{"doi":"10.1101/2022.02.02.478879","title":"mcPBWT: Space-efficient Multi-column PBWT Scanning Algorithm for Composite Haplotype Matching","abstract":"Positional Burrows-Wheeler Transform (PBWT) is a data structure that supports efficient algorithms for finding matching segments in a panel of haplotypes. It is of interest to study the composite patterns of multiple matching segments or blocks arranged contiguously along a same haplotype as they can indicate recombination crossover events, gene-conversion tracts, or, sometimes, errors of phasing algorithms. However, current PBWT algorithms do not support search of such composite patterns efficiently. Here, we present our algorithm, mcPBWT (multi-column PBWT), that uses multiple synchronized runs of PBWT at different variant sites providing a \"look-ahead\" information of matches at those variant sites. Such \"look-ahead\" information allows us to analyze multiple contiguous matching pairs in a single pass. We present two specific cases of mcPBWT, namely double-PBWT and triple-PBWT which utilize two and three columns of PBWT respectively. double-PBWT finds two matching pairs' combinations representative of crossover event or phasing error while triple-PBWT finds three matching pairs' combinations representative of gene-conversion tract.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2022,"id":305804,"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":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9513,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2022-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":87092,"name":"Ardalan Naseri","orcid":"0000-0002-2747-2193","position":1,"is_corresponding":false},{"id":24932,"name":"Degui Zhi","orcid":"0000-0001-7754-1890","position":2,"is_corresponding":false},{"id":87093,"name":"Shaojie Zhang","orcid":"0000-0002-4051-5549","position":3,"is_corresponding":false},{"id":87091,"name":"Pramesh Shakya","orcid":"0000-0003-2708-9933","position":0,"is_corresponding":true}],"reference_count":15,"raw_metadata":null,"created_at":"2026-07-19T00:32:44.983506Z","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":[]}