{"id":"W4388643693","doi":"10.1093/bioadv/vbad162","title":"aaHash: recursive amino acid sequence hashing","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Dynamic perfect hashing; Hash function; Computer science; String (physics); Universal hashing; Context (archaeology); K-independent hashing; Theoretical computer science; Hash table; Algorithm; Locality-sensitive hashing; Double hashing; Biology; Mathematics; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0001559372,0.0001623693,0.000142542,0.00005902452,0.0001705908,0.00004047572,0.0002430718,0.00007459406,0.000004794247],"category_scores_gemma":[0.0001118031,0.0001470951,0.00007099761,0.0001834722,0.0001022775,0.000005661628,0.0001861175,0.00005903245,0.0001192867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001144563,"about_ca_system_score_gemma":0.00004772931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002902374,"about_ca_topic_score_gemma":0.00001345742,"domain_scores_codex":[0.9990846,0.00001286212,0.000264439,0.0001785176,0.0001388048,0.0003208123],"domain_scores_gemma":[0.9994271,0.00001807281,0.0001252034,0.0002846505,0.00007615861,0.00006877628],"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":[0.00008225313,0.00004997134,0.005819424,0.0003045739,0.0002411784,0.00001397787,0.002603623,0.002125658,0.7877169,0.002262556,0.01499808,0.1837818],"study_design_scores_gemma":[0.0007679868,0.000532195,0.003881132,0.00006320468,0.00003551203,0.00003283452,0.003479015,0.002619937,0.243167,0.002861117,0.7417176,0.0008424988],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9800145,0.004809379,0.002126124,0.0003393599,0.0008613028,0.000326389,0.0001430259,0.00004857749,0.01133137],"genre_scores_gemma":[0.9738334,0.007729465,0.01673089,0.0004332347,0.0002761389,0.00004450749,0.0001734097,0.00002626395,0.0007526787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7267195,"threshold_uncertainty_score":0.5998365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02459884249832153,"score_gpt":0.2769423388426316,"score_spread":0.2523434963443101,"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."}}