{"id":"https://openalex.org/W4387346439","doi":"https://doi.org/10.1145/3584371.3612947","title":"An Approach to Developing Benchmark Datasets for Protein Secondary Structure Segmentation from Cryo-EM Density Maps","display_name":"An Approach to Developing Benchmark Datasets for Protein Secondary Structure Segmentation from Cryo-EM Density Maps","publication_year":2023,"publication_date":"2023-09-03","ids":{"openalex":"https://openalex.org/W4387346439","doi":"https://doi.org/10.1145/3584371.3612947","pmid":"https://pubmed.ncbi.nlm.nih.gov/41509644"},"language":"en","primary_location":{"id":"doi:10.1145/3584371.3612947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3612947","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3612947","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3612947","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100612153","display_name":"Thu Ha Nguyen","orcid":"https://orcid.org/0000-0001-5656-7207"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thu Nguyen","raw_affiliation_strings":["Old Dominion University, Norfolk, United States"],"raw_orcid":"https://orcid.org/0009-0004-3436-4360","affiliations":[{"raw_affiliation_string":"Old Dominion University, Norfolk, United States","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103042140","display_name":"Yongcheng Mu","orcid":"https://orcid.org/0009-0005-7058-2979"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongcheng Mu","raw_affiliation_strings":["Old Dominion University, Norfolk, United States"],"raw_orcid":"https://orcid.org/0009-0005-7058-2979","affiliations":[{"raw_affiliation_string":"Old Dominion University, Norfolk, United States","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086030102","display_name":"Jiangwen Sun","orcid":"https://orcid.org/0009-0000-8905-7553"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiangwen Sun","raw_affiliation_strings":["Old Dominion University, Norfolk, United States"],"raw_orcid":"https://orcid.org/0009-0000-8905-7553","affiliations":[{"raw_affiliation_string":"Old Dominion University, Norfolk, United States","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049641499","display_name":"Jing He","orcid":"https://orcid.org/0000-0002-7249-4746"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing He","raw_affiliation_strings":["Old Dominion University, Norfolk, United States"],"raw_orcid":"https://orcid.org/0000-0002-7249-4746","affiliations":[{"raw_affiliation_string":"Old Dominion University, Norfolk, United States","institution_ids":["https://openalex.org/I81365321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100612153"],"corresponding_institution_ids":["https://openalex.org/I81365321"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09293552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2023","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11162","display_name":"Enzyme Structure and Function","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11162","display_name":"Enzyme Structure and Function","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10857","display_name":"Advanced Electron Microscopy Techniques and Applications","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1315","display_name":"Structural 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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9851999878883362,"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/segmentation","display_name":"Segmentation","score":0.7306203246116638},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7167174816131592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6716870069503784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5917628407478333},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5204730033874512},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.5176727771759033},{"id":"https://openalex.org/keywords/protein-secondary-structure","display_name":"Protein secondary structure","score":0.49289774894714355},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47205835580825806},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4652700424194336},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.453368216753006},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4523202180862427},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4511135220527649},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4451759457588196},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4346180856227875}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7306203246116638},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7167174816131592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6716870069503784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5917628407478333},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5204730033874512},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.5176727771759033},{"id":"https://openalex.org/C62614982","wikidata":"https://www.wikidata.org/wiki/Q904984","display_name":"Protein secondary