{"id":"W4377047057","doi":"10.1093/bioadv/vbad059","title":"A self-knowledge distillation-driven CNN-LSTM model for predicting disease outcomes using longitudinal microbiome data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto; Western University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Manitoba Medical Service Foundation","keywords":"Microbiome; Computer science; Artificial intelligence; Convolutional neural network; Deep learning; Inference; Machine learning; Data mining; Bioinformatics; Biology","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":[0.0002100143,0.0002095966,0.0002089138,0.00009990302,0.0003011487,0.00005801633,0.0004053776,0.00008384888,0.000001790769],"category_scores_gemma":[0.0001211574,0.0001883951,0.00008715875,0.0001733066,0.00005671951,0.00005659304,0.000407547,0.00005714599,0.00001989441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003504129,"about_ca_system_score_gemma":0.0002965589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002502374,"about_ca_topic_score_gemma":0.00003556086,"domain_scores_codex":[0.9987386,0.00001282277,0.0004343582,0.000311756,0.00009418423,0.0004082136],"domain_scores_gemma":[0.998899,0.00003705834,0.0002053006,0.0005980803,0.0001065728,0.0001539772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008205797,0.001075722,0.6393335,0.0170062,0.00135724,0.00001247511,0.005453395,0.1348646,0.1488422,0.001631568,0.02932482,0.02027766],"study_design_scores_gemma":[0.0005258434,0.0000431473,0.004685589,0.00004676781,0.00006359712,0.000004205032,0.000113679,0.9755995,0.0002081622,0.00006748047,0.01838252,0.0002595408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7018338,0.002225309,0.2867727,0.0003255514,0.000906282,0.001732455,0.005578785,0.0002953677,0.0003297068],"genre_scores_gemma":[0.7801226,0.001102855,0.210147,0.0001517208,0.0003690654,0.00004759654,0.0074183,0.00006654538,0.0005743014],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8407349,"threshold_uncertainty_score":0.7682527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06966997547000747,"score_gpt":0.3625614829663176,"score_spread":0.2928915074963101,"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."}}