{"id":"https://openalex.org/W7214716732","doi":"https://doi.org/10.64898/2026.09.24.754018","title":"SCAR: Controlled mutations, ancient DNA damage, and fragmentation of fasta and fastq sequences","display_name":"SCAR: Controlled mutations, ancient DNA damage, and fragmentation of fasta and fastq sequences","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214716732","doi":"https://doi.org/10.64898/2026.09.24.754018"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.24.754018","doi":"https://doi.org/10.64898/2026.09.24.754018","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754018","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.24.754018.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.24.754018.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146301009","display_name":"Mads Hartmann","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mads Hartmann","raw_affiliation_strings":["Department of Health Technology, Section for Bioinformatics, Technical University of Denmark","\u00d8rsteds Plads, Building 345C, DK-2800 Kongens Lyngby, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Health Technology, Section for Bioinformatics, Technical University of Denmark","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"\u00d8rsteds Plads, Building 345C, DK-2800 Kongens Lyngby, Denmark","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036052678","display_name":"Michael V. Westbury","orcid":"https://orcid.org/0000-0003-0478-3930","observed_orcids":["https://orcid.org/0000-0003-0478-3930"]},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Michael V Westbury","raw_affiliation_strings":["Department of Health Technology, Section for Bioinformatics, Technical University of Denmark","\u00d8rsteds Plads, Building 345C, DK-2800 Kongens Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0003-0478-3930","affiliations":[{"raw_affiliation_string":"Department of Health Technology, Section for Bioinformatics, Technical University of Denmark","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"\u00d8rsteds Plads, Building 345C, DK-2800 Kongens Lyngby, Denmark","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5036052678"],"corresponding_institution_ids":["https://openalex.org/I96673099"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/synthetic-sequencing-data","display_name":"synthetic sequencing data","score":0.5910000205039978},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.7829999923706055},{"id":"https://openalex.org/keywords/read-mapping","display_name":"read mapping","score":0.8130000233650208},{"id":"https://openalex.org/keywords/heterozygosity","display_name":"heterozygosity","score":0.8880000114440918},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C191015642","wikidata":"https://www.wikidata.org/wiki/Q1132459","display_name":"Fragmentation (computing)","level":2,"score":0.7044000029563904},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5936999917030334},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5921000242233276},{"id":"https://openalex.org/C143589142","wikidata":"https://www.wikidata.org/wiki/Q2617554","display_name":"Loss of heterozygosity","level":4,"score":0.5544000267982483},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.5357000231742859},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4812999963760376},{"id":"https://openalex.org/C43759708","wikidata":"https://www.wikidata.org/wiki/Q3749256","display_name":"DNA fragmentation","level":4,"score":0.4641000032424927},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4122999906539917},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.40130001306533813},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3799999952316284},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.33730000257492065},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.26179999113082886},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.24.754018","doi":"https://doi.org/10.64898/2026.09.24.754018","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754018","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.24.754018.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.24.754018","doi":"https://doi.org/10.64898/2026.09.24.754018","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754018","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.24.754018.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322436","display_name":"Novo Nordisk","ror":"https://ror.org/0435rc536"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214716732.pdf","grobid_xml":"https://content.openalex.org/works/W7214716732.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2091705028","https://openalex.org/W2129034036","https://openalex.org/W2150163641","https://openalex.org/W2157539385","https://openalex.org/W2544029679","https://openalex.org/W3000431709","https://openalex.org/W3004804976","https://openalex.org/W4391463597","https://openalex.org/W4396921490","https://openalex.org/W4409629797","https://openalex.org/W4410816531","https://openalex.org/W7202132590","https://openalex.org/W7202367073","https://openalex.org/W7213529984"],"related_works":["https://openalex.org/W2103283541","https://openalex.org/W3048385873","https://openalex.org/W3090081181","https://openalex.org/W1987069789","https://openalex.org/W2997093135","https://openalex.org/W4384930820","https://openalex.org/W6945351954","https://openalex.org/W2150163641","https://openalex.org/W4294591302","https://openalex.org/W3040188334"],"abstract_inverted_index":{"Abstract":[0],"Summary":[1],"Controlled":[2],"modification":[3],"of":[4,63,72],"sequencing":[5],"data":[6],"is":[7,90,98,109],"important":[8],"for":[9],"reproducible":[10],"benchmarking,":[11],"particularly":[12],"when":[13],"evaluating":[14],"analyses":[15,67],"affected":[16],"by":[17],"read":[18,81],"fragmentation,":[19],"divergent":[20],"reference":[21],"genomes":[22],"and":[23,32,37,49,52,77,83,87,94],"ancient":[24],"DNA":[25],"damage.":[26],"SCAR":[27,89],"introduces":[28],"controlled":[29],"mutations,":[30],"fragmentation":[31],"position-specific":[33],"damage":[34],"into":[35],"FASTA":[36],"FASTQ":[38],"data.":[39],"All":[40],"features":[41],"can":[42,55],"be":[43,56],"used":[44],"separately":[45],"or":[46],"in":[47,92,106],"combination,":[48],"empirical":[50],"fragment-length":[51],"mismatch":[53],"profiles":[54],"supplied":[57],"to":[58],"closely":[59],"reproduce":[60],"the":[61,69,73,95],"properties":[62],"targeted":[64],"datasets.":[65],"Validation":[66],"showed":[68],"successful":[70],"implementation":[71],"requested":[74],"sequence":[75],"changes,":[76],"their":[78],"impact":[79],"on":[80],"mapping":[82],"heterozygosity":[84],"analyses.":[85],"Availability":[86],"Implementation":[88],"implemented":[91],"C++":[93],"latest":[96],"code":[97],"available":[99,119],"at":[100,111,113,120],"https://github.com/Madshartmann1/SCAR":[101],".":[102,122],"The":[103],"version":[104],"described":[105],"this":[107],"article":[108],"archived":[110],"Zenodo":[112],"https://doi.org/10.5281/zenodo.22789736":[114],",":[115],"with":[116],"validation":[117],"material":[118],"https://doi.org/10.5281/zenodo.21915766":[121]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-30T00:00:00"}
