{"id":"https://openalex.org/W4408068002","doi":"https://doi.org/10.1186/s12859-025-06079-3","title":"PyPropel: a Python-based tool for efficiently processing and characterising protein data","display_name":"PyPropel: a Python-based tool for efficiently processing and characterising protein data","publication_year":2025,"publication_date":"2025-03-01","ids":{"openalex":"https://openalex.org/W4408068002","doi":"https://doi.org/10.1186/s12859-025-06079-3","pmid":"https://pubmed.ncbi.nlm.nih.gov/40025421"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-025-06079-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06079-3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06079-3","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06079-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078691732","display_name":"Jianfeng Sun","orcid":"https://orcid.org/0000-0002-1274-5080"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210146357","display_name":"Oxford BioMedica (United Kingdom)","ror":"https://ror.org/03dp0vf82","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210146357"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianfeng Sun","raw_affiliation_strings":["Botnar Research Centre, University of Oxford, Headington, Oxford, OX3 7LD, UK. jianfeng.sun@ndorms.ox.ac.uk","Botnar Research Centre, University of Oxford, Headington, Oxford, OX3 7LD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Botnar Research Centre, University of Oxford, Headington, Oxford, OX3 7LD, UK. jianfeng.sun@ndorms.ox.ac.uk","institution_ids":["https://openalex.org/I4210146357"]},{"raw_affiliation_string":"Botnar Research Centre, University of Oxford, Headington, Oxford, OX3 7LD, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036165777","display_name":"Jinlong Ru","orcid":"https://orcid.org/0000-0002-6757-6018"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jinlong Ru","raw_affiliation_strings":["Chair of Prevention of Microbial Diseases, School of Life Sciences Weihenstephan, Technical University of Munich, 85354, Freising, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Prevention of Microbial Diseases, School of Life Sciences Weihenstephan, Technical University of Munich, 85354, Freising, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045781099","display_name":"Adam P. Cribbs","orcid":"https://orcid.org/0000-0001-5288-3077"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adam P. Cribbs","raw_affiliation_strings":["Botnar Research Centre, University of Oxford, Headington, Oxford, OX3 7LD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Botnar Research Centre, University of Oxford, Headington, Oxford, OX3 7LD, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101829955","display_name":"Dapeng Xiong","orcid":"https://orcid.org/0000-0002-8381-5680"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dapeng Xiong","raw_affiliation_strings":["Department of Computational Biology, Cornell University, Ithaca, 14853, USA. dx38@cornell.edu","Weill Institute for Cell and Molecular Biology, Cornell University, Ithaca, 14853, USA. dx38@cornell.edu","Weill Institute for Cell and Molecular Biology, Cornell University, Ithaca, 14853, USA","Department of Computational Biology, Cornell University, Ithaca, 14853, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Biology, Cornell University, Ithaca, 14853, USA. dx38@cornell.edu","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Weill Institute for Cell and Molecular Biology, Cornell University, Ithaca, 14853, USA. dx38@cornell.edu","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Weill Institute for Cell and Molecular Biology, Cornell University, Ithaca, 14853, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Department of Computational Biology, Cornell University, Ithaca, 14853, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101829955"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.0045,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72931563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"26","issue":"1","first_page":"70","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.19979999959468842,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.19979999959468842,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.13930000364780426,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.11479999870061874,"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/python","display_name":"Python (programming language)","score":0.8066086173057556},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7707167863845825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7330655455589294},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6264942288398743},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5284115076065063},{"id":"https://openalex.org/keywords/structural-genomics","display_name":"Structural genomics","score":0.4491288363933563},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4432530403137207},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.4157119393348694},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33656781911849976},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3315715193748474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25258868932724},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.22319895029067993},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2146349847316742},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17259687185287476},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1550990641117096}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8066086173057556},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7707167863845825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7330655455589294},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6264942288398743},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5284115076065063},{"id":"https://openalex.org/C192772702","wikidata":"https://www.wikidata.org/wiki/Q2583975","display_name":"Structural