{"id":"W4205272967","doi":"10.1109/bibm52615.2021.9669606","title":"Improving human essential protein prediction using only protein sequences via ensemble learning","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Computer science; Ensemble learning; Machine learning; Boosting (machine learning); Artificial intelligence; Centrality; Data mining; Mathematics","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":[0.001058596,0.0006952633,0.0008924353,0.001587175,0.0003912842,0.0004165843,0.0004808157,0.0006063103,0.0007520871],"category_scores_gemma":[0.002146687,0.0002669246,0.0007389625,0.0009782615,0.0001652015,0.001286909,0.0006256,0.0007104113,0.0005240364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000412497,"about_ca_system_score_gemma":0.0005699149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003626262,"about_ca_topic_score_gemma":0.005466192,"domain_scores_codex":[0.9995117,0.0001157271,0.00002486752,0.0001566364,0.0001337355,0.00005735772],"domain_scores_gemma":[0.9991067,0.0004012938,0.00008187087,0.000116066,0.0002218848,0.00007218881],"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":[0.001096012,0.0005307174,0.05679134,0.0002961164,0.0004585379,0.0004799116,0.0001170142,0.410802,0.04555601,0.004180097,0.0199701,0.4597222],"study_design_scores_gemma":[0.00001127304,0.00003429015,0.001868374,0.000006725769,0.0000236392,0.00005505295,0.000008125664,0.9922414,0.003188882,0.001926323,0.0006289946,0.000006882226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4569233,0.002870041,0.5308772,0.0003951671,0.0001658425,0.0000694796,0.001972923,0.003493448,0.003232472],"genre_scores_gemma":[0.8865895,0.0008416556,0.1055597,0.0001715793,0.00007674379,0.00004758042,0.00514183,0.0001260856,0.001445291],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003626262,"threshold_uncertainty_score":0.007210314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02349242915637555,"score_gpt":0.2962368771833754,"score_spread":0.2727444480269999,"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."}}