{"id":"W4414083938","doi":"10.1038/s41564-025-02112-6","title":"Learning ecosystem-scale dynamics from microbiome data with MDSINE2","year":2025,"lang":"en","type":"article","venue":"Nature Microbiology","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; Defense Advanced Research Projects Agency; National Science Foundation; National Institutes of Health; Massachusetts Life Sciences Center; U.S. Department of Health and Human Services; National Institute of Diabetes and Digestive and Kidney Diseases; U.S. Department of Defense","keywords":"Microbiome; Benchmark (surveying); Inference; Bayesian probability; Dynamical systems theory; Noise (video); Bayesian inference; Time series; Limit (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003750776,0.001364652,0.001154574,0.001907374,0.0005288773,0.001595746,0.001821246,0.001627637,0.00256422],"category_scores_gemma":[0.01198498,0.0008876828,0.001775315,0.000998645,0.0006262968,0.001741047,0.002022598,0.002182085,0.001197359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007517862,"about_ca_system_score_gemma":0.001738853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00562884,"about_ca_topic_score_gemma":0.01453545,"domain_scores_codex":[0.9991298,0.0003488649,0.00005023891,0.000264834,0.0001596475,0.00004659456],"domain_scores_gemma":[0.9966132,0.00251368,0.0001959503,0.0002960604,0.000229199,0.0001519471],"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":[0.0004642729,0.0002129466,0.02561504,0.0006400184,0.0009631368,0.0002502529,0.0002344201,0.8281448,0.007590559,0.009651224,0.01109375,0.1151396],"study_design_scores_gemma":[0.00002512499,0.00002595015,0.000615334,0.00001357227,0.00001393407,0.00003435302,0.0000119752,0.9900814,0.0009098168,0.006472962,0.001780029,0.00001560902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07180769,0.00137191,0.9031295,0.0008270557,0.0001439076,0.0001253543,0.007168549,0.01398333,0.001442724],"genre_scores_gemma":[0.3506629,0.0006149454,0.6223424,0.0006961629,0.0001381754,0.0004691358,0.02144127,0.001489587,0.002145385],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00562884,"threshold_uncertainty_score":0.01983619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003052808709757936,"score_gpt":0.2464192700439447,"score_spread":0.2433664613341867,"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."}}