767608,0.0003429462,0.00001670283,0.00001166122,0.004863577,0.0008816403,0.0002415036,0.9919049,0.0001456493],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003322061,0.3547745,0.642947,0.00001857677,0.0001622754,0.0007345767,0.001314479,0.000008583806,0.000006827348],"genre_scores_gemma":[0.00003118536,0.1766076,0.8128816,0.0000417615,0.0004759275,0.0001940783,0.009656225,0.00003510548,0.00007650701],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9937602,"threshold_uncertainty_score":0.5838039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2246045402564346,"score_gpt":0.4994441404292237,"score_spread":0.2748396001727891,"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."}}