{"id":"W4406887020","doi":"10.1093/bioinformatics/btaf042","title":"Multidimensional scaling improves distance-based clustering for microbiome data","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; School of Medicine and Public Health, University of Wisconsin-Madison","keywords":"Cluster analysis; Computer science; Multidimensional scaling; Medoid; Microbiome; Data mining; Clustering high-dimensional data; Dimensionality reduction; Artificial intelligence; Pattern recognition (psychology); Machine learning; Bioinformatics; Biology","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":[0.0002098567,0.0001297844,0.0001294713,0.00005687087,0.0001503428,0.00003260993,0.000288173,0.0001183531,0.000002634047],"category_scores_gemma":[0.00006259606,0.0001199917,0.0000537124,0.00007500246,0.00005084926,0.000008429996,0.0002509877,0.00005064469,0.000006043035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002148723,"about_ca_system_score_gemma":0.0002325284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006073698,"about_ca_topic_score_gemma":0.00002643427,"domain_scores_codex":[0.9991745,0.000008790689,0.0003217517,0.0001927845,0.00004691435,0.0002552515],"domain_scores_gemma":[0.9992026,0.00002207061,0.00009105409,0.0005649358,0.00007120039,0.00004815264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001449323,0.00005763291,0.0001573896,0.0008023796,0.00004773081,2.153348e-7,0.0000420083,0.0001458034,0.9679503,0.0001526868,0.02187432,0.00862459],"study_design_scores_gemma":[0.002676724,0.0001503362,0.0009809445,0.0002160377,0.00005274461,0.000004703197,0.0001980198,0.2508325,0.1308218,0.000023074,0.6136195,0.0004235527],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09850036,0.0006511173,0.8972729,0.0005796239,0.0007218355,0.000798712,0.000922444,0.00004036337,0.0005126824],"genre_scores_gemma":[0.3964388,0.00009399211,0.5891304,0.004562966,0.0002388802,0.0000387549,0.008034578,0.00003703354,0.001424588],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8371285,"threshold_uncertainty_score":0.4893121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02101199347599604,"score_gpt":0.2972578748309899,"score_spread":0.2762458813549938,"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."}}