{"id":"W4292573278","doi":"10.1098/rstb.2021.0237","title":"Mandrake: visualizing microbial population structure by embedding millions of genomes into a low-dimensional representation","year":2022,"lang":"en","type":"article","venue":"Philosophical Transactions of the Royal Society B Biological Sciences","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Global Health Research","funders":"H2020 European Research Council; Medical Research Council; Norges Forskningsråd","keywords":"Population genomics; Genome; Population; Genomics; Computational biology; Computer science; Biology; Data science; 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":[0.001551735,0.001745161,0.00110744,0.003109385,0.0009546289,0.003042453,0.002569113,0.001591134,0.008886507],"category_scores_gemma":[0.005751913,0.0009837868,0.002508886,0.001969273,0.0006413699,0.002657604,0.003445863,0.002849286,0.002697756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005273562,"about_ca_system_score_gemma":0.001278174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004091947,"about_ca_topic_score_gemma":0.006945426,"domain_scores_codex":[0.9993761,0.0001910655,0.0000396384,0.0001655653,0.0001602814,0.0000673813],"domain_scores_gemma":[0.9987581,0.0006849169,0.0001233006,0.0001637289,0.000166335,0.0001036183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00117655,0.000527538,0.01243134,0.002974058,0.001466317,0.001192604,0.004058137,0.1284784,0.1038774,0.04932535,0.1530003,0.541492],"study_design_scores_gemma":[0.0001686345,0.000128105,0.004633796,0.0002250292,0.0001622271,0.0008182171,0.0006067417,0.8268636,0.02816075,0.05867218,0.07925841,0.000302255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0218223,0.0009921355,0.9161944,0.0006953698,0.0001790208,0.0001293521,0.005578863,0.0525535,0.001855062],"genre_scores_gemma":[0.09381089,0.0007065102,0.8912706,0.0002955229,0.00006026061,0.0003943522,0.006956503,0.005095421,0.001409952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008886507,"threshold_uncertainty_score":0.02972835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02229158982997805,"score_gpt":0.2859438745253158,"score_spread":0.2636522846953378,"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."}}