{"id":"W4409905545","doi":"10.1093/nargab/lqaf048","title":"Discovering governing equations of biological systems through representation learning and sparse model discovery","year":2025,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Computer science; Identification (biology); Representation (politics); Gene regulatory network; Artificial intelligence; Machine learning; Dynamical systems theory; Biological network; Complex system; Biological data; Nonlinear system; PageRank; Systems biology; Key (lock); Theoretical computer science; Deep learning; Data mining; Computational biology; Gene; Biology; Bioinformatics; 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":[0.0001548432,0.0001061464,0.0001739702,0.00003909052,0.0001150681,0.0000658988,0.00006129714,0.0001043251,3.988523e-7],"category_scores_gemma":[0.00006327251,0.00009267232,0.00005108383,0.00009479669,0.00008016852,0.00002062786,0.0001791538,0.00006810781,3.801366e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001642258,"about_ca_system_score_gemma":0.00005140935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001978892,"about_ca_topic_score_gemma":0.000006792376,"domain_scores_codex":[0.9993159,0.00002459034,0.0003226799,0.0001450755,0.00006829643,0.0001234985],"domain_scores_gemma":[0.9995976,0.00002600359,0.000172355,0.0001394437,0.0000391848,0.00002538246],"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":[0.0001015175,0.0000504393,0.03867861,0.0003669077,0.0004461965,6.362888e-7,0.001228286,0.7352794,0.2100444,0.007768797,0.0002232499,0.005811573],"study_design_scores_gemma":[0.0003243302,0.00007481765,0.0006259998,0.00004044619,0.00007211568,0.000003843114,0.002067787,0.988667,0.005973592,0.0001944893,0.001796445,0.0001592015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7858101,0.00147127,0.2119612,0.00002190273,0.00003817147,0.0001006096,0.00001822845,0.000004775178,0.0005737559],"genre_scores_gemma":[0.9907578,0.002779139,0.005941623,0.00002467181,0.00003181415,0.000004986414,0.0001117131,0.000005902776,0.0003423638],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2533875,"threshold_uncertainty_score":0.3779067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02124096170560071,"score_gpt":0.2637873461398547,"score_spread":0.2425463844342539,"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."}}