{"id":"W3175203932","doi":"10.1093/bioinformatics/btab482","title":"phyLoSTM: a novel deep learning model on disease prediction from longitudinal microbiome data","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Microbiome; Computer science; Artificial intelligence; Machine learning; Random forest; Convolutional neural network; Longitudinal study; Deep learning; Bioinformatics; Biology; Medicine; Pathology","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":[0.00009964004,0.000159634,0.0001293193,0.00003598336,0.0001441472,0.00005754285,0.0002572956,0.0001224683,0.00002288142],"category_scores_gemma":[0.00008972074,0.0001579592,0.00005535994,0.00008305752,0.0000381477,0.00001655444,0.0003381521,0.0001492532,0.00005848475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002536111,"about_ca_system_score_gemma":0.000224728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008757835,"about_ca_topic_score_gemma":0.00002340348,"domain_scores_codex":[0.9990323,0.00001705163,0.0002911568,0.0002930097,0.0001154966,0.0002510021],"domain_scores_gemma":[0.9988959,0.000009405766,0.0001077706,0.0007474863,0.00008204869,0.0001573576],"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":[0.0002994318,0.0004519408,0.004875639,0.0002584663,0.0001655064,0.00001071816,0.0003561215,0.007448742,0.9693874,0.000128544,0.01202954,0.004587917],"study_design_scores_gemma":[0.002405141,0.0002846374,0.03568379,0.0001687243,0.0001612184,0.00003902472,0.0003571169,0.8775247,0.02226811,0.00006046659,0.06036308,0.0006839516],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.836877,0.001041305,0.1548841,0.0004844741,0.0004374272,0.0003083764,0.004653906,0.00007003596,0.001243308],"genre_scores_gemma":[0.9227265,0.0006035387,0.04419451,0.001283358,0.0004088812,0.000007667434,0.02986643,0.00003955657,0.000869614],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9471194,"threshold_uncertainty_score":0.6441391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03789715023382904,"score_gpt":0.2732261782664164,"score_spread":0.2353290280325874,"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."}}