genomics","level":3,"score":0.4491288363933563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4432530403137207},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.4157119393348694},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33656781911849976},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3315715193748474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25258868932724},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.22319895029067993},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2146349847316742},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17259687185287476},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1550990641117096},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1186/s12859-025-06079-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06079-3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06079-3","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40025421","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40025421","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:8e918851f6664d33821d7e3bc96192a5","is_oa":true,"landing_page_url":"https://doaj.org/article/8e918851f6664d33821d7e3bc96192a5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 26, Iss 1, Pp 1-9 (2025)","raw_type":"article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1792083","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1792083","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:6d5ce526-e994-4e15-941c-4fdbda94dc22","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jisc Publications Router","raw_type":"http://purl.org/coar/resource_type/c_dcae04bc"},{"id":"pmh:oai:pubmedcentral.nih.gov:11871610","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11871610","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-025-06079-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06079-3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06079-3","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408068002.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1967293793","https://openalex.org/W2008708467","https://openalex.org/W2043338013","https://openalex.org/W2051210555","https://openalex.org/W2053418558","https://openalex.org/W2056825408","https://openalex.org/W2125558238","https://openalex.org/W2125583308","https://openalex.org/W2131474431","https://openalex.org/W2136799255","https://openalex.org/W2143035592","https://openalex.org/W2155051670","https://openalex.org/W2160257187","https://openalex.org/W2376573086","https://openalex.org/W2789857505","https://openalex.org/W2793168264","https://openalex.org/W2794498378","https://openalex.org/W2804523481","https://openalex.org/W2921372942","https://openalex.org/W2967960129","https://openalex.org/W2994687354","https://openalex.org/W3112376646","https://openalex.org/W3133915333","https://openalex.org/W3134163647","https://openalex.org/W3136918052","https://openalex.org/W3181892255","https://openalex.org/W3186474696","https://openalex.org/W3214130279","https://openalex.org/W4200140556","https://openalex.org/W4206231552","https://openalex.org/W4206694472","https://openalex.org/W4206977474","https://openalex.org/W4306697720","https://openalex.org/W4313334355","https://openalex.org/W4317369987","https://openalex.org/W4375858802","https://openalex.org/W4385969132","https://openalex.org/W4387043315","https://openalex.org/W4387866268","https://openalex.org/W4390988763","https://openalex.org/W4403734627","https://openalex.org/W4403783647"],"related_works":["https://openalex.org/W638577851","https://openalex.org/W2968354375","https://openalex.org/W2359440920","https://openalex.org/W2889550857","https://openalex.org/W3013372948","https://openalex.org/W3135997498","https://openalex.org/W4242417330","https://openalex.org/W4388282505","https://openalex.org/W2361861616","https://openalex.org/W3198631238"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1],"volume":[2],"of":[3,23,59,115],"protein":[4,60,95,116,132],"sequence":[5,73],"data":[6,76,120],"has":[7],"grown":[8],"exponentially":[9],"in":[10,16,68],"recent":[11],"years,":[12],"driven":[13],"by":[14,105],"advancements":[15],"metagenomics.":[17],"Despite":[18],"this,":[19],"a":[20,49,63,89,107],"substantial":[21],"proportion":[22],"these":[24],"sequences":[25],"remain":[26],"poorly":[27],"annotated,":[28],"underscoring":[29],"the":[30,56,112],"need":[31],"for":[32,42,82,92],"robust":[33],"bioinformatics":[34],"tools":[35,104],"to":[36,54,122],"facilitate":[37],"efficient":[38,131],"characterisation":[39],"and":[40,74,80,86,125],"annotation":[41,124],"functional":[43,123],"studies.":[44,134],"RESULTS:":[45],"We":[46],"present":[47],"PyPropel,":[48],"Python-based":[50],"computational":[51],"tool":[52],"developed":[53],"streamline":[55],"large-scale":[57],"analysis":[58],"data,":[61],"with":[62],"particular":[64],"focus":[65],"on":[66],"applications":[67],"machine":[69],"learning.":[70],"PyPropel":[71,98],"integrates":[72],"structural":[75],"pre-processing,":[77],"feature":[78],"generation,":[79],"post-processing":[81],"model":[83,126],"performance":[84,127],"evaluation":[85],"visualisation,":[87],"offering":[88,106],"comprehensive":[90],"solution":[91],"handling":[93],"complex":[94],"datasets.":[96],"CONCLUSION:":[97],"provides":[99],"added":[100],"value":[101],"over":[102],"existing":[103],"unified":[108],"workflow":[109],"that":[110],"encompasses":[111],"full":[113],"spectrum":[114],"research,":[117],"from":[118],"raw":[119],"pre-processing":[121],"analysis,":[128],"thereby":[129],"supporting":[130],"function":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-06T08:01:05.025921","created_date":"2025-10-10T00:00:00"}
