{"id":"https://openalex.org/W4385564401","doi":"https://doi.org/10.1093/bioinformatics/btad488","title":"SHEPHARD: a modular and extensible software architecture for analyzing and annotating large protein datasets","display_name":"SHEPHARD: a modular and extensible software architecture for analyzing and annotating large protein datasets","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385564401","doi":"https://doi.org/10.1093/bioinformatics/btad488","pmid":"https://pubmed.ncbi.nlm.nih.gov/37540173"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad488","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad488","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad488/51038856/btad488.pdf","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad488/51038856/btad488.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049393042","display_name":"Garrett M. Ginell","orcid":"https://orcid.org/0000-0001-6511-5480"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Garrett M Ginell","raw_affiliation_strings":["Center for Biomolecular Condensates, Washington University in St. Louis , 1 Brookings Drive , Saint Louis, MO 63130, United States","Department of Biochemistry and Molecular Biophysics, Washington University School of Medicine , 660 South Euclid Avenue , Saint Louis, MO 63110, United States"],"affiliations":[{"raw_affiliation_string":"Center for Biomolecular Condensates, Washington University in St. Louis , 1 Brookings Drive , Saint Louis, MO 63130, United States","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Department of Biochemistry and Molecular Biophysics, Washington University School of Medicine , 660 South Euclid Avenue , Saint Louis, MO 63110, United States","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062543815","display_name":"Aidan J. Flynn","orcid":"https://orcid.org/0000-0003-0607-9381"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aidan J Flynn","raw_affiliation_strings":["Center for Biomolecular Condensates, Washington University in St. Louis , 1 Brookings Drive , Saint Louis, MO 63130, United States","Department of Biochemistry and Molecular Biophysics, Washington University School of Medicine , 660 South Euclid Avenue , Saint Louis, MO 63110, United States"],"affiliations":[{"raw_affiliation_string":"Center for Biomolecular Condensates, Washington University in St. Louis , 1 Brookings Drive , Saint Louis, MO 63130, United States","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Department of Biochemistry and Molecular Biophysics, Washington University School of Medicine , 660 South Euclid Avenue , Saint Louis, MO 63110, United States","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054483983","display_name":"Alex S. Holehouse","orcid":"https://orcid.org/0000-0002-4155-5729"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex S Holehouse","raw_affiliation_strings":["Center for Biomolecular Condensates, Washington University in St. Louis , 1 Brookings Drive , Saint Louis, MO 63130, United States","Department of Biochemistry and Molecular Biophysics, Washington University School of Medicine , 660 South Euclid Avenue , Saint Louis, MO 63110, United States"],"affiliations":[{"raw_affiliation_string":"Center for Biomolecular Condensates, Washington University in St. Louis , 1 Brookings Drive , Saint Louis, MO 63130, United States","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Department of Biochemistry and Molecular Biophysics, Washington University School of Medicine , 660 South Euclid Avenue , Saint Louis, MO 63110, United States","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049393042"],"corresponding_institution_ids":["https://openalex.org/I204465549"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.4647,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79698383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"39","issue":"8","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.9983000159263611,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.7905799150466919},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6567603349685669},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5874300599098206},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5531203746795654},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.539264976978302},{"id":"https://openalex.org/keywords/proteome","display_name":"Proteome","score":0.487619549036026},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3742522895336151},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3420878052711487},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.32892653346061707},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.2738388776779175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17204061150550842},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.14686664938926697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7905799150466919},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6567603349685669},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5874300599098206},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5531203746795654},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.539264976978302},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.487619549036026},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3742522895336151},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3420878052711487},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32892653346061707},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2738388776779175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17204061150550842},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14686664938926697}],"mesh":[{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btad488","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad488","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad488/51038856/btad488.pdf","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"},{"id":"pmid:37540173","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37540173","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10423030","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10423030","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10423030/pdf/btad488.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:digitalcommons.wustl.edu:oa_4-3130","is_oa":true,"landing_page_url":"https://digitalcommons.wustl.edu/oa_4/2133","pdf_url":null,"source":{"id":"https://openalex.org/S4306400764","display_name":"Digital Commons@Becker (Washington University School of Medicine)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I204465549","host_organization_name":"Washington University in St. Louis","host_organization_lineage":["https://openalex.org/I204465549"],"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":"2020-Current year OA Pubs","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad488","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad488","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad488/51038856/btad488.pdf","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/G1391377831","display_name":null,"funder_award_id":"2213983","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3972398431","display_name":null,"funder_award_id":"2213983","funder_id":"https://openalex.org/F4320337398","funder_display_name":"Division of Biological Infrastructure"},{"id":"https://openalex.org/G5893828390","display_name":null,"funder_award_id":"2128068","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","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"},{"id":"https://openalex.org/F4320307333","display_name":"Longer Life Foundation","ror":"https://ror.org/02kesxz96"},{"id":"https://openalex.org/F4320337398","display_name":"Division of Biological Infrastructure","ror":"https://ror.org/04qn9mx93"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385564401.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1934555946","https://openalex.org/W1972376083","https://openalex.org/W2028927305","https://openalex.org/W2102025585","https://openalex.org/W2170892735","https://openalex.org/W2425405879","https://openalex.org/W2739999456","https://openalex.org/W2905220927","https://openalex.org/W2944831967","https://openalex.org/W2981408675","https://openalex.org/W3093315678","https://openalex.org/W3129991888","https://openalex.org/W3156051371","https://openalex.org/W3183475563","https://openalex.org/W3194158938","https://openalex.org/W4220685469","https://openalex.org/W4220875218","https://openalex.org/W4221129295","https://openalex.org/W4226201541","https://openalex.org/W4280512557","https://openalex.org/W4384820649"],"related_works":["https://openalex.org/W4281781478","https://openalex.org/W4323036830","https://openalex.org/W1892467659","https://openalex.org/W1906486629","https://openalex.org/W4318619745","https://openalex.org/W3021560500","https://openalex.org/W2166247150","https://openalex.org/W2951166193","https://openalex.org/W2995130350","https://openalex.org/W2065246746"],"abstract_inverted_index":{"We":[0],"provided":[1],"SHEPHARD":[2],"as":[3,11],"both":[4],"a":[5,12,17],"stand-alone":[6],"software":[7],"package":[8],"(https://github.com/holehouse-lab/shephard),":[9],"and":[10],"Google":[13],"Colab":[14],"notebook":[15],"with":[16],"collection":[18],"of":[19],"precomputed":[20],"proteome-wide":[21],"annotations":[22],"(https://github.com/holehouse-lab/shephard-colab).":[23]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
