{"id":"https://openalex.org/W4404050643","doi":"https://doi.org/10.1101/2024.11.01.621607","title":"Squeakuences: a portable tool for formatting \u2018squeaky-clean\u2019 sequences to eliminate bioinformatic software incompatibilities","display_name":"Squeakuences: a portable tool for formatting \u2018squeaky-clean\u2019 sequences to eliminate bioinformatic software incompatibilities","publication_year":2024,"publication_date":"2024-11-03","ids":{"openalex":"https://openalex.org/W4404050643","doi":"https://doi.org/10.1101/2024.11.01.621607"},"language":"en","primary_location":{"id":"doi:10.1101/2024.11.01.621607","doi":"https://doi.org/10.1101/2024.11.01.621607","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.11.01.621607","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2024/11/08/2024.11.01.621607.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/2024/11/08/2024.11.01.621607.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109760478","display_name":"Linnea E Lane","orcid":"https://orcid.org/0009-0001-4154-806X","observed_orcids":["https://orcid.org/0009-0001-4154-806X"]},"institutions":[{"id":"https://openalex.org/I53835047","display_name":"Oregon State University Cascades","ror":"https://ror.org/00tngcb91","country_code":"US","type":"education","lineage":["https://openalex.org/I53835047"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linnea E Lane","raw_affiliation_strings":["Oregon State University-Cascades, Biology Program","Oregon State University-Cascades, Computer Science Program"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University-Cascades, Biology Program","institution_ids":["https://openalex.org/I53835047"]},{"raw_affiliation_string":"Oregon State University-Cascades, Computer Science Program","institution_ids":["https://openalex.org/I53835047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114942101","display_name":"Ashley N Doerfler","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I53835047","display_name":"Oregon State University Cascades","ror":"https://ror.org/00tngcb91","country_code":"US","type":"education","lineage":["https://openalex.org/I53835047"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashley N Doerfler","raw_affiliation_strings":["Oregon State University-Cascades, Biology Program","Oregon State University-Cascades, Computer Science Program"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University-Cascades, Biology Program","institution_ids":["https://openalex.org/I53835047"]},{"raw_affiliation_string":"Oregon State University-Cascades, Computer Science Program","institution_ids":["https://openalex.org/I53835047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106355980","display_name":"Luna A L\u2019Argent","orcid":"https://orcid.org/0000-0001-8249-2712","observed_orcids":["https://orcid.org/0000-0001-8249-2712"]},"institutions":[{"id":"https://openalex.org/I53835047","display_name":"Oregon State University Cascades","ror":"https://ror.org/00tngcb91","country_code":"US","type":"education","lineage":["https://openalex.org/I53835047"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luna A L\u2019Argent","raw_affiliation_strings":["Oregon State University-Cascades, Biochemistry and Molecular Biology Program"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University-Cascades, Biochemistry and Molecular Biology Program","institution_ids":["https://openalex.org/I53835047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114942103","display_name":"Emily Touchette","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I53835047","display_name":"Oregon State University Cascades","ror":"https://ror.org/00tngcb91","country_code":"US","type":"education","lineage":["https://openalex.org/I53835047"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emily Touchette","raw_affiliation_strings":["Oregon State University-Cascades, Biology Program"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University-Cascades, Biology Program","institution_ids":["https://openalex.org/I53835047"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bronson Mills","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I53835047","display_name":"Oregon State University Cascades","ror":"https://ror.org/00tngcb91","country_code":"US","type":"education","lineage":["https://openalex.org/I53835047"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bronson Mills","raw_affiliation_strings":["Oregon State University-Cascades, Biology Program"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University-Cascades, Biology Program","institution_ids":["https://openalex.org/I53835047"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jessika Bryant","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I53835047","display_name":"Oregon State University Cascades","ror":"https://ror.org/00tngcb91","country_code":"US","type":"education","lineage":["https://openalex.org/I53835047"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jessika Bryant","raw_affiliation_strings":["Oregon State University-Cascades, Biology Program"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University-Cascades, Biology Program","institution_ids":["https://openalex.org/I53835047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108802208","display_name":"Savannah N Roller","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I53835047","display_name":"Oregon State University Cascades","ror":"https://ror.org/00tngcb91","country_code":"US","type":"education","lineage":["https://openalex.org/I53835047"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Savannah N Roller","raw_affiliation_strings":["Oregon State University-Cascades, Biochemistry and Molecular Biology Program"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University-Cascades, Biochemistry and Molecular Biology Program","institution_ids":["https://openalex.org/I53835047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034882785","display_name":"Evan S. Forsythe","orcid":"https://orcid.org/0000-0002-3865-2245","observed_orcids":["https://orcid.org/0000-0002-3865-2245"]},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]},{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]},{"id":"https://openalex.org/I53835047","display_name":"Oregon State University