{"doi":"10.1016/j.cels.2021.08.009","title":"Minimizer-space de Bruijn graphs: Whole-genome assembly of long reads in minutes on a personal computer","abstract":"DNA sequencing data continue to progress toward longer reads with increasingly lower sequencing error rates. Here, we define an algorithmic approach, mdBG, that makes use of minimizer-space de Bruijn graphs to enable long-read genome assembly. mdBG achieves orders-of-magnitude improvement in both speed and memory usage over existing methods without compromising accuracy. A human genome is assembled in under 10 min using 8 cores and 10 GB RAM, and 60 Gbp of metagenome reads are assembled in 4 min using 1 GB RAM. In addition, we constructed a minimizer-space de Bruijn graph-based representation of 661,405 bacterial genomes, comprising 16 million nodes and 45 million edges, and successfully search it for anti-microbial resistance (AMR) genes in 12 min. We expect our advances to be essential to sequence analysis, given the rise of long-read sequencing in genomics, metagenomics, and pangenomics. Code for constructing mdBGs is freely available for download at https://github.com/ekimb/rust-mdbg/.","journal":"Cell Systems","year":2021,"id":148469,"datarank":0.7266280629687888,"base_score":4.844187086458591,"endowment":4.844187086458591,"self_citation_contribution":0.7266280629687888,"citation_network_contribution":0.0,"self_endowment_contribution":0.7266280629687888,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":126,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9555,"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":3585,"name":"Bonnie Berger","orcid":"0000-0002-2724-7228","position":1,"is_corresponding":false},{"id":550281,"name":"Rayan Chikhi","orcid":"0000-0003-1099-8735","position":2,"is_corresponding":false},{"id":557253,"name":"Barış Ekim","orcid":"0000-0002-4040-403X","position":0,"is_corresponding":true}],"reference_count":77,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-18T23:42:46.224799Z","pmid":"34525345","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":[]}