{"id":"https://openalex.org/W7126073133","doi":"https://doi.org/10.1109/bibm66473.2025.11356259","title":"A Multipurpose Protein Compressor Based on MDL and Genetic Algorithm","display_name":"A Multipurpose Protein Compressor Based on MDL and Genetic Algorithm","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126073133","doi":"https://doi.org/10.1109/bibm66473.2025.11356259"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5124293282","display_name":"M. Zohaib Nawaz","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"M. Zohaib Nawaz","raw_affiliation_strings":["Shenzhen University,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124293282","display_name":"M. Zohaib Nawaz","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"M. Saqib Nawaz","raw_affiliation_strings":["Shenzhen University,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038682039","display_name":"Philippe Fournier\u2010Viger","orcid":"https://orcid.org/0000-0002-7680-9899"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Philippe Fournier-Viger","raw_affiliation_strings":["Shenzhen University,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124294425","display_name":"Xinzheng Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinzheng Niu","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124218720","display_name":"Mengqiu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengqiu Li","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5124293282"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67344898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6889","last_page":"6896"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.16269999742507935,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.16269999742507935,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.11640000343322754,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.09000000357627869,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.6107000112533569},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5741000175476074},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.5733000040054321},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.555400013923645},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5375000238418579},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4634999930858612},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.45879998803138733},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.41260001063346863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.614300012588501},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.6107000112533569},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5741000175476074},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.5733000040054321},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44769999384880066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4223000109195709},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.37279999256134033},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3698999881744385},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.31610000133514404},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C147816474","wikidata":"https://www.wikidata.org/wiki/Q169525","display_name":"Protein engineering","level":3,"score":0.3046000003814697},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.302700012922287},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1659842140","https://openalex.org/W2127912200","https://openalex.org/W2158678815","https://openalex.org/W2469728511","https://openalex.org/W2903404191","https://openalex.org/W2911837058","https://openalex.org/W2912135067","https://openalex.org/W2951893579","https://openalex.org/W2976854536","https://openalex.org/W3038746171","https://openalex.org/W3092794487","https://openalex.org/W3098741556","https://openalex.org/W3123545922","https://openalex.org/W3157476266","https://openalex.org/W4226309432","https://openalex.org/W4247001379","https://openalex.org/W4291017687","https://openalex.org/W4380883088","https://openalex.org/W4384341779","https://openalex.org/W4398163942","https://openalex.org/W4400943345","https://openalex.org/W4401570038","https://openalex.org/W4403094469","https://openalex.org/W4403966511","https://openalex.org/W4404458588","https://openalex.org/W4405388509","https://openalex.org/W4406159770","https://openalex.org/W4406261761","https://openalex.org/W4408508943"],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"expansion":[2],"of":[3,27,93],"protein":[4,37,74,122,140],"sequence":[5,141],"databases":[6],"has":[7],"created":[8],"challenges":[9],"for":[10,139],"efficient":[11,130],"storage,":[12],"transmission,":[13],"and":[14,43,59,117],"analysis.":[15,142],"Unlike":[16],"genomic":[17],"sequences":[18],"with":[19,85],"only":[20,128],"four":[21],"nucleotide":[22],"bases,":[23],"proteins":[24],"are":[25],"composed":[26],"twenty":[28],"amino":[29,94],"acids,":[30],"making":[31],"compression":[32,75,104,131],"more":[33],"complex.":[34],"Existing":[35],"specialized":[36],"compressors,":[38],"such":[39,114],"as":[40,115],"AC,":[41],"AC2":[42],"CPM-FCM,":[44],"have":[45],"achieved":[46],"promising":[47],"performance":[48,105],"but":[49,133],"still":[50],"face":[51],"limitations,":[52],"including":[53],"high":[54],"computational":[55],"cost,":[56],"low":[57],"adaptability":[58],"limited":[60],"biological":[61],"interpretability.":[62],"This":[63,124],"paper":[64],"introduces":[65],"GMP":[66,102,126,143],"(Genetic":[67],"algorithm-based":[68],"MDL":[69],"Protein":[70],"compressor),":[71],"a":[72,86,135],"novel":[73],"framework":[76,132],"that":[77,101],"leverages":[78],"the":[79],"Minimum":[80],"Description":[81],"Length":[82],"(MDL)":[83],"principle":[84],"genetic":[87],"algorithm":[88],"to":[89,107],"discover":[90],"optimal":[91],"patterns":[92],"acid":[95],"subsequences":[96],"(kAA-mers).":[97],"Experimental":[98],"results":[99],"demonstrate":[100],"attains":[103],"comparable":[106],"state-of-the-art":[108],"methods":[109],"while":[110],"additionally":[111],"supporting":[112],"tasks":[113],"classification":[116],"clustering-capabilities":[118],"absent":[119],"from":[120],"traditional":[121],"compressors.":[123],"makes":[125],"not":[127],"an":[129],"also":[134],"biologically":[136],"interpretable":[137],"tool":[138],"is":[144],"available":[145],"at":[146],"github.com/MuhammadzohaibNawaz/GMP":[147]},"counts_by_year":[],"updated_date":"2026-02-01T03:34:12.195049","created_date":"2026-01-30T00:00:00"}