{"id":"W4321443557","doi":"10.1002/cpz1.666","title":"Clustering Highly Divergent Homologous Proteins: An Alignment‐Free Method","year":2023,"lang":"en","type":"article","venue":"Current Protocols","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Cluster analysis; Computational biology; Alignment-free sequence analysis; Hierarchical clustering; Homology (biology); Sequence alignment; Biology; Multiple sequence alignment; Coding region; Distance matrix; Protein superfamily; Genetics; Computer science; Gene; Peptide sequence; Artificial intelligence; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000336053,0.0001967637,0.0001711753,0.00005666526,0.0002382748,0.0001045015,0.0005603078,0.00006010577,0.002753685],"category_scores_gemma":[0.00003480744,0.0001776283,0.00009175728,0.0003116108,0.0000668586,0.0004557254,0.0009232337,0.0001853974,0.002130658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001869552,"about_ca_system_score_gemma":0.00001172476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001251975,"about_ca_topic_score_gemma":0.00007952596,"domain_scores_codex":[0.9984458,0.0001432874,0.0002871448,0.0004717454,0.0002218878,0.0004301268],"domain_scores_gemma":[0.9990906,0.00002123344,0.0001121217,0.0006020279,0.00001010904,0.0001638755],"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":[0.00007434752,0.0007019026,0.001315884,0.0001224037,0.0000264794,0.00003333271,0.0009924782,0.0008407596,0.6785818,0.00007672032,0.02831062,0.2889233],"study_design_scores_gemma":[0.001401672,0.0006381253,0.05694228,0.0002688538,0.00003073625,0.00004364546,0.0001276261,0.003582653,0.06544574,0.0009594437,0.8697752,0.0007840122],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"protocol","genre_gemma":"protocol","genre_scores_codex":[0.3672784,0.0000691399,0.1168828,0.002027206,0.004952315,0.4895956,0.000608997,0.003384672,0.01520098],"genre_scores_gemma":[0.1465738,0.00005802751,0.04315123,0.0004634738,0.001063523,0.7986422,0.000257668,0.0002079043,0.009582215],"genre_candidate":"protocol","genre_consensus":"protocol","teacher_disagreement_score":0.8414646,"threshold_uncertainty_score":0.9986463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05921266559322631,"score_gpt":0.3747504526448367,"score_spread":0.3155377870516104,"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."}}