{"id":"https://openalex.org/W7215115652","doi":"https://doi.org/10.64898/2026.09.25.754512","title":"EXCON: a scalable, reproducible Nextflow pipeline for CAFE-based gene EXpansion and CONtraction analysis","display_name":"EXCON: a scalable, reproducible Nextflow pipeline for CAFE-based gene EXpansion and CONtraction analysis","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7215115652","doi":"https://doi.org/10.64898/2026.09.25.754512"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.25.754512","doi":"https://doi.org/10.64898/2026.09.25.754512","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.25.754512","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/01/2026.09.25.754512.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","license_id":"https://openalex.org/licenses/cc-by","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/2026/10/01/2026.09.25.754512.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056583523","display_name":"Christopher D. R. Wyatt","orcid":"https://orcid.org/0000-0001-8033-2213","observed_orcids":["https://orcid.org/0000-0001-8033-2213"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Christopher Wyatt","raw_affiliation_strings":["Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, Gower Street, University College London, London WC1E 6BT, UK"],"raw_orcid":"https://orcid.org/0000-0001-8033-2213","affiliations":[{"raw_affiliation_string":"Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, Gower Street, University College London, London WC1E 6BT, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147446054","display_name":"Fernando Duarte Frutos","orcid":"https://orcid.org/0009-0003-2093-1734","observed_orcids":["https://orcid.org/0009-0003-2093-1734"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fernando Duarte","raw_affiliation_strings":["Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, Gower Street, University College London, London WC1E 6BT, UK"],"raw_orcid":"https://orcid.org/0009-0003-2093-1734","affiliations":[{"raw_affiliation_string":"Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, Gower Street, University College London, London WC1E 6BT, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077994638","display_name":"Alexandra Cerqueira de Araujo","orcid":"https://orcid.org/0000-0002-9273-9886","observed_orcids":["https://orcid.org/0000-0002-9273-9886"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexandra Cerqueira De Araujo","raw_affiliation_strings":["Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, Gower Street, University College London, London WC1E 6BT, UK"],"raw_orcid":"https://orcid.org/0000-0002-9273-9886","affiliations":[{"raw_affiliation_string":"Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, Gower Street, University College London, London WC1E 6BT, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054272673","display_name":"Simon Murray","orcid":"https://orcid.org/0009-0007-0787-1051","observed_orcids":["https://orcid.org/0009-0007-0787-1051"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Murray","raw_affiliation_strings":["Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, Gower Street, University College London, London WC1E 6BT, UK"],"raw_orcid":"https://orcid.org/0009-0007-0787-1051","affiliations":[{"raw_affiliation_string":"Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, Gower Street, University College London, London WC1E 6BT, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010515756","display_name":"C\u00edntia Akemi Oi","orcid":"https://orcid.org/0000-0002-3682-8219","observed_orcids":["https://orcid.org/0000-0002-3682-8219"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cintia Oi","raw_affiliation_strings":["Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, Gower Street, University College London, London WC1E 6BT, UK"],"raw_orcid":"https://orcid.org/0000-0002-3682-8219","affiliations":[{"raw_affiliation_string":"Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, Gower Street, University College London, London WC1E 6BT, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056925004","display_name":"Seirian Sumner","orcid":"https://orcid.org/0000-0003-0213-2018","observed_orcids":["https://orcid.org/0000-0003-0213-2018"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Seirian Sumner","raw_affiliation_strings":["Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, Gower Street, University College London, London WC1E 6BT, UK"],"raw_orcid":"https://orcid.org/0000-0003-0213-2018","affiliations":[{"raw_affiliation_string":"Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, Gower Street, University College London, London WC1E 6BT, UK","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5056583523"],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9907000064849854,"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":0.9907000064849854,"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.006300000008195639,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.0007999999797903001,"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/gene-family-expansion-and-contraction","display_name":"gene family expansion and contraction","score":0.9539999961853027},{"id":"https://openalex.org/keywords/coffee-shop","display_name":"coffee shop","score":0.8209999799728394},{"id":"https://openalex.org/keywords/nextflow-pipeline","display_name":"Nextflow pipeline","score":0.7070000171661377},{"id":"https://openalex.org/keywords/ortholog-identification","display_name":"ortholog identification","score":0.527999997138977},{"id":"https://openalex.org/keywords/gene-ontology-enrichment","display_name":"gene ontology