{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003978201,0.0002869543,0.0002440627,0.0002160868,0.0002769475,0.0002122536,0.0002551377,0.0002143834,0.0001966834],"category_scores_gemma":[0.000188045,0.000255761,0.00007939775,0.0001983414,0.0001915649,0.00005183245,0.0001822432,0.0003885615,0.00001639391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004991494,"about_ca_system_score_gemma":0.0002856139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009602024,"about_ca_topic_score_gemma":0.00003095851,"domain_scores_codex":[0.9980869,0.00006899308,0.0006726465,0.0003187265,0.0005444246,0.0003083545],"domain_scores_gemma":[0.9987085,0.00001175591,0.000434554,0.0002553224,0.0004515171,0.0001383546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004530199,0.00005721234,0.0004037449,0.0001480612,0.0000928619,0.00001151703,0.0002165442,0.0001696113,0.9850059,0.001183948,0.0001085427,0.01255682],"study_design_scores_gemma":[0.001746802,0.001281854,0.0002255951,0.0007261543,0.00005867179,0.0003135843,0.001463443,0.563347,0.4240141,0.0003666345,0.005830378,0.0006257978],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9368796,0.00005469793,0.05348958,0.0006250964,0.0005201941,0.0004253597,0.00005384969,0.00003824407,0.007913327],"genre_scores_gemma":[0.9845877,0.00007234784,0.01144562,0.000174605,0.0006368794,0.00001500627,0.0008312963,0.00002281724,0.002213674],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5631774,"threshold_uncertainty_score":0.9999894,"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."}}