{"id":"W3011478582","doi":"10.2196/17643","title":"A Graph Convolutional Network–Based Method for Chemical-Protein Interaction Extraction: Algorithm Development","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China","keywords":"Computer science; Sentence; Dependency graph; ENCODE; Natural language processing; Artificial intelligence; Graph; Information extraction; Relationship extraction; Dependency (UML); Knowledge graph; Biomedical text mining; Machine learning; Theoretical computer science; Text mining","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035984,0.0001576934,0.000192255,0.00002519284,0.00009226481,0.00002228388,0.0002113735,0.0003800231,0.0001037405],"category_scores_gemma":[0.0003570314,0.000135082,0.0001083296,0.0001269783,0.0001204756,0.000007798447,0.00008572242,0.0002473175,0.00001878051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002309074,"about_ca_system_score_gemma":0.0003035939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001112701,"about_ca_topic_score_gemma":0.00000103842,"domain_scores_codex":[0.9986139,0.00003458038,0.0005181333,0.0001617995,0.0003826028,0.0002889856],"domain_scores_gemma":[0.9992148,0.00007407634,0.000163214,0.0001212733,0.00009919563,0.0003274035],"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":[0.0003667115,0.0001755578,0.00003687074,0.0003368933,0.0001848375,0.00000481393,0.0007133258,0.0001010624,0.01153699,0.0001809669,0.07776583,0.9085962],"study_design_scores_gemma":[0.001555216,0.0003193487,0.00003355977,0.00008766382,0.00001593583,0.00002420895,0.000508896,0.1501589,0.03741538,0.0001066254,0.8094823,0.0002918834],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01253727,0.0000915141,0.9847219,0.001803701,0.0001918105,0.0003372857,0.0000139639,0.00006552597,0.0002370184],"genre_scores_gemma":[0.02471028,0.000009750372,0.9667161,0.006537584,0.0009682273,0.0003701893,0.0006000206,0.00001696988,0.00007090062],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9083043,"threshold_uncertainty_score":0.5508485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0294580438385864,"score_gpt":0.3368170228323837,"score_spread":0.3073589789937973,"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."}}