{"id":"W2139259976","doi":"10.1186/1471-2105-4-11","title":"PreBIND and Textomy – mining the biomedical literature for protein-protein interactions using a support vector machine","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":340,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; National Research Council Canada; Lunenfeld-Tanenbaum Research Institute","funders":"Canadian Institutes of Health Research; Directorate for Biological Sciences; Genome Canada","keywords":"Computer science; Support vector machine; Set (abstract data type); Task (project management); Interaction information; Precision and recall; Recall; Data curation; Interaction network; Artificial intelligence; Protein–protein interaction; Data mining; Machine learning; Database; Information retrieval; Biology","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":[0.003664037,0.001115911,0.001130792,0.01690686,0.0006997165,0.002174788,0.00132593,0.000947494,0.008280493],"category_scores_gemma":[0.01239189,0.0003690659,0.001302856,0.007089309,0.0005402458,0.00217465,0.00143533,0.0008191144,0.004607525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008082588,"about_ca_system_score_gemma":0.003111933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002209707,"about_ca_topic_score_gemma":0.003747143,"domain_scores_codex":[0.9978281,0.0004170439,0.0005289041,0.0005328124,0.0005994194,0.00009379743],"domain_scores_gemma":[0.9913651,0.004296163,0.001220894,0.0006881528,0.002145953,0.0002838159],"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":[0.000945551,0.0003989681,0.02033173,0.00663502,0.0004595455,0.001075073,0.0006788184,0.005066533,0.03736115,0.002692855,0.0528539,0.871501],"study_design_scores_gemma":[0.000700597,0.002955172,0.09226254,0.002301746,0.001320389,0.007551084,0.002627303,0.317281,0.1706269,0.03345927,0.3684707,0.000443324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3048123,0.03055897,0.4491294,0.006488458,0.001080134,0.004479551,0.1394828,0.04922898,0.01473933],"genre_scores_gemma":[0.2728015,0.005532228,0.6024123,0.0007535659,0.0003976708,0.002010341,0.1073434,0.0005317177,0.00821724],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01690686,"threshold_uncertainty_score":0.02770096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02721208388926301,"score_gpt":0.2967162964898785,"score_spread":0.2695042126006155,"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."}}