<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>2420</id>
    <completedYear>2017</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue>4</issue>
    <volume>8</volume>
    <type>article</type>
    <publisherName>MDPI AG</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">K-mer Content, Correlation, and Position Analysis of Genome DNA Sequences for the Identification of Function and Evolutionary Features</title>
    <abstract language="eng">In genome analysis, k-mer-based comparison methods have become standard tools. However, even though they are able to deliver reliable results, other algorithms seem to work better in some cases. To improve k-mer-based DNA sequence analysis and comparison, we successfully checked whether adding positional resolution is beneficial for finding and/or comparing interesting organizational structures. A simple but efficient algorithm for extracting and saving local k-mer spectra (frequency distribution of k-mers) was developed and used. The results were analyzed by including positional information based on visualizations as genomic maps and by applying basic vector correlation methods. This analysis was concentrated on small word lengths (1 ≤ k ≤ 4) on relatively small viral genomes of Papillomaviridae and Herpesviridae, while also checking its usability for larger sequences, namely human chromosome 2 and the homologous chromosomes (2A, 2B) of a chimpanzee. Using this alignment-free analysis, several regions with specific characteristics in Papillomaviridae and Herpesviridae formerly identified by independent, mostly alignment-based methods, were confirmed. Correlations between the k-mer content and several genes in these genomes have been found, showing similarities between classified and unclassified viruses, which may be potentially useful for further taxonomic research. Furthermore, unknown k-mer correlations in the genomes of Human Herpesviruses (HHVs), which are probably of major biological function, are found and described. Using the chromosomes of a chimpanzee and human that are currently known, identities between the species on every analyzed chromosome were reproduced. This demonstrates the feasibility of our approach for large data sets of complex genomes. Based on these results, we suggest k-mer analysis with positional resolution as a method for closing a gap between the effectiveness of alignment-based methods (like NCBI BLAST) and the high pace of standard k-mer analysis.</abstract>
    <parentTitle language="eng">Genes</parentTitle>
    <identifier type="issn">2073-4425</identifier>
    <identifier type="doi">https://doi.org/10.3390/genes8040122</identifier>
    <enrichment key="opus_doi_flag">true</enrichment>
    <enrichment key="opus_import_data">{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T12:33:51Z","timestamp":1722947631798},"reference-count":31,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2017,4,19]],"date-time":"2017-04-19T00:00:00Z","timestamp":1492560000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Genes"],"abstract":"&lt;jats:p&gt;In genome analysis, k-mer-based comparison methods have become standard tools. However, even though they are able to deliver reliable results, other algorithms seem to work better in some cases. To improve k-mer-based DNA sequence analysis and comparison, we successfully checked whether adding positional resolution is beneficial for finding and\/or comparing interesting organizational structures. A simple but efficient algorithm for extracting and saving local k-mer spectra (frequency distribution of k-mers) was developed and used. The results were analyzed by including positional information based on visualizations as genomic maps and by applying basic vector correlation methods. This analysis was concentrated on small word lengths (1 \u2264 k \u2264 4) on relatively small viral genomes of Papillomaviridae and Herpesviridae, while also checking its usability for larger sequences, namely human chromosome 2 and the homologous chromosomes (2A, 2B) of a chimpanzee. Using this alignment-free analysis, several regions with specific characteristics in Papillomaviridae and Herpesviridae formerly identified by independent, mostly alignment-based methods, were confirmed. Correlations between the k-mer content and several genes in these genomes have been found, showing similarities between classified and unclassified viruses, which may be potentially useful for further taxonomic research. Furthermore, unknown k-mer correlations in the genomes of Human Herpesviruses (HHVs), which are probably of major biological function, are found and described. Using the chromosomes of a chimpanzee and human that are currently known, identities between the species on every analyzed chromosome were reproduced. This demonstrates the feasibility of our approach for large data sets of complex genomes. Based on these results, we suggest k-mer analysis with positional resolution as a method for closing a gap between the effectiveness of alignment-based methods (like NCBI BLAST) and the high pace of standard k-mer analysis.&lt;\/jats:p&gt;","DOI":"10.3390\/genes8040122","type":"journal-article","created":{"date-parts":[[2017,4,19]],"date-time":"2017-04-19T14:22:01Z","timestamp":1492611721000},"page":"122","source":"Crossref","is-referenced-by-count":36,"title":["K-mer Content, Correlation, and Position Analysis of Genome DNA Sequences for the Identification of Function and Evolutionary Features"],"prefix":"10.3390","volume":"8","author":[{"given":"Aaron","family":"Sievers","sequence":"first","affiliation":[{"name":"Kirchhoff-Institute for Physics, Heidelberg University, INF 227, 69117 Heidelberg, Germany"}]},{"given":"Katharina","family":"Bosiek","sequence":"additional","affiliation":[{"name":"Kirchhoff-Institute for Physics, Heidelberg University, INF 227, 69117 Heidelberg, Germany"}]},{"given":"Marc","family":"Bisch","sequence":"additional","affiliation":[{"name":"Kirchhoff-Institute for Physics, Heidelberg University, INF 227, 69117 Heidelberg, Germany"}]},{"given":"Chris","family":"Dreessen","sequence":"additional","affiliation":[{"name":"Kirchhoff-Institute for Physics, Heidelberg University, INF 227, 69117 Heidelberg, Germany"}]},{"given":"Jascha","family":"Riedel","sequence":"additional","affiliation":[{"name":"Kirchhoff-Institute for Physics, Heidelberg University, INF 227, 69117 Heidelberg, Germany"}]},{"given":"Patrick","family":"Fro\u00df","sequence":"additional","affiliation":[{"name":"Kirchhoff-Institute for Physics, Heidelberg University, INF 227, 69117 Heidelberg, Germany"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-9430-1987","authenticated-orcid":false,"given":"Michael","family":"Hausmann","sequence":"additional","affiliation":[{"name":"Kirchhoff-Institute for Physics, Heidelberg University, INF 227, 69117 Heidelberg, Germany"}]},{"given":"Georg","family":"Hildenbrand","sequence":"additional","affiliation":[{"name":"Kirchhoff-Institute for Physics, Heidelberg University, INF 227, 69117 Heidelberg, Germany"},{"name":"Department of Radiation Oncology, Universit\u00e4tsmedizin Mannheim, Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2017,4,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","article-title":"Basic local alignment search tool","volume":"215","author":"Altschul","year":"1990","journal-title":"J. Mol. Biol."