{"id":"https://openalex.org/W7214333111","doi":"https://doi.org/10.64898/2026.09.19.750380","title":"nf-rare-var-assoc: a comprehensive genetic association pipeline with rich QC","display_name":"nf-rare-var-assoc: a comprehensive genetic association pipeline with rich QC","publication_year":2026,"publication_date":"2026-09-24","ids":{"openalex":"https://openalex.org/W7214333111","doi":"https://doi.org/10.64898/2026.09.19.750380"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.19.750380","doi":"https://doi.org/10.64898/2026.09.19.750380","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.19.750380","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/24/2026.09.19.750380.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/24/2026.09.19.750380.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032215788","display_name":"Piotr Suszynski","orcid":"https://orcid.org/0009-0001-0449-8761","observed_orcids":["https://orcid.org/0009-0001-0449-8761"]},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Piotr Suszy\u0144ski","raw_affiliation_strings":["Warsaw University of Technology"],"raw_orcid":"https://orcid.org/0009-0001-0449-8761","affiliations":[{"raw_affiliation_string":"Warsaw University of Technology","institution_ids":["https://openalex.org/I108403487"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079290300","display_name":"Tomasz Gambin","orcid":"https://orcid.org/0000-0002-0941-4571","observed_orcids":["https://orcid.org/0000-0002-0941-4571"]},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Tomasz Gambin","raw_affiliation_strings":["Warsaw University of Technology"],"raw_orcid":"https://orcid.org/0000-0002-0941-4571","affiliations":[{"raw_affiliation_string":"Warsaw University of Technology","institution_ids":["https://openalex.org/I108403487"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5032215788"],"corresponding_institution_ids":["https://openalex.org/I108403487"],"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/T11642","display_name":"Genomics and Rare Diseases","score":0.9218999743461609,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11642","display_name":"Genomics and Rare Diseases","score":0.9218999743461609,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.05790000036358833,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0052999998442828655,"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/genetic-association-testing","display_name":"genetic association testing","score":0.8289999961853027},{"id":"https://openalex.org/keywords/rare-diseases","display_name":"rare diseases","score":0.6460000276565552},{"id":"https://openalex.org/keywords/whole-exome-sequencing","display_name":"exome sequencing","score":0.9330000281333923},{"id":"https://openalex.org/keywords/data-quality-control","display_name":"data quality control","score":0.7390000224113464},{"id":"https://openalex.org/keywords/data-filtering","display_name":"data filtering","score":0.6650000214576721},{"id":"https://openalex.org/keywords/nextflow","display_name":"Nextflow","score":0.8420000076293945},{"id":"https://openalex.org/keywords/small-cohorts","display_name":"small cohorts","score":0.6340000033378601},{"id":"https://openalex.org/keywords/bioinformatics-pipeline","display_name":"bioinformatics pipeline","score":0.6850000023841858}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7387999892234802},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6097000241279602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5950999855995178},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5633000135421753},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.5187000036239624},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C186413461","wikidata":"https://www.wikidata.org/wiki/Q744727","display_name":"Genetic association","level":5,"score":0.4731999933719635},{"id":"https://openalex.org/C2983325608","wikidata":"https://www.wikidata.org/wiki/Q17084606","display_name":"Data association","level":3,"score":0.4429999887943268},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C2993807623","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genetic data","level":3,"score":0.36820000410079956},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.35030001401901245},{"id":"https://openalex.org/C2994538360","wikidata":"https://www.wikidata.org/wiki/Q774081","display_name":"Association test","level":5,"score":0.34200000762939453},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C10590036","wikidata":"https://www.wikidata.org/wiki/Q417664","display_name":"Exome","level":5,"score":0.32249999046325684},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3190000057220459},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C16671776","wikidata":"https://www.wikidata.org/wiki/Q5420592","display_name":"Exome sequencing","level":4,"score":0.2964000105857849},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C106208931","wikidata":"https://www.wikidata.org/wiki/Q1098876","display_name":"Genome-wide association study","level":5,"score":0.2599000036716461},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.19.750380","doi":"https://doi.org/10.64898/2026.09.19.750380","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.19.750380","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/24/2026.09.19.750380.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.19.750380","doi":"https://doi.org/10.64898/2026.09.19.750380","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.19.750380","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/24/2026.09.19.750380.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.5683000087738037}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214333111.pdf","grobid_xml":"https://content.openalex.org/works/W7214333111.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4411753936","https://openalex.org/W3135287178","https://openalex.org/W2280781077","https://openalex.org/W2065125274","https://openalex.org/W2626228265","https://openalex.org/W4307847968","https://openalex.org/W2510549946","https://openalex.org/W4223984061","https://openalex.org/W4294169796","https://openalex.org/W2968196002"],"abstract_inverted_index":{"Abstract":[0],"Genetic":[1],"association":[2,26,44,79,111,127,134],"analyses":[3,135],"of":[4,41,96,124],"exome":[5],"sequencing":[6],"data":[7,52,86,125],"pose":[8],"distinct":[9],"methodological":[10],"challenges":[11],"in":[12,18],"small":[13],"cohorts,":[14],"which":[15,81],"are":[16],"common":[17],"rare":[19],"disease":[20],"research.":[21],"Data":[22],"filtering":[23,87],"prior":[24],"to":[25,47,63,118,137],"testing":[27,112,128],"requires":[28,57],"particular":[29],"care,":[30],"especially":[31],"when":[32],"analyzing":[33],"datasets":[34],"generated":[35],"under":[36],"different":[37],"study":[38],"designs.":[39],"Most":[40],"current":[42],"genetic":[43,78],"tools":[45,105],"need":[46],"be":[48],"integrated":[49],"into":[50],"complex":[51],"processing":[53],"pipelines,":[54],"whose":[55],"implementation":[56],"technical":[58,141],"expertise":[59],"and":[60,88,109,114,129],"is":[61],"prone":[62],"error.":[64],"To":[65],"alleviate":[66],"mentioned":[67],"issues":[68],"we":[69],"built":[70],"a":[71,93],"comprehensive,":[72],"high":[73],"performance":[74],"Nextflow":[75],"workflow":[76],"for":[77],"testing,":[80],"includes":[82],"all":[83],"commonly":[84],"performed":[85],"preparation":[89],"steps,":[90],"controlled":[91],"by":[92],"rich":[94],"set":[95],"modifiable":[97],"parameters.":[98],"We":[99],"compared":[100],"our":[101,116],"software":[102],"against":[103],"existing":[104],"incorporating":[106],"quality":[107],"control":[108],"aggregated":[110],"steps":[113],"found":[115],"solution":[117],"offer":[119],"the":[120],"most":[121],"complete":[122],"suite":[123],"preparation,":[126],"reporting":[130],"modules,":[131],"making":[132],"small-cohort":[133],"accessible":[136],"teams":[138],"with":[139],"limited":[140],"expertise.":[142]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-26T00:00:00"}