{"doi":"10.1101/2022.06.13.495703","title":"DIVE: a reference-free statistical approach to diversity-generating &amp; mobile genetic element discovery","abstract":"<jats:p>\n                  Diversity-generating and mobile genetic elements are paramount to microbial and viral evolution and result in evolutionary leaps conferring novel phenotypes, such as antimicrobial resistance. State-of-the-art algorithms to detect these elements have many limitations, including reliance on reference genomes, assemblers, and heuristics, resulting in computational bottlenecks and limiting the scope of biological discoveries. Here we introduce DIVE, a new reference-free approach to overcome these limitations using information contained in sequencing reads alone. We show that DIVE has improved detection power compared to existing reference-based methods using simulations and real data. We use DIVE to rediscover and characterize the activity of known and novel elements and generate new biological hypotheses about the mobilome. Using DIVE we rediscover CRISPR and identify novel repeats, and we discover unannotated genetic hyper-variability hotspots in\n                  <jats:italic>Escherichia coli</jats:italic>\n                  and\n                  <jats:italic>Vibrio cholerae</jats:italic>\n                  . Building on DIVE, we develop a reference-free framework capable of\n                  <jats:italic>de novo</jats:italic>\n                  discovery of mobile genetic elements, not currently available to our knowledge, and we use it to rediscover the known transposons in\n                  <jats:italic>Mycobacterium tuberculosis</jats:italic>\n                  , the causative agent of\n                  <jats:italic>tuberculosis</jats:italic>\n                  .\n                </jats:p>","journal":null,"year":null,"id":611759,"datarank":0.16479184330021646,"base_score":1.0986122886681096,"endowment":1.0986122886681096,"self_citation_contribution":0.16479184330021646,"citation_network_contribution":0.0,"self_endowment_contribution":0.16479184330021646,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":2,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":252038,"name":"Peter L. Wang","orcid":"0000-0001-9651-3860","position":1,"is_corresponding":false},{"id":558818,"name":"Julia Salzman","orcid":"0000-0001-7630-3436","position":2,"is_corresponding":false},{"id":12240,"name":"Jordi Abante","orcid":"0000-0003-4137-2858","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"DIVE: a reference-free statistical approach to diversity-generating &amp; mobile genetic element discovery","abstract":"<jats:p>\n                  Diversity-generating and mobile genetic elements are paramount to microbial and viral evolution and result in evolutionary leaps conferring novel phenotypes, such as antimicrobial resistance. State-of-the-art algorithms to detect these elements have many limitations, including reliance on reference genomes, assemblers, and heuristics, resulting in computational bottlenecks and limiting the scope of biological discoveries. Here we introduce DIVE, a new reference-free approach to overcome these limitations using information contained in sequencing reads alone. We show that DIVE has improved detection power compared to existing reference-based methods using simulations and real data. We use DIVE to rediscover and characterize the activity of known and novel elements and generate new biological hypotheses about the mobilome. Using DIVE we rediscover CRISPR and identify novel repeats, and we discover unannotated genetic hyper-variability hotspots in\n                  <jats:italic>Escherichia coli</jats:italic>\n                  and\n                  <jats:italic>Vibrio cholerae</jats:italic>\n                  . Building on DIVE, we develop a reference-free framework capable of\n                  <jats:italic>de novo</jats:italic>\n                  discovery of mobile genetic elements, not currently available to our knowledge, and we use it to rediscover the known transposons in\n                  <jats:italic>Mycobacterium tuberculosis</jats:italic>\n                  , the causative agent of\n                  <jats:italic>tuberculosis</jats:italic>\n                  .\n                </jats:p>","is_dataset_classified":null,"base_score":1.0986122886681096,"endowment":1.0986122886681096,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"21097893","pmcid":null,"openalex_id":"https://openalex.org/W4283026411","authors":[],"funders":[{"funder_name":"National Institutes of Health","grant_id":"5R35GM139517-05","title":"Computational- and experimental- driven discovery of splicing regulation and circRNA function"}],"total_grants":1,"fwci":null,"citation_percentile":null,"influential_citations":0,"citation_trend":[{"year":2022,"count":1},{"year":2023,"count":1}],"oa_status":"green","license":"CC BY","oa_locations":[{"url":"https://www.biorxiv.org/content/biorxiv/early/2022/06/16/2022.06.13.495703.full.pdf","host_type":"repository"},{"url":"https://www.biorxiv.org/content/biorxiv/early/2022/06/16/2022.06.13.495703.full.pdf","host_type":"repository"},{"url":"https://syndication.highwire.org/content/doi/10.1101/2022.06.13.495703","host_type":"publisher"},{"url":"https://doi.org/10.1101/2022.06.13.495703","host_type":"repository"},{"url":"https://doi.org/10.1186/s13059-023-03038-0","host_type":""},{"url":"https://pubmed.ncbi.nlm.nih.gov/37864197","host_type":""},{"url":"http://dx.doi.org/10.1186/s13059-023-03038-0","host_type":""},{"url":"https://doaj.org/article/d39810e741274db18bf0e3fcbafc668b","host_type":""}],"fields_of_study":["Genomics and Phylogenetic Studies","RNA and protein synthesis mechanisms","Evolution and Genetic Dynamics","0301 basic medicine","03 medical and health sciences"],"mesh_terms":[],"keywords":["Mobile genetic elements","Computational biology","Biology","Genome","Transposable element","Heuristics","CRISPR","Genetics","Computer science","Gene","Gene Transfer, Horizontal","Diversity-generating mechanisms","QH301-705.5","Integrative and conjugative elements","Method","Horizontal gene transfer","QH426-470","Interspersed Repetitive Sequences","DNA Transposable Elements","Biology (General)","Transposable elements"],"sdg_mappings":[{"sdg_number":0,"sdg_label":"Good health and well-being"}],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-01T22:20:16.763805Z","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":[]}