{"id":"https://openalex.org/W2119512378","doi":"https://doi.org/10.1109/csb.2003.1227329","title":"A block coding method that leads to significantly lower entropy values for the proteins and coding sections of Haemophilus influenzae","display_name":"A block coding method that leads to significantly lower entropy values for the proteins and coding sections of Haemophilus influenzae","publication_year":2004,"publication_date":"2004-03-30","ids":{"openalex":"https://openalex.org/W2119512378","doi":"https://doi.org/10.1109/csb.2003.1227329","mag":"2119512378","pmid":"https://pubmed.ncbi.nlm.nih.gov/16452804"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2003.1227329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","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/A5086096412","display_name":"G. Sampath","orcid":"https://orcid.org/0000-0002-3719-9098"},"institutions":[{"id":"https://openalex.org/I64281891","display_name":"College of New Jersey","ror":"https://ror.org/02nx5r318","country_code":"US","type":"education","lineage":["https://openalex.org/I64281891"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"G. Sampath","raw_affiliation_strings":["Department of Computer Science, College of New Jersey, Ewing, NJ, USA","[Department of Computer Science, College of New Jersey, Ewing, NJ, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of New Jersey, Ewing, NJ, USA","institution_ids":["https://openalex.org/I64281891"]},{"raw_affiliation_string":"[Department of Computer Science, College of New Jersey, Ewing, NJ, USA]","institution_ids":["https://openalex.org/I64281891"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5086096412"],"corresponding_institution_ids":["https://openalex.org/I64281891"],"apc_list":null,"apc_paid":null,"fwci":0.6029,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.65774848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"287","last_page":"293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9958999752998352,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9944000244140625,"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/haemophilus-influenzae","display_name":"Haemophilus influenzae","score":0.6895030736923218},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.529573917388916},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4992945194244385},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47080719470977783},{"id":"https://openalex.org/keywords/haemophilus","display_name":"Haemophilus","score":0.4502803087234497},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3391302824020386},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.32276320457458496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27122074365615845},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.20772311091423035},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1763383448123932},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13208097219467163},{"id":"https://openalex.org/keywords/bacteria","display_name":"Bacteria","score":0.12993115186691284},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11980006098747253}],"concepts":[{"id":"https://openalex.org/C2776925733","wikidata":"https://www.wikidata.org/wiki/Q1141979","display_name":"Haemophilus influenzae","level":3,"score":0.6895030736923218},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.529573917388916},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4992945194244385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47080719470977783},{"id":"https://openalex.org/C2776402342","wikidata":"https://www.wikidata.org/wiki/Q311275","display_name":"Haemophilus","level":3,"score":0.4502803087234497},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3391302824020386},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.32276320457458496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27122074365615845},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.20772311091423035},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1763383448123932},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13208097219467163},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.12993115186691284},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11980006098747253},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006193","descriptor_name":"Haemophilus influenzae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006193","descriptor_name":"Haemophilus influenzae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006193","descriptor_name":"Haemophilus influenzae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"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":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1109/csb.2003.1227329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-article"},{"id":"pmid:16452804","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16452804","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":"Proceedings. IEEE Computer Society Bioinformatics Conference","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.128.9376","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.128.9376","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://conferences.computer.org/bioinformatics/csb2003/pdf/reg_pprs/028_sampath(email6-10-03).pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1490430289","https://openalex.org/W1496422306","https://openalex.org/W1523176169","https://openalex.org/W1588594383","https://openalex.org/W1673352269","https://openalex.org/W1970231722","https://openalex.org/W1980569719","https://openalex.org/W2038180954","https://openalex.org/W2046441184","https://openalex.org/W2108278098","https://openalex.org/W2124871568","https://openalex.org/W2155729921","https://openalex.org/W2315040229","https://openalex.org/W2947000318","https://openalex.org/W3214380909","https://openalex.org/W6629764630","https://openalex.org/W6630503602","https://openalex.org/W6635219794","https://openalex.org/W6637074867","https://openalex.org/W6645321515","https://openalex.org/W6763546739"],"related_works":["https://openalex.org/W2386345146","https://openalex.org/W1986889155","https://openalex.org/W1979424193","https://openalex.org/W1522784025","https://openalex.org/W2418669643","https://openalex.org/W2159561955","https://openalex.org/W2062030243","https://openalex.org/W2001038692","https://openalex.org/W4232650466","https://openalex.org/W1915787817"],"abstract_inverted_index":{"A":[0],"simple":[1],"statistical":[2],"block":[3],"code":[4,92],"in":[5,33,129,141],"combination":[6],"with":[7,108],"the":[8,24,30,36,58,70,95,105,118,143,146],"LZW-based":[9],"compression":[10,27],"utilities":[11],"gzip":[12],"and":[13,63,81,132,145],"compress":[14],"has":[15,97],"been":[16],"found":[17],"to":[18,73],"increase":[19],"by":[20],"a":[21,88,98,109],"significant":[22],"amount":[23],"level":[25],"of":[26,47,60,66,75,101,120,135],"possible":[28],"for":[29,104],"proteins":[31],"encoded":[32],"Haemophilus":[34],"influenzae,":[35],"first":[37],"fully":[38],"sequenced":[39],"genome.":[40,147],"The":[41],"method":[42],"yields":[43],"an":[44,64],"entropy":[45,100],"value":[46],"3.665":[48],"bits":[49],"per":[50],"symbol":[51],"(bps),":[52],"which":[53],"is":[54],"0.657":[55],"bps":[56,62,68,77,103],"below":[57],"maximum":[59,99],"4.322":[61],"improvement":[65],"0.452":[67],"over":[69],"best":[71],"known":[72],"date":[74],"4.118":[76],"using":[78],"Matsumoto,":[79],"Sadakane,":[80],"Imai's":[82],"lza-CTW":[83],"algorithm.":[84],"Calculations":[85],"based":[86],"on":[87],"compact":[89],"inverse":[90],"genetic":[91],"show":[93,127],"that":[94,124],"genome":[96],"1.757":[102],"coding":[106],"regions,":[107],"possibly":[110],"lower":[111],"actual":[112],"entropy.":[113],"These":[114],"results":[115],"hint":[116],"at":[117],"existence":[119],"hitherto":[121],"unexplored":[122],"redundancies":[123],"do":[125],"not":[126],"up":[128],"Markov":[130],"models":[131],"are":[133],"indicative":[134],"more":[136],"internal":[137],"structure":[138],"than":[139],"suspected":[140],"both":[142],"protein":[144]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
