{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00256692,0.001339956,0.001636053,0.004995615,0.0007466399,0.001157764,0.001105164,0.001269465,0.001064393],"category_scores_gemma":[0.00496685,0.0002857287,0.001635241,0.002873053,0.0003454825,0.001299952,0.0004792045,0.0008010982,0.000615747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008248998,"about_ca_system_score_gemma":0.00110084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006413334,"about_ca_topic_score_gemma":0.003777581,"domain_scores_codex":[0.9981917,0.0003839391,0.0001774933,0.0004621867,0.000587709,0.0001969392],"domain_scores_gemma":[0.9967319,0.001742262,0.0003040795,0.0002116785,0.0009257522,0.00008444828],"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":[0.0006552128,0.0006919291,0.04364516,0.0004517042,0.0005459021,0.0002662389,0.0001113728,0.3600711,0.01258924,0.001512919,0.005725421,0.5737337],"study_design_scores_gemma":[0.00001959478,0.0000718859,0.003278096,0.00001579997,0.00007534361,0.00006258177,0.000016832,0.9901674,0.004422512,0.001299579,0.0005556006,0.00001480157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2893889,0.004239985,0.695158,0.0004304936,0.0002219136,0.0002867759,0.0007966726,0.006616955,0.00286024],"genre_scores_gemma":[0.6897045,0.0008078421,0.3054698,0.0002474106,0.000127506,0.0001707399,0.002078436,0.0002167483,0.001177088],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006413334,"threshold_uncertainty_score":0.01357532,"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."}}