{"id":"W3209044105","doi":"10.1186/s12859-021-04420-0","title":"Improve hot region prediction by analyzing different machine learning algorithms","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Wuhan University of Science and Technology; Wuhan University; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Naive Bayes classifier; Machine learning; Artificial intelligence; Random forest; Hot spot (computer programming); Support vector machine; Cluster analysis; Algorithm; Bayes' theorem; Precision and recall; Measure (data warehouse); Data mining; Pattern recognition (psychology); Bayesian probability","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0003097255,0.0001768605,0.0001953041,0.0001043209,0.0001825689,0.000317019,0.0003601475,0.00007187304,0.000006825189],"category_scores_gemma":[0.0003290247,0.0001616707,0.0001082999,0.0004402866,0.00002596259,0.0008723476,0.0003712623,0.0002612472,0.0000209565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001059855,"about_ca_system_score_gemma":0.0001149703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007028013,"about_ca_topic_score_gemma":0.000004233723,"domain_scores_codex":[0.9985104,0.0001277016,0.0004715391,0.000234809,0.0003962246,0.0002592946],"domain_scores_gemma":[0.9987205,0.000435149,0.0002223638,0.0003827215,0.0001332073,0.0001060333],"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":[0.00003536731,0.0006337109,0.03289563,0.0007870619,0.0001901136,0.00003960427,0.006069009,0.1637924,0.002050003,0.01211035,0.006239469,0.7751573],"study_design_scores_gemma":[0.0003280067,0.00006820937,0.002499816,0.00002962111,0.00001233492,0.00004318976,0.00007299476,0.9916408,0.00266798,0.0005826235,0.001884251,0.0001701825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00522663,0.0002288405,0.993042,0.0001540843,0.0004756712,0.0001100982,0.00002438613,0.0002050498,0.0005332326],"genre_scores_gemma":[0.03157735,0.0001375328,0.9666927,0.0002344293,0.000132587,0.00001641746,0.0002539303,0.00001926177,0.0009357973],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8278484,"threshold_uncertainty_score":0.6592739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02324694645982791,"score_gpt":0.263191126878798,"score_spread":0.2399441804189701,"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."}}