{"doi":"10.1101/gr.280940.125","title":"Partitioned multi-MUM finding for scalable pangenomics with MumemtoM","abstract":"Pangenome collections are growing to hundreds of high-quality genomes. This necessitates scalable methods for constructing pangenome alignments that can incorporate newly sequenced assemblies. We previously developed Mumemto, which computes maximal unique matches (multi-MUMs) across pangenomes using compressed indexing. In this work, we introduce MumemtoM (Mumemto Merge), comprising two new partitioning and merging strategies. Both strategies enable highly parallel, memory-efficient, and updateable computation of multi-MUMs. One of the strategies, called string-based merging, is also capable of conducting the merges in a way that follows the shape of a phylogenetic tree, naturally yielding the multi-MUM for the tree's internal nodes as well as the root. With these strategies, Mumemto now scales to 474 human haplotypes, the only multi-MUM method able to do so. It also introduces a time-memory tradeoff that allows Mumemto to be tailored to more scenarios, including in resource-limited settings.","journal":"Genome Research","year":2025,"id":559463,"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":1,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9487,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":18148,"name":"Ben Langmead","orcid":"0000-0003-2437-1976","position":1,"is_corresponding":false},{"id":588170,"name":"Vikram S. Shivakumar","orcid":"0000-0002-1424-3711","position":0,"is_corresponding":true}],"reference_count":0,"raw_metadata":null,"created_at":"2026-07-19T02:55:34.849815Z","pmid":"41203424","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":[]}