{"id":"https://openalex.org/W7154083460","doi":"https://doi.org/10.1093/bioinformatics/btag182","title":"Harvesting more reads from single-cell combinatorial barcoding data with <i>scarecrow</i>","display_name":"Harvesting more reads from single-cell combinatorial barcoding data with <i>scarecrow</i>","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7154083460","doi":"https://doi.org/10.1093/bioinformatics/btag182"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag182","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag182","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btag182","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043379066","display_name":"David Wragg","orcid":"https://orcid.org/0000-0002-4007-953X"},"institutions":[{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Wragg","raw_affiliation_strings":["Institute of Medical Sciences , University of Aberdeen, Foresterhill , Aberdeen, AB25 2ZD,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Medical Sciences , University of Aberdeen, Foresterhill , Aberdeen, AB25 2ZD,","institution_ids":["https://openalex.org/I195460627"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019518267","display_name":"Eunchai Kang","orcid":"https://orcid.org/0000-0001-6884-622X"},"institutions":[{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eunchai Kang","raw_affiliation_strings":["Institute of Medical Sciences , University of Aberdeen, Foresterhill , Aberdeen, AB25 2ZD,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Medical Sciences , University of Aberdeen, Foresterhill , Aberdeen, AB25 2ZD,","institution_ids":["https://openalex.org/I195460627"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133489670","display_name":"M D Morgan","orcid":null},"institutions":[{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Michael D Morgan","raw_affiliation_strings":["Institute of Medical Sciences , University of Aberdeen, Foresterhill , Aberdeen, AB25 2ZD,"],"raw_orcid":"https://orcid.org/0000-0003-0757-0711","affiliations":[{"raw_affiliation_string":"Institute of Medical Sciences , University of Aberdeen, Foresterhill , Aberdeen, AB25 2ZD,","institution_ids":["https://openalex.org/I195460627"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5133489670"],"corresponding_institution_ids":["https://openalex.org/I195460627"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48754259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.95660001039505,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.95660001039505,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.02800000086426735,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/barcode","display_name":"Barcode","score":0.9890000224113464},{"id":"https://openalex.org/keywords/dna-barcoding","display_name":"DNA barcoding","score":0.682200014591217},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6315000057220459},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5572999715805054},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42419999837875366},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.3262999951839447}],"concepts":[{"id":"https://openalex.org/C2776841711","wikidata":"https://www.wikidata.org/wiki/Q856","display_name":"Barcode","level":2,"score":0.9890000224113464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.710099995136261},{"id":"https://openalex.org/C141732470","wikidata":"https://www.wikidata.org/wiki/Q1154642","display_name":"DNA barcoding","level":2,"score":0.682200014591217},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6315000057220459},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5572999715805054},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40610000491142273},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3880999982357025},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.350600004196167},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.3262999951839447},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.27799999713897705},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/bioinformatics/btag182","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag182","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag182","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag182","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5331466997","display_name":null,"funder_award_id":"RG/R2/232125","funder_id":"https://openalex.org/F4320320006","funder_display_name":"Royal Society"}],"funders":[{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2794083495","https://openalex.org/W3145635506","https://openalex.org/W4394735445","https://openalex.org/W4394757126","https://openalex.org/W4405409733","https://openalex.org/W4406439270"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Summary":[1],"Combinatorial":[2],"barcoding":[3,19,30,127],"technologies":[4],"for":[5,158,234],"single-cell":[6,125,215],"nucleotide":[7,82,175],"sequencing,":[8],"such":[9],"as":[10,166],"split-pool":[11],"ligation":[12],"protocols,":[13],"involve":[14],"sequential":[15],"rounds":[16],"of":[17,28,69,121,137,180,240],"cell":[18,72],"to":[20,38,71,109,139,148,165,173,188],"uniquely":[21],"tag":[22],"individual":[23],"cells.":[24],"The":[25],"rapid":[26],"adoption":[27],"combinatorial":[29,126],"in":[31,36,48,153,195,223,247],"recent":[32],"years":[33],"is":[34,218,255],"due":[35],"part":[37],"its":[39],"scalability":[40],"across":[41],"cells":[42],"and":[43,117,177,190,212,225,252,261],"samples.":[44],"However,":[45],"small":[46],"shifts":[47],"barcode":[49,60,142,151,193,204],"positions":[50,87],"within":[51,88],"sequencing":[52,122,198],"reads":[53,70,95,123,138],"caused":[54],"by":[55],"technical":[56],"artifacts,":[57],"e.g.":[58],"during":[59,103],"incorporation":[61],"or":[62,98],"synthesis,":[63],"can":[64,244],"impact":[65],"the":[66,119,178,241,248],"accurate":[67],"assignment":[68],"barcodes.":[73],"Existing":[74],"processing":[75,106],"tools":[76],"typically":[77],"assume":[78],"barcodes":[79,100],"contain":[80],"fixed-length":[81],"sequences":[83,152],"located":[84],"at":[85],"fixed":[86],"reads,":[89],"overlooking":[90],"any":[91],"positional":[92,159],"variability.":[93],"Consequently,":[94],"containing":[96],"truncated":[97],"mispositioned":[99],"are":[101,145,170,185],"discarded":[102],"initial":[104,183],"data":[105,111,210],"steps":[107],"leading":[108],"significant":[110],"loss.":[112],"To":[113],"solve":[114],"this":[115],"limitation":[116],"maximize":[118],"retention":[120],"from":[124],"experiments,":[128],"we":[129,163],"introduce":[130],"scarecrow.":[131],"This":[132],"tool":[133],"screens":[134],"a":[135,161],"subsample":[136],"generate":[140],"position-specific":[141],"profiles,":[143],"which":[144],"then":[146,171],"used":[147,187],"flexibly":[149],"identify":[150],"each":[154],"read":[155],"whilst":[156],"accounting":[157],"errors,":[160],"phenomenon":[162],"refer":[164],"\u201cjitter\u201d.":[167],"Barcode":[168],"matches":[169],"prioritized":[172],"minimize":[174],"mismatches":[176],"degree":[179],"jitter.":[181],"These":[182],"profiles":[184],"subsequently":[186],"extract":[189],"error":[191,205],"correct":[192],"combinations":[194],"high":[196],"throughput":[197],"libraries.":[199],"By":[200],"incorporating":[201],"jitter":[202],"into":[203],"correction,":[206],"scarecrow":[207,242],"enables":[208],"greater":[209],"recovery":[211],"improved":[213],"downstream":[214],"analyses.":[216],"Scarecrow":[217,254],"fully":[219],"open":[220],"access,":[221],"implemented":[222],"Python,":[224],"generates":[226],"output":[227],"files":[228],"using":[229],"standardized":[230],"sequence":[231],"file":[232],"formats":[233],"maximal":[235],"interoperability.":[236],"A":[237],"detailed":[238],"explanation":[239],"workflow":[243],"be":[245],"found":[246],"supplementary":[249],"materials.":[250],"Availability":[251],"implementation":[253],"freely":[256],"available":[257],"on":[258],"GitHub":[259],"https://github.com/MorganResearchLab/scarecrow":[260],"Zenodo":[262],"https://doi.org/10.5281/zenodo.18621784.":[263]},"counts_by_year":[],"updated_date":"2026-06-18T08:10:14.011955","created_date":"2026-04-14T00:00:00"}