{"doi":"10.1093/bioinformatics/btac564","title":"ntHash2: recursive spaced seed hashing for nucleotide sequences","abstract":"MOTIVATION: Spaced seeds are robust alternatives to k-mers in analyzing nucleotide sequences with high base mismatch rates. Hashing is also crucial for efficiently storing abundant sequence data. Here, we introduce ntHash2, a fast algorithm for spaced seed hashing that can be integrated into various bioinformatics tools for efficient sequence analysis with applications in genome research. RESULTS: ntHash2 is up to 2.1× faster at hashing various spaced seeds than the previous version and 3.8× faster than conventional hashing algorithms with naïve adaptation. Additionally, we reduced the collision rate of ntHash for longer k-mer lengths and improved the uniformity of the hash distribution by modifying the canonical hashing mechanism. AVAILABILITY AND IMPLEMENTATION: ntHash2 is freely available online at github.com/bcgsc/ntHash under an MIT license. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.","journal":"Bioinformatics","year":2022,"id":252818,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":23,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9511,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2022-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":408980,"name":"Johnathan Wong","orcid":"0000-0002-1687-8972","position":1,"is_corresponding":false},{"id":459240,"name":"Vladimir Nikolić","orcid":"0000-0002-2992-9935","position":2,"is_corresponding":false},{"id":22083,"name":"Hamid Mohamadi","orcid":null,"position":3,"is_corresponding":false},{"id":18717,"name":"René L. Warren","orcid":"0000-0002-9890-2293","position":4,"is_corresponding":false},{"id":18731,"name":"Inanc Birol","orcid":"0000-0003-0950-7839","position":5,"is_corresponding":false},{"id":897421,"name":"Parham Kazemi","orcid":"0000-0002-2126-5644","position":0,"is_corresponding":true}],"reference_count":5,"raw_metadata":null,"created_at":"2026-07-19T00:24:50.819822Z","pmid":"36000872","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}