structure","level":2,"score":0.49289774894714355},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47205835580825806},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4652700424194336},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.453368216753006},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4523202180862427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4511135220527649},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4451759457588196},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4346180856227875},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3584371.3612947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3612947","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3612947","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},{"id":"pmid:41509644","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41509644","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":"ACM-BCB ... ... : the ... ACM Conference on Bioinformatics, Computational Biology and Biomedicine. ACM Conference on Bioinformatics, Computational Biology and Biomedicine","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12774664","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12774664/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12774664/pdf/nihms-2132123.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM BCB","raw_type":"Text"},{"id":"pmh:oai:digitalcommons.odu.edu:computerscience_fac_pubs-1303","is_oa":true,"landing_page_url":"https://digitalcommons.odu.edu/computerscience_fac_pubs/298","pdf_url":null,"source":{"id":"https://openalex.org/S4377196314","display_name":"ODU Digital Commons (Old Dominion University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I81365321","host_organization_name":"Old Dominion University","host_organization_lineage":["https://openalex.org/I81365321"],"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":"Computer Science Faculty Publications","raw_type":"conference"}],"best_oa_location":{"id":"doi:10.1145/3584371.3612947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3612947","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3612947","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G5933034863","display_name":null,"funder_award_id":"R01-GM062968","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8288036582","display_name":null,"funder_award_id":"NIH R01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G835039876","display_name":null,"funder_award_id":"NIH R01-GM062968","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387346439.pdf","grobid_xml":"https://content.openalex.org/works/W4387346439.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2049266248","https://openalex.org/W2054116168","https://openalex.org/W2132629607","https://openalex.org/W2133442602","https://openalex.org/W2147791333","https://openalex.org/W2152086886","https://openalex.org/W2180441778","https://openalex.org/W2404441930","https://openalex.org/W2576361275","https://openalex.org/W2580555377","https://openalex.org/W2591330651","https://openalex.org/W2913356304","https://openalex.org/W2966489898","https://openalex.org/W3011088659","https://openalex.org/W3013510002","https://openalex.org/W3083406432","https://openalex.org/W3105695732","https://openalex.org/W3107709469","https://openalex.org/W3114526705","https://openalex.org/W3127623024","https://openalex.org/W3129954825","https://openalex.org/W3210648509","https://openalex.org/W4313017257"],"related_works":["https://openalex.org/W4387327236","https://openalex.org/W2183488467","https://openalex.org/W1990237101","https://openalex.org/W4309907966","https://openalex.org/W2028462208","https://openalex.org/W4387896287","https://openalex.org/W4285337533","https://openalex.org/W2982831492","https://openalex.org/W3170838353","https://openalex.org/W2187490799"],"abstract_inverted_index":{"More":[0],"and":[1,81,88,94,106,139],"more":[2],"deep":[3,24,115],"learning":[4,25,116],"approaches":[5,26],"have":[6,37],"been":[7,38],"proposed":[8],"to":[9,40,63,98],"segment":[10],"secondary":[11,103,123,137],"structures":[12,124],"from":[13,125],"cryo-electron":[14],"density":[15],"maps":[16],"at":[17],"medium":[18],"resolution":[19],"range":[20],"(5-10\u00c5).":[21],"Although":[22],"the":[23,42,55,75,100,110,136,143],"show":[27,130],"great":[28],"potential,":[29],"only":[30],"a":[31,91,114],"few":[32],"small":[33],"experimental":[34],"data":[35,65,82,107,140],"sets":[36,66,97],"used":[39],"test":[41,92],"approaches.":[43],"There":[44],"is":[45],"limited":[46],"understanding":[47],"about":[48],"potential":[49,72],"factors,":[50],"in":[51,70,135],"data,":[52],"that":[53,118,131],"affect":[54],"performance":[56,111,144],"of":[57,102,112,121,145],"segmentation.":[58],"We":[59],"propose":[60],"an":[61],"approach":[62,85],"generate":[64],"with":[67],"desired":[68],"specifications":[69],"three":[71],"factors":[73],"-":[74],"protein":[76,122],"sequence":[77],"identity,":[78],"structural":[79],"contents,":[80],"quality.":[83],"The":[84],"was":[86],"implemented":[87],"has":[89],"generated":[90],"set":[93],"various":[95,132],"training":[96],"study":[99],"effect":[101],"structure":[104,138],"content":[105,133],"quality":[108,141],"on":[109],"DeepSSETracer,":[113],"method":[117],"segments":[119],"regions":[120],"cryo-EM":[126],"map":[127],"components.":[128],"Results":[129],"levels":[134],"influence":[142],"segmentation":[146],"for":[147],"DeepSSETracer.":[148]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}