{"doi":"10.1101/2021.01.12.426474","title":"An optimized FM-index library for nucleotide and amino acid search","abstract":"Abstract Pattern matching is a key step in a variety of biological sequence analysis pipelines. The FM-index is a compressed data structure for pattern matching, with search run time that is independent of the length of the database text. We present AvxWindowedFMindex (AWFM-index), an open-source, thread-parallel FM-index library written in C that is optimized for indexing nucleotide and amino acid sequences. AWFM-index is easy to incorporate into bioinformatics software and is able to perform exact match count and locate queries ~2-4x faster than SeqAn3’s FM-index implementation for nucleotide search, and ~2-6x faster for amino acid search in a single-threaded context. This performance is due to (i) a new approach to storing FM-index data in a strided bit-vector format that enables extremely efficient computation of the FM-index occurrence function via AVX2 bitwise instructions, and (ii) inclusion of a cache-efficient lookup table for partial k-mer searches. AWFM-index also trivially parallelizes to multiple threads with good scaling, and enables efficient on-disk storage of the memory-intensive suffix array. The open-source library is available for download at https://github.com/TravisWheelerLab/AvxWindowFmIndex .","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2021,"id":218268,"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":2,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9481,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":264756,"name":"Travis J. Wheeler","orcid":"0000-0003-2004-1785","position":1,"is_corresponding":false},{"id":579031,"name":"Tim Anderson","orcid":null,"position":0,"is_corresponding":true}],"reference_count":26,"raw_metadata":null,"created_at":"2026-07-18T23:53:29.626149Z","pmid":null,"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":[]}