{"id":"W3000887590","doi":"10.1016/j.ygeno.2020.01.017","title":"Using extreme gradient boosting to identify origin of replication in Saccharomyces cerevisiae via hybrid features","year":2020,"lang":"en","type":"article","venue":"Genomics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":62,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Taipei Medical University; Nvidia","keywords":"Biology; Computational biology; Replication (statistics); DNA replication; Boosting (machine learning); Benchmark (surveying); Mechanism (biology); DNA sequencing; Computer science; Gene; Artificial intelligence; Genetics; Machine learning","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":[0.0002032855,0.0001102056,0.0001435603,0.00004564877,0.0000340454,0.00002045335,0.0002125437,0.00005286279,0.000006595168],"category_scores_gemma":[0.0002296763,0.0001185812,0.00004781426,0.0001073157,0.00001800225,0.000004632918,0.0001540151,0.0000979196,0.000007159821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003388618,"about_ca_system_score_gemma":0.00003886226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004553409,"about_ca_topic_score_gemma":0.00001097127,"domain_scores_codex":[0.9991421,0.00003107961,0.0003236519,0.0002594588,0.00008350552,0.0001601659],"domain_scores_gemma":[0.9993551,0.000008574861,0.0001748935,0.0003455275,0.00004252747,0.00007331333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003789021,0.00001137774,0.0104643,0.00007778945,0.00001467701,0.000001259259,0.0004319552,0.006727339,0.9767359,0.00004391272,0.00036443,0.005089152],"study_design_scores_gemma":[0.0008211693,0.0003753898,0.04065541,0.00009498818,0.00004769628,0.00007396486,0.0002954591,0.0451866,0.8579391,0.0001357667,0.05371088,0.0006635462],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9853471,0.0002641074,0.01353687,0.0003087102,0.00005855004,0.000213119,0.00001421228,0.000009840043,0.0002474995],"genre_scores_gemma":[0.9754417,0.00004046255,0.02378544,0.0004819742,0.000136718,0.00000390858,0.00007182146,0.00001790481,0.00002005706],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1187968,"threshold_uncertainty_score":0.4835599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04807439189777356,"score_gpt":0.3213951069901215,"score_spread":0.2733207150923479,"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."}}