{"doi":"10.1093/bioinformatics/btad729","title":"Dupsifter: a lightweight duplicate marking tool for whole genome bisulfite sequencing","abstract":"SUMMARY: In whole genome sequencing data, polymerase chain reaction amplification results in duplicate DNA fragments coming from the same location in the genome. The process of preparing a whole genome bisulfite sequencing (WGBS) library, on the other hand, can create two DNA fragments from the same location that should not be considered duplicates. Currently, only one WGBS-aware duplicate marking tool exists. However, it only works with the output from a single tool, does not accept streaming input or output, and requires a substantial amount of memory relative to the input size. Dupsifter provides an aligner-agnostic duplicate marking tool that is lightweight, has streaming capabilities, and is memory efficient. AVAILABILITY AND IMPLEMENTATION: Source code and binaries are freely available at https://github.com/huishenlab/dupsifter under the MIT license. Dupsifter is implemented in C and is supported on macOS and Linux.","journal":"Bioinformatics","year":2023,"id":371928,"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":6,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9566,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":284749,"name":"Wanding Zhou","orcid":"0000-0001-9126-1932","position":1,"is_corresponding":false},{"id":486008,"name":"Benjamin K. Johnson","orcid":"0000-0002-1482-1032","position":2,"is_corresponding":false},{"id":14040,"name":"Hui Shen","orcid":"0000-0001-9767-4084","position":3,"is_corresponding":false},{"id":638458,"name":"Jacob Morrison","orcid":"0000-0001-8592-4744","position":0,"is_corresponding":true}],"reference_count":12,"raw_metadata":null,"created_at":"2026-07-19T01:15:49.453761Z","pmid":"38092060","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":[]}