{"doi":"10.1101/2020.03.15.992941","title":"Merqury: reference-free quality, completeness, and phasing assessment for genome assemblies","abstract":"Abstract Recent long-read assemblies often exceed the quality and completeness of available reference genomes, making validation challenging. Here we present Merqury, a novel tool for reference-free assembly evaluation based on efficient k-mer set operations. By comparing k-mers in a de novo assembly to those found in unassembled high-accuracy reads, Merqury estimates base-level accuracy and completeness. For trios, Merqury can also evaluate haplotype-specific accuracy, completeness, phase block continuity, and switch errors. Multiple visualizations, such as k-mer spectrum plots, can be generated for evaluation. We demonstrate on both human and plant genomes that Merqury is a fast and robust method for assembly validation. Availability of data and material Project name: Merqury Project home page: https://github.com/marbl/merqury , https://github.com/marbl/meryl Archived version: https://github.com/marbl/merqury/releases/tag/v1.0 Operating system(s): Platform independent Programming language: C++, Java, Perl Other requirements: gcc 4.8 or higher, java 1.6 or higher License: Public domain (see https://github.com/marbl/merqury/blob/master/README.license ) Any restrictions to use by non-academics: No restrictions applied","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2020,"id":118476,"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":73,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9559,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2020-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":4363,"name":"Brian P. Walenz","orcid":"0000-0001-8431-1428","position":1,"is_corresponding":false},{"id":2118,"name":"Sergey Koren","orcid":"0000-0002-1472-8962","position":2,"is_corresponding":false},{"id":2122,"name":"Adam  M. Phillippy","orcid":"0000-0003-2983-8934","position":3,"is_corresponding":false},{"id":21320,"name":"Arang Rhie","orcid":"0000-0002-9809-8127","position":0,"is_corresponding":true}],"reference_count":48,"raw_metadata":null,"created_at":"2026-07-18T23:13:58.531532Z","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":[]}