{"id":"W4297394736","doi":"10.3389/fbinf.2022.954529","title":"Predicting liver cancer on epigenomics data using machine learning","year":2022,"lang":"en","type":"article","venue":"Frontiers in Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Laurentian University","funders":"","keywords":"Epigenomics; Liver cancer; Epigenetics; DNA methylation; Computational biology; Biology; Feature selection; Cancer; Histone; Genome; Hepatocellular carcinoma; Computer science; Gene; Bioinformatics; Artificial intelligence; Genetics; Gene expression","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":[0.0004554463,0.0001218359,0.0001278673,0.0001078531,0.0002439973,0.00002418202,0.000366195,0.00006493393,0.0000214016],"category_scores_gemma":[0.00007489519,0.0001335132,0.00003100534,0.0001362958,0.0000287133,0.00001075665,0.0005529916,0.0002500337,0.000001065881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009510075,"about_ca_system_score_gemma":0.00007447082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001174748,"about_ca_topic_score_gemma":0.00005596934,"domain_scores_codex":[0.9990303,0.0000682551,0.0003027805,0.0001951913,0.0001804919,0.0002230181],"domain_scores_gemma":[0.9993533,0.000009308831,0.0001711782,0.000401162,0.00002114578,0.00004385732],"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":[0.0001793262,0.00009590993,0.4642974,0.00007871385,0.00009634704,0.000005708395,0.001323888,0.4774853,0.007128196,0.00001722699,0.0009188566,0.04837316],"study_design_scores_gemma":[0.0003511193,0.0001375249,0.0008571171,0.000008893842,0.00001532503,0.00000186806,0.0006429628,0.9542491,0.003359837,0.00002328095,0.04017746,0.0001754467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9226843,0.007813848,0.06695022,0.00003740159,0.001151477,0.000286897,0.0002840114,0.00001806112,0.0007737748],"genre_scores_gemma":[0.8642321,0.004904238,0.1272923,0.0003511432,0.0003196308,0.00003170473,0.002446498,0.00006361652,0.0003587741],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4767639,"threshold_uncertainty_score":0.5444511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03194714082554689,"score_gpt":0.2715499766577785,"score_spread":0.2396028358322316,"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."}}