{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001559588,0.0007574683,0.0008501002,0.001268564,0.0008456793,0.001643378,0.002415724,0.001133407,0.01693837],"category_scores_gemma":[0.006886318,0.0006179052,0.000836694,0.00157085,0.0008788166,0.00246739,0.002203193,0.001302343,0.0134339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006923464,"about_ca_system_score_gemma":0.001402066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001226617,"about_ca_topic_score_gemma":0.001278794,"domain_scores_codex":[0.9982383,0.0003676695,0.0001460079,0.0003814863,0.0007051698,0.0001612505],"domain_scores_gemma":[0.997191,0.0009309815,0.0002187697,0.0008469391,0.000631637,0.0001808088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0014032,0.0002555515,0.003885852,0.0009243382,0.0001664768,0.0002339513,0.0004327203,0.04434197,0.06225976,0.06431277,0.1067014,0.715082],"study_design_scores_gemma":[0.0003159679,0.0005778402,0.001753275,0.000110726,0.00005184126,0.0007828829,0.0001676066,0.6519503,0.1178334,0.1118869,0.1143462,0.0002229935],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02095841,0.001139685,0.9103141,0.000350193,0.000467328,0.0003513972,0.002382701,0.05623456,0.007801621],"genre_scores_gemma":[0.2345582,0.0004005318,0.7446373,0.0003831976,0.0002590576,0.0004982377,0.006221225,0.003406243,0.00963621],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01693837,"threshold_uncertainty_score":0.05666447,"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."}}