enrichment","score":0.7200000286102295},{"id":"https://openalex.org/keywords/primate-genomics","display_name":"primate genomics","score":0.7160000205039978},{"id":"https://openalex.org/keywords/orthogroups","display_name":"orthogroups","score":0.6010000109672546}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7095000147819519},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5570999979972839},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5339000225067139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5246000289916992},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.5216000080108643},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.47029998898506165},{"id":"https://openalex.org/C5911399","wikidata":"https://www.wikidata.org/wiki/Q2278983","display_name":"Gene family","level":4,"score":0.45649999380111694},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.44040000438690186},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C105176652","wikidata":"https://www.wikidata.org/wiki/Q1147112","display_name":"Comparative genomics","level":5,"score":0.37439998984336853},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2888000011444092},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.2605000138282776},{"id":"https://openalex.org/C2778113609","wikidata":"https://www.wikidata.org/wiki/Q10897","display_name":"Lambda","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C161078062","wikidata":"https://www.wikidata.org/wiki/Q1068690","display_name":"Functional genomics","level":5,"score":0.2563000023365021},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C64331007","wikidata":"https://www.wikidata.org/wiki/Q831672","display_name":"Spanning tree","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.25.754512","doi":"https://doi.org/10.64898/2026.09.25.754512","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.25.754512","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/01/2026.09.25.754512.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.25.754512","doi":"https://doi.org/10.64898/2026.09.25.754512","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.25.754512","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/01/2026.09.25.754512.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322308","display_name":"KU Leuven","ror":"https://ror.org/05f950310"},{"id":"https://openalex.org/F4320332167","display_name":"Directorate for Biological Sciences","ror":"https://ror.org/001xhss06"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215115652.pdf","grobid_xml":"https://content.openalex.org/works/W7215115652.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W6894056309","https://openalex.org/W6944546543","https://openalex.org/W6949985536","https://openalex.org/W7163984798","https://openalex.org/W7203822423"],"related_works":["https://openalex.org/W7100281561","https://openalex.org/W2122821321","https://openalex.org/W6968985702","https://openalex.org/W2791084997","https://openalex.org/W3113087152","https://openalex.org/W2804606599","https://openalex.org/W4386209610","https://openalex.org/W3194245924","https://openalex.org/W2143578996","https://openalex.org/W7098884558"],"abstract_inverted_index":{"Abstract":[0],"Gene":[1],"family":[2,38,75],"expansion":[3],"and":[4,51,70,84,98,103,107,118,121,138],"contraction":[5],"analysis":[6,87],"is":[7,26,176],"a":[8,42,90,131,149],"commonly":[9],"used":[10],"approach":[11],"in":[12,36],"evolutionary":[13,19],"comparative":[14],"genomics":[15],"to":[16,33,130],"identify":[17],"lineage-specific":[18],"pressures":[20],"on":[21],"gene":[22,37,74,146,153],"copy/family":[23],"number.":[24],"CAFE":[25,116],"one":[27],"of":[28,45,167],"the":[29,140,164,168],"most":[30],"popular":[31],"tools":[32],"measure":[34],"changes":[35],"size,":[39],"but":[40],"requires":[41,108],"high":[43,123],"level":[44],"bioinformatics":[46],"expertise,":[47],"manual":[48],"parameter":[49],"tuning":[50],"preprocessing.":[52],"Here":[53],"we":[54],"present":[55],"EXCON,":[56],"an":[57],"automated,":[58],"Eco-Flow":[59],"community-developed":[60],"Nextflow":[61],"pipeline":[62,113,141],"that":[63],"integrates":[64],"NCBI":[65],"genome":[66,96],"download,":[67],"annotation":[68],"quality":[69],"format":[71],"pre-processing,":[72],"orthologous":[73],"identification":[76],"(Orthofinder),":[77],"ultrametric":[78],"tree":[79],"formatting,":[80],"birth-death":[81],"modelling":[82],"(CAFE),":[83],"GO":[85],"enrichment":[86],"(eggNOG-mapper/TopGO)":[88],"into":[89],"single,":[91],"portable":[92],"workflow.":[93],"EXCON":[94,175],"accepts":[95],"assemblies":[97],"annotations,":[99],"supports":[100],"local,":[101],"HPC":[102],"cloud-based":[104],"computing":[105],"environments,":[106],"minimal":[109],"user":[110],"configuration.":[111],"The":[112],"auto-selects":[114],"appropriate":[115],"lambda":[117],"error":[119],"models,":[120],"separates":[122],"variance":[124],"orthogroups":[125],"for":[126],"separate":[127],"treatment.":[128],"Applied":[129],"24-species":[132],"primate":[133],"dataset":[134],"spanning":[135],"Catarrhini,":[136],"Platyrrhini":[137],"Strepsirrhini,":[139],"identified":[142],"358":[143],"rapidly":[144],"evolving":[145],"families,":[147],"including":[148],"DUX":[150],"(double":[151],"homeobox)":[152],"showing":[154],"repeated,":[155],"independent":[156],"copy-number":[157],"turnover":[158],"across":[159],"multiple":[160],"lineages,":[161],"consistent":[162],"with":[163],"known":[165],"instability":[166],"D4Z4":[169],"macrosatellite":[170],"repeat":[171],"it":[172],"resides":[173],"in.":[174],"freely":[177],"available":[178],"at":[179],"https://github.com/Eco-Flow/excon":[180],".":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-02T00:00:00"}
