{"id":"https://openalex.org/W2980176690","doi":"https://doi.org/10.1109/embc.2019.8857598","title":"Protein Subcellular Localization Prediction Based on Internal Micro-similarities of Markov Chains","display_name":"Protein Subcellular Localization Prediction Based on Internal Micro-similarities of Markov Chains","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2980176690","doi":"https://doi.org/10.1109/embc.2019.8857598","mag":"2980176690","pmid":"https://pubmed.ncbi.nlm.nih.gov/31946144"},"language":"en","primary_location":{"id":"doi:10.1109/embc.2019.8857598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc.2019.8857598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007771081","display_name":"Asem Alaa","orcid":null},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Asem Alaa","raw_affiliation_strings":["Department of Systems and Biomedical Faculty of Engineering, Cairo University, Giza, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Biomedical Faculty of Engineering, Cairo University, Giza, Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075057705","display_name":"Ayman El\u2010Baz","orcid":"https://orcid.org/0000-0001-7264-1323"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ayman M. Eldeib","raw_affiliation_strings":["Department of Systems and Biomedical Faculty of Engineering, Cairo University, Giza, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Biomedical Faculty of Engineering, Cairo University, Giza, Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086750542","display_name":"Ahmed A. Metwally","orcid":"https://orcid.org/0000-0002-0155-7412"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ahmed A. Metwally","raw_affiliation_strings":["Department of Systems and Biomedical Faculty of Engineering, Cairo University, Giza, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Biomedical Faculty of Engineering, Cairo University, Giza, Egypt","institution_ids":["https://openalex.org/I145487455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.171,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.53465038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2019","issue":null,"first_page":"1355","last_page":"1358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.993399977684021,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9902999997138977,"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":0.7113416194915771},{"id":"https://openalex.org/keywords/subcellular-localization","display_name":"Subcellular localization","score":0.6480257511138916},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.643306314945221},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5890869498252869},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5410839319229126},{"id":"https://openalex.org/keywords/proteomics","display_name":"Proteomics","score":0.48705485463142395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4809417128562927},{"id":"https://openalex.org/keywords/protein-subcellular-localization-prediction","display_name":"Protein subcellular localization prediction","score":0.42772769927978516},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4263647496700287},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.42255282402038574},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.41808751225471497},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3468259871006012},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32912445068359375},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15873733162879944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113416194915771},{"id":"https://openalex.org/C2776879804","wikidata":"https://www.wikidata.org/wiki/Q7630919","display_name":"Subcellular localization","level":3,"score":0.6480257511138916},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.643306314945221},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5890869498252869},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5410839319229126},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.48705485463142395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4809417128562927},{"id":"https://openalex.org/C140051345","wikidata":"https://www.wikidata.org/wiki/Q7251501","display_name":"Protein subcellular localization prediction","level":3,"score":0.42772769927978516},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4263647496700287},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.42255282402038574},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.41808751225471497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3468259871006012},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32912445068359375},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15873733162879944},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C190062978","wikidata":"https://www.wikidata.org/wiki/Q79899","display_name":"Cytoplasm","level":2,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013347","descriptor_name":"Subcellular Fractions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013347","descriptor_name":"Subcellular Fractions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013347","descriptor_name":"Subcellular Fractions","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":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021381","descriptor_name":"Protein Transport","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021381","descriptor_name":"Protein Transport","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021381","descriptor_name":"Protein Transport","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":2,"locations":[{"id":"doi:10.1109/embc.2019.8857598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc.2019.8857598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-article"},{"id":"pmid:31946144","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31946144","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":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1988301066","https://openalex.org/W2005687845","https://openalex.org/W2034070267","https://openalex.org/W2059185913","https://openalex.org/W2100851422","https://openalex.org/W2115252128","https://openalex.org/W2124306486","https://openalex.org/W2154139219","https://openalex.org/W2163614729","https://openalex.org/W2597082880","https://openalex.org/W2730472814","https://openalex.org/W2747811776","https://openalex.org/W2749697459","https://openalex.org/W2884869637","https://openalex.org/W2885241647","https://openalex.org/W2890567665","https://openalex.org/W2963141751","https://openalex.org/W6677618333","https://openalex.org/W6683915439","https://openalex.org/W6734945091"],"related_works":["https://openalex.org/W2351398203","https://openalex.org/W4205775722","https://openalex.org/W4366498163","https://openalex.org/W2402975874","https://openalex.org/W3215969703","https://openalex.org/W4389024241","https://openalex.org/W2384565783","https://openalex.org/W2406531951","https://openalex.org/W2099701744","https://openalex.org/W2391458050"],"abstract_inverted_index":{"Elucidating":[0],"protein":[1,24,46,70],"subcellular":[2,25,47,71,140],"localization":[3,72],"is":[4,27,145],"an":[5,28,51],"essential":[6],"topic":[7],"in":[8,15,35,112],"proteomics":[9],"research":[10],"due":[11],"to":[12,54,68,92,116],"its":[13],"importance":[14],"the":[16,75,101],"process":[17,30],"of":[18,78,105,138],"drug":[19],"discovery.":[20],"Unfortunately,":[21],"experimentally":[22],"uncovering":[23],"targets":[26,48],"arduous":[29],"that":[31,97,123],"may":[32],"not":[33],"result":[34],"a":[36,65,94,106,135],"successful":[37],"localization.":[38],"In":[39,60],"contrast,":[40],"computational":[41],"methods":[42,56],"can":[43],"rapidly":[44],"predict":[45,69],"and":[49,109],"are":[50],"efficient":[52],"alternative":[53],"experimental":[55],"for":[57],"unannotated":[58],"proteins.":[59],"this":[61],"work,":[62],"we":[63,121],"introduce":[64],"new":[66],"method":[67,88,125],"which":[73],"increases":[74],"predictive":[76],"power":[77],"generative":[79],"probabilistic":[80],"models":[81,91],"while":[82],"preserving":[83],"their":[84,110],"explanatory":[85],"benefit.":[86],"Our":[87],"exploits":[89],"Markov":[90,118],"produce":[93],"feature":[95],"vector":[96],"records":[98],"micro-similarities":[99],"between":[100],"underlying":[102],"probability":[103],"distributions":[104],"given":[107],"sequence":[108],"counterparts":[111],"reference":[113],"models.":[114],"Compared":[115],"ordinary":[117],"chain":[119],"inference,":[120],"show":[122],"our":[124],"improves":[126],"overall":[127],"accuracy":[128],"by":[129],"10%":[130],"under":[131],"10-fold":[132],"cross-validation":[133],"on":[134,148],"dataset":[136],"consisting":[137],"10":[139],"locations.":[141],"The":[142],"source":[143],"code":[144],"publicly":[146],"available":[147],"https://github.com/aametwally/MC":[149],"MicroSimilarities.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
