{"id":"W2883727091","doi":"10.1021/acs.biochem.8b00473","title":"Revealing Unexplored Sequence-Function Space Using Sequence Similarity Networks","year":2018,"lang":"en","type":"article","venue":"Biochemistry","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":105,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Computational biology; Sequence (biology); Function (biology); Similarity (geometry); Protein sequencing; Sequence space; Biology; Protein function; Repertoire; Sequence alignment; Protein structure database; Alignment-free sequence analysis; Peptide sequence; Computer science; Genetics; Sequence database; Artificial intelligence; Gene; Mathematics; Physics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002731532,0.0002522464,0.0001715357,0.00002049729,0.0002432421,0.00006348454,0.0002708987,0.0004327916,0.00004056868],"category_scores_gemma":[0.00005402789,0.0002622952,0.0001070373,0.0001467116,0.0002727351,0.000009397994,0.0001831108,0.0001972292,0.0000140559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006158606,"about_ca_system_score_gemma":0.0001469596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002751464,"about_ca_topic_score_gemma":0.000006193273,"domain_scores_codex":[0.9986336,0.00002618002,0.0003158569,0.0004381881,0.0001451285,0.0004410151],"domain_scores_gemma":[0.9988939,0.000008423262,0.0001816052,0.0005906612,0.0001721202,0.0001533386],"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":[0.00007837741,0.00002044005,0.0004272721,0.00003650891,0.00005505217,0.000002657599,0.00002891289,0.0008731518,0.9928007,0.00005856784,0.004027163,0.001591248],"study_design_scores_gemma":[0.0007265893,0.0002376452,0.0001192747,0.0001342419,0.0000898584,0.0001115456,0.0002090458,0.09959832,0.8798974,0.0004211704,0.01754928,0.0009056689],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9168864,0.0007056524,0.07947481,0.000126654,0.0005911346,0.0001712731,0.00003371623,0.00005085878,0.001959469],"genre_scores_gemma":[0.9913213,0.00009725559,0.004925397,0.0005465797,0.002341186,0.000007950421,0.0002630941,0.0000317187,0.0004655794],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1129033,"threshold_uncertainty_score":0.999983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03823930741795281,"score_gpt":0.2771345886916788,"score_spread":0.238895281273726,"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."}}