{"id":"W4382069006","doi":"10.3390/pharmaceutics15071808","title":"Ensemble-Learning and Feature Selection Techniques for Enhanced Antisense Oligonucleotide Efficacy Prediction in Exon Skipping","year":2023,"lang":"en","type":"article","venue":"Pharmaceutics","topic":"Advanced biosensing and bioanalysis techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Muscular Dystrophy Canada; Canadian Institutes of Health Research; Women and Children's Health Research Institute; National Center of Neurology and Psychiatry; Children's Health Research Institute","keywords":"Exon skipping; Computer science; Machine learning; Random forest; Feature selection; Artificial intelligence; Boosting (machine learning); Ensemble learning; Exon; Bioinformatics; Gene; Biology; Alternative splicing; Genetics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002901442,0.0001502705,0.0001448206,0.0001537443,0.0001288458,0.00002564161,0.00004728857,0.0001650368,4.123023e-7],"category_scores_gemma":[0.000139495,0.0001530831,0.00005935551,0.0003334667,0.00004129526,0.000007272987,0.00005372729,0.0001819198,0.00000100389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002363251,"about_ca_system_score_gemma":0.00001601699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002312129,"about_ca_topic_score_gemma":0.00001200696,"domain_scores_codex":[0.999087,0.0000576866,0.0001680915,0.0003456657,0.00008095313,0.0002605419],"domain_scores_gemma":[0.9996711,0.00003371688,0.00007956996,0.00008519361,0.00008090255,0.00004952259],"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":[0.0001011737,0.00002355208,0.001072139,0.00003374811,0.00002526444,0.000001676168,0.00003310978,0.00005508112,0.9547181,0.00000509554,0.0004967951,0.04343427],"study_design_scores_gemma":[0.0004001605,0.0001506533,0.0006508188,0.00004332715,0.00003754446,0.00001277282,0.00005611577,0.004710567,0.9600172,0.00004029015,0.03372001,0.0001605355],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9848168,0.000162644,0.0137087,0.0002221061,0.00006515977,0.0004437083,0.00001248001,0.0003429003,0.000225525],"genre_scores_gemma":[0.9879741,0.00209784,0.008875321,0.0001107093,0.0002025576,0.00002964066,0.0001457908,0.00002898545,0.000535076],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04327373,"threshold_uncertainty_score":0.6242546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01953525147434966,"score_gpt":0.3456866444112189,"score_spread":0.3261513929368692,"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."}}