{"id":"W3177371828","doi":"10.1089/cmb.2020.0543","title":"Essential Protein Prediction Based on node2vec and XGBoost","year":2021,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Biological network; Identification (biology); Computational biology; Construct (python library); Boosting (machine learning); Artificial intelligence; Machine learning; Data mining; Biology","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":[0.0005402212,0.0001078437,0.0002011452,0.0002088799,0.00008141115,0.00008082638,0.0002344058,0.00006403271,0.00001934295],"category_scores_gemma":[0.0002612087,0.0000966353,0.00008823202,0.0002638458,0.00006802866,0.0002461999,0.00009209306,0.0001955702,0.000005443684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000465887,"about_ca_system_score_gemma":0.0005533905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001044189,"about_ca_topic_score_gemma":4.607289e-7,"domain_scores_codex":[0.9984979,0.000419013,0.0004226963,0.0002226444,0.0003082367,0.0001294772],"domain_scores_gemma":[0.9981917,0.0007553207,0.0002868208,0.0001169752,0.0005642333,0.00008492787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009337953,0.000235742,0.0009299306,0.00001856125,0.00006110728,0.00009573602,0.00008551763,0.8181748,0.004693452,0.1524421,0.0003087679,0.02286082],"study_design_scores_gemma":[0.00103887,0.0004196605,0.02120776,0.0000527359,0.00000984106,0.0003772093,0.000007275517,0.808861,0.00274042,0.1639166,0.001250714,0.0001179628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1714332,0.0001067264,0.8242116,0.003435726,0.0004622116,0.00005954487,0.00001052166,0.00001600911,0.0002645013],"genre_scores_gemma":[0.7733492,0.000002486986,0.2258418,0.0005824572,0.0001854413,0.000002010708,0.00001483053,0.000004699842,0.00001701458],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6019161,"threshold_uncertainty_score":0.3940673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01235493312477577,"score_gpt":0.2912001665630558,"score_spread":0.27884523343828,"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."}}