{"id":"W4376286406","doi":"10.1101/2023.05.08.539909","title":"aaHash: recursive amino acid sequence hashing","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"Canadian Institutes of Health Research; National Institutes of Health","keywords":"Hash function; Dynamic perfect hashing; String (physics); Computer science; Universal hashing; Context (archaeology); K-independent hashing; Theoretical computer science; Hash table; Algorithm; Perfect hash function; 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":[0.001655401,0.0007898532,0.0008943787,0.001285521,0.0008057664,0.001732253,0.002310712,0.001163416,0.01457067],"category_scores_gemma":[0.006312833,0.0006146656,0.0008126613,0.001599796,0.0009604874,0.002373615,0.002197246,0.001394718,0.01227394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006466656,"about_ca_system_score_gemma":0.001258928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001017607,"about_ca_topic_score_gemma":0.00108015,"domain_scores_codex":[0.9982532,0.0003763832,0.0001327932,0.0003924626,0.0006950395,0.0001500215],"domain_scores_gemma":[0.9973366,0.0008650481,0.0002019249,0.000872608,0.0005495613,0.0001743592],"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":[0.001382788,0.0002463894,0.003762323,0.0009277994,0.0001931739,0.0002492738,0.0004231435,0.05118414,0.0673444,0.08605436,0.1125474,0.6756848],"study_design_scores_gemma":[0.0002957381,0.0004236114,0.001581897,0.00009078353,0.00004607817,0.0006974653,0.0001394022,0.6452497,0.1114651,0.1312917,0.1085258,0.000192764],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01795781,0.0009862176,0.9282799,0.0003343453,0.0004163047,0.0002732292,0.002194409,0.04337415,0.006183691],"genre_scores_gemma":[0.2182812,0.0004203489,0.761353,0.000344742,0.00028097,0.000455318,0.005972262,0.00334548,0.009546618],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01457067,"threshold_uncertainty_score":0.04874367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03062097246910129,"score_gpt":0.2439459876309779,"score_spread":0.2133250151618766,"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."}}