Cascades","ror":"https://ror.org/00tngcb91","country_code":"US","type":"education","lineage":["https://openalex.org/I53835047"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Evan S Forsythe","raw_affiliation_strings":["Oregon State University, Department of Integrative Biology","Oregon State University-Cascades, Biochemistry and Molecular Biology Program","Oregon State University-Cascades, Biology Program","University of Arizona"],"raw_orcid":"https://orcid.org/0000-0002-3865-2245","affiliations":[{"raw_affiliation_string":"Oregon State University, Department of Integrative Biology","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"Oregon State University-Cascades, Biochemistry and Molecular Biology Program","institution_ids":["https://openalex.org/I53835047"]},{"raw_affiliation_string":"Oregon State University-Cascades, Biology Program","institution_ids":["https://openalex.org/I53835047"]},{"raw_affiliation_string":"University of Arizona","institution_ids":["https://openalex.org/I138006243"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034882785"],"corresponding_institution_ids":["https://openalex.org/I131249849","https://openalex.org/I138006243","https://openalex.org/I53835047"],"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":0.9839000105857849,"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":0.9839000105857849,"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":0.00989999994635582,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.00559999980032444,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/command-line-tool","display_name":"command-line tool","score":0.6159999966621399},{"id":"https://openalex.org/keywords/phylogenetics","display_name":"phylogenetics","score":0.5920000076293945},{"id":"https://openalex.org/keywords/genome-annotation","display_name":"genome annotation","score":0.9480000138282776},{"id":"https://openalex.org/keywords/genome-analysis","display_name":"genome analysis","score":0.859000027179718},{"id":"https://openalex.org/keywords/metadata-tracking","display_name":"metadata tracking","score":0.5460000038146973},{"id":"https://openalex.org/keywords/python-script","display_name":"Python script","score":0.382999986410141}],"concepts":[{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.9316352605819702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6005608439445496},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5844564437866211},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4077269434928894},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3719632625579834},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34606441855430603}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/2024.11.01.621607","doi":"https://doi.org/10.1101/2024.11.01.621607","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.11.01.621607","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2024/11/08/2024.11.01.621607.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:10.1101/2024.11.01.621607","doi":"https://doi.org/10.1101/2024.11.01.621607","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.11.01.621607","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2024/11/08/2024.11.01.621607.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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G425194367","display_name":"RESEARCH-PGR: Illuminating the Plant Protein Interactome with Genome-wide Signatures of Coevolution","funder_award_id":"2114641","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404050643.pdf","grobid_xml":"https://content.openalex.org/works/W4404050643.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2128880918","https://openalex.org/W2949460346"],"related_works":["https://openalex.org/W2184102084","https://openalex.org/W2308359027","https://openalex.org/W1526952949","https://openalex.org/W1983603485","https://openalex.org/W3157535213","https://openalex.org/W2529838505","https://openalex.org/W2735888489","https://openalex.org/W2341728059","https://openalex.org/W2949460346","https://openalex.org/W3007499863"],"abstract_inverted_index":{"Abstract":[0],"Computational":[1],"analysis":[2,112],"of":[3,9,17,28,107,140,158],"biological":[4],"sequences":[5,159],"is":[6,181],"the":[7,108,138,146,156],"cornerstone":[8],"modern":[10],"bioinformatics":[11],"research.":[12],"Complex":[13],"processing":[14,132],"and":[15,26,35,60,72,83,97,133,150,172],"interpretation":[16],"data":[18,144],"often":[19],"entails":[20],"multi-step":[21],"workflows.":[22],"The":[23,119],"specific":[24],"requirements":[25],"limitations":[27],"individual":[29,131],"applications":[30,66],"can":[31,121],"require":[32],"laborious":[33],"reformatting":[34],"piecemeal":[36],"\u2018data-wrangling\u2019":[37],"to":[38,58,116,129,169],"produce":[39],"a":[40,47,53,77,103],"satisfactory":[41],"input":[42],"for":[43,65,111],"each":[44],"step":[45],"in":[46,76,88],"pipeline.":[48],"We":[49,136,166],"present":[50],"Squeakuences":[51,81,101,123,141,168,179],",":[52],"command":[54],"line":[55],"tool":[56],"developed":[57],"simplify":[59],"automate":[61],"FASTA":[62],"file":[63,110,164],"preparation":[64],"such":[67,91],"as":[68,92],"phylogenetics,":[69],"gene":[70],"annotation,":[71],"genome":[73,149],"analysis.":[74],"Implemented":[75],"lightweight":[78],"Python":[79],"script,":[80],"identifies":[82],"removes":[84],"potentially":[85],"problematic":[86],"elements":[87],"sequence":[89,109,177],"identifiers,":[90],"non-alphanumeric":[93],"characters,":[94],"white":[95],"space,":[96],"excessive":[98],"character":[99],"count.":[100],"outputs":[102],"new":[104],"clean":[105],"version":[106],"alongside":[113],"metadata":[114],"files":[115],"track":[117],"changes.":[118],"user":[120],"customize":[122],"\u2019":[124],"behavior":[125],"using":[126],"optional":[127],"arguments":[128],"meet":[130],"formatting":[134],"requirements.":[135],"tested":[137],"performance":[139],"on":[142],"molecular":[143],"from":[145],"human":[147],"reference":[148],"found":[151],"that":[152],"runtime":[153],"correlates":[154],"with":[155,163],"number":[157],"processed":[160],"but":[161],"not":[162],"size.":[165],"expect":[167],"save":[170],"time":[171],"manual":[173],"effort":[174],"when":[175],"analyzing":[176],"data.":[178],"code":[180],"freely":[182],"available":[183],"at":[184],"https://github.com/EvanForsythe/Squeakuences":[185],".":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2024-11-05T00:00:00"}
