{"doi":"10.1093/bioinformatics/btae757","title":"Fast and exact gap-affine partial order alignment with POASTA","abstract":"MOTIVATION: Partial order alignment is a widely used method for computing multiple sequence alignments, with applications in genome assembly and pangenomics, among many others. Current algorithms to compute the optimal, gap-affine partial order alignment do not scale well to larger graphs and sequences. While heuristic approaches exist, they do not guarantee optimal alignment and sacrifice alignment accuracy. RESULTS: We present POASTA, a new optimal algorithm for partial order alignment that exploits long stretches of matching sequence between the graph and a query. We benchmarked POASTA against the state-of-the-art on several diverse bacterial gene datasets and demonstrated an average speed-up of 4.1× and up to 9.8×, using less memory. POASTA's memory scaling characteristics enabled the construction of much larger POA graphs than previously possible, as demonstrated by megabase-length alignments of 342 Mycobacterium tuberculosis sequences. AVAILABILITY AND IMPLEMENTATION: POASTA is available on Github at https://github.com/broadinstitute/poasta.","journal":"Bioinformatics","year":2024,"id":451255,"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":4,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9474,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":44778,"name":"Abigail L. Manson","orcid":"0000-0002-3800-0714","position":1,"is_corresponding":false},{"id":29020,"name":"Ashlee M. Earl","orcid":"0000-0001-7857-9145","position":2,"is_corresponding":false},{"id":58439,"name":"Kiran Garimella","orcid":"0000-0002-6212-5736","position":3,"is_corresponding":false},{"id":44767,"name":"Thomas Abeel","orcid":"0000-0002-7205-7431","position":4,"is_corresponding":false},{"id":807755,"name":"Lucas R. van Dijk","orcid":"0000-0002-7565-5859","position":0,"is_corresponding":true}],"reference_count":39,"raw_metadata":null,"created_at":"2026-07-19T02:02:41.417944Z","pmid":"39752324","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":[]}