{"id":"W4404366653","doi":"10.1101/2024.11.13.623527","title":"Exploring large protein sequence space through homology- and representation-based hierarchical clustering","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"","keywords":"Sequence homology; Homology (biology); Computational biology; Hierarchical clustering; Representation (politics); Cluster analysis; Sequence (biology); Space (punctuation); Computer science; Evolutionary biology; Biology; Peptide sequence; Artificial intelligence; Genetics; Amino acid","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":[0.001124745,0.0007996605,0.0007871077,0.004358687,0.001072624,0.001567919,0.001268968,0.0006972383,0.001930733],"category_scores_gemma":[0.002832038,0.0005070949,0.001137929,0.003707942,0.0008109802,0.001332962,0.00170797,0.0009889435,0.001167329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001120251,"about_ca_system_score_gemma":0.001639375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008831814,"about_ca_topic_score_gemma":0.009351511,"domain_scores_codex":[0.9990755,0.0002549611,0.00004518767,0.0002545386,0.0002882161,0.00008157116],"domain_scores_gemma":[0.999084,0.0003318492,0.0001390006,0.0001586443,0.0002068267,0.00007961199],"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":[0.0005763575,0.0004748671,0.01385511,0.0008301567,0.0004552872,0.0004862808,0.001722181,0.3805965,0.1436292,0.03987481,0.01269563,0.4048036],"study_design_scores_gemma":[0.00002015939,0.00003528783,0.002110434,0.0000261945,0.00002569192,0.00008325285,0.000214028,0.9529445,0.01013144,0.03028399,0.004092963,0.00003221167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1014808,0.0004448921,0.8890319,0.0003540853,0.00002306467,0.0001851124,0.001358957,0.00527659,0.00184459],"genre_scores_gemma":[0.3335432,0.0003538121,0.6595806,0.00008111091,0.00002466833,0.0002075643,0.004389906,0.0005393499,0.001279757],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008831814,"threshold_uncertainty_score":0.01756078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03851422540899763,"score_gpt":0.2552619284423832,"score_spread":0.2167477030333856,"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."}}