{"id":"W4411009890","doi":"10.1093/molbev/msaf136","title":"Exploring Large Protein Sequence Space through Homology- and Representation-based Hierarchical Clustering","year":2025,"lang":"en","type":"article","venue":"Molecular Biology and Evolution","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"Human Frontier Science Program","keywords":"Biology; Computational biology; Sequence alignment; Alignment-free sequence analysis; Sequence analysis; Protein function prediction; Hidden Markov model; Homology (biology); Protein sequencing; Sequence (biology); Cluster analysis; Phylogenetic tree; Multiple sequence alignment; Leverage (statistics); Visualization; Pipeline (software); Bioinformatics; Genetics; Computer science; Data mining; Peptide sequence; Artificial intelligence; Gene; Protein function","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":[0.0001254472,0.0001267818,0.0001299995,0.00004592024,0.0001857081,0.0000107975,0.00006548674,0.0001321449,0.00000102753],"category_scores_gemma":[0.00008726123,0.0001262169,0.00003560927,0.00008225992,0.0002074402,0.000002070436,0.0001727101,0.00008571181,6.824124e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001256831,"about_ca_system_score_gemma":0.00004271554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000594784,"about_ca_topic_score_gemma":0.00003980349,"domain_scores_codex":[0.9991117,0.0001096186,0.0001323381,0.0003958252,0.00002929034,0.0002213025],"domain_scores_gemma":[0.9996925,0.00001492851,0.00003719336,0.0001854181,0.0000390438,0.00003092732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007097038,0.00001913887,0.0225275,0.00002486763,0.00005191406,0.000003025613,0.00004267313,0.00009491223,0.961597,0.01488404,0.00001609096,0.0006678531],"study_design_scores_gemma":[0.003751168,0.001106882,0.2102645,0.0001399543,0.0001326801,0.00005395842,0.000485649,0.004767241,0.71517,0.05030198,0.01286697,0.0009589603],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8507044,0.002831578,0.1451332,0.0007569281,0.00008866133,0.0001875113,0.0000121463,0.00000653715,0.0002789953],"genre_scores_gemma":[0.9949148,0.000239718,0.004338199,0.0002667523,0.00003557384,0.00009775104,0.00003739635,0.000007324034,0.00006249877],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.246427,"threshold_uncertainty_score":0.5146974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03312948828492843,"score_gpt":0.2995392262859621,"score_spread":0.2664097380010336,"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."}}