{"id":"W4409238952","doi":"10.1101/2025.04.01.646674","title":"Unsupervised Whole-Genome Representation Learning Captures Bacterial Phenotypes","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Representation (politics); Phenotype; Genome; Computational biology; Artificial intelligence; Unsupervised learning; Computer science; Biology; Evolutionary biology; Genetics; Gene","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":[0.0005253111,0.0005485953,0.0004391266,0.0006253679,0.0001514873,0.0004965229,0.0006633246,0.0006360621,0.0006468013],"category_scores_gemma":[0.002153955,0.0001851209,0.0005907054,0.0005388062,0.0003841683,0.001001134,0.0005095204,0.0008995222,0.0002995909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005891147,"about_ca_system_score_gemma":0.0004448562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002354615,"about_ca_topic_score_gemma":0.002914784,"domain_scores_codex":[0.9997161,0.00008379501,0.000009567722,0.0001193668,0.00003397935,0.00003716378],"domain_scores_gemma":[0.99882,0.000578891,0.0001894346,0.0002179059,0.0001451889,0.00004862802],"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":[0.0004584724,0.0004060377,0.02366126,0.0001724353,0.0001251103,0.0002324426,0.0001416628,0.7770625,0.08204435,0.00416061,0.003147697,0.1083874],"study_design_scores_gemma":[0.000005929784,0.00004065146,0.002196737,0.000003953261,0.000007098215,0.00002064957,0.00001608616,0.9898616,0.005174571,0.002457197,0.0002089783,0.000006558599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8204206,0.0002354763,0.1746233,0.0003025255,0.0000270295,0.00002429913,0.001177892,0.002125673,0.00106323],"genre_scores_gemma":[0.963267,0.00006958806,0.03240622,0.00009996684,0.00001188418,0.00002662183,0.003290953,0.0001004883,0.0007271744],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002354615,"threshold_uncertainty_score":0.004681826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01215532278943317,"score_gpt":0.224725510414632,"score_spread":0.2125701876251989,"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."}}