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Chan, C.X., and Ragan, M.A. (2013). Next-generation phylogenetics. Biol. Direct, 8.","DOI":"10.1186\/1745-6150-8-3"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Alsop, E.B., and Raymond, J. (2013). Resolving prokaryotic taxonomy without rRNA: Longer oligonucleotide word lengths improve genome and metagenome taxonomic classification. PLoS ONE, 8.","DOI":"10.1371\/journal.pone.0067337"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1080\/07391102.1986.10507643","article-title":"Linguistics of nucleotide sequences: morphology and comparison of vocabularies","volume":"4","author":"Brendel","year":"1986","journal-title":"J. Biomol. Struct. Dyn."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zhou, F., Olman, V., and Xu, Y. (2008). Barcodes for genomes and applications. BMC Bioinform., 9.","DOI":"10.1186\/1471-2105-9-546"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/S0378-1119(02)01206-4","article-title":"Pentamer vocabularies characterizing introns and intron-like intergenic tracts from Caenorhabditis elegans and Drosophila melanogaster","volume":"304","author":"Bultrini","year":"2003","journal-title":"Gene"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1101\/gr.152201","article-title":"Low-complexity regions in Plasmodium falciparum proteins","volume":"11","author":"Pizzi","year":"2001","journal-title":"Genome Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1146\/annurev.micro.54.1.641","article-title":"Pathogenicity islands and the evolution of microbes","volume":"54","author":"Hacker","year":"2000","journal-title":"Annu. Rev. Microbiol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1126\/science.1128794","article-title":"Selective silencing of foreign DNA with low GC content by the H-NS protein in Salmonella","volume":"313","author":"Navarre","year":"2006","journal-title":"Science"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1007\/s002390010050","article-title":"Divergence of noncoding sequences and of insertions encoding nonglobular domains at a genomic region well conserved in plasmodia","volume":"50","author":"Pizzi","year":"2000","journal-title":"J. Mol. Evolut."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Pozzoli, U., Menozzi, G., Fumagalli, M., Cereda, M., Comi, G.P., Cagliani, R., Bresolin, N., and Sironi, M. (2008). Both selective and neutral processes drive GC content evolution in the human genome. BMC Evolut. Biol., 8.","DOI":"10.1186\/1471-2148-8-99"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4783","DOI":"10.1093\/nar\/gkt144","article-title":"Comparative analysis using k-mer and k-flank patterns provides evidence for CpG island sequence evolution in mammalian genomes","volume":"41","author":"Chae","year":"2013","journal-title":"Nucleic Acids Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"D34","DOI":"10.1093\/nar\/gki063","article-title":"GenBank","volume":"33","author":"Benson","year":"2005","journal-title":"Nucleic Acids Res."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1098\/rspl.1895.0041","article-title":"Note on regression and inheritance in the case of two parents","volume":"58","author":"Pearson","year":"1895","journal-title":"Proc. R. Soc. Lond."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1093\/bioinformatics\/btr011","article-title":"A fast, lock-free approach for efficient parallel counting of occurrences of k-mers","volume":"27","author":"Kingsford","year":"2011","journal-title":"Bioinformatics"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"10227","DOI":"10.1073\/pnas.94.19.10227","article-title":"Compositional differences within and between eukaryotic genomes","volume":"94","author":"Karlin","year":"1997","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/MCSE.2007.55","article-title":"Matplotlib: A 2D graphics environment","volume":"9","author":"Hunter","year":"2007","journal-title":"Compt. Sci. Eng."},{"key":"ref_18","first-page":"D13","article-title":"Database resources of the National Center for Biotechnology Information","volume":"40","author":"Acland","year":"2009","journal-title":"Nucleic Acids Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2286","DOI":"10.2741\/1971","article-title":"Papillomavirus genome structure, expression, and post-trascriptional regulation","volume":"11","author":"Zheng","year":"2006","journal-title":"Front. Biosci."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"E37","DOI":"10.1111\/j.1749-6632.2011.06358.x","article-title":"Evolution of sexually transmitted and sexually transmissible human herpesviruses","volume":"1230","author":"Davison","year":"2011","journal-title":"Ann. N. Y. Acad. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/BF02170221","article-title":"On the desoxyribonucleic acid content of sea urchin gametes","volume":"8","author":"Elson","year":"1952","journal-title":"Expertientia"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"8040","DOI":"10.1128\/JVI.73.10.8040-8052.1999","article-title":"Human herpesvirus 6B genome sequence: Coding content and comparison with human herpesvirus 6A","volume":"73","author":"Dominguez","year":"1999","journal-title":"J. Vorol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1016\/j.virol.2006.01.015","article-title":"The genome of Epstein-Barr virus type 2 strain AG876","volume":"350","author":"Dolan","year":"2006","journal-title":"J. Virol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/viro.1998.9105","article-title":"The DNA sequence of the RK strain of human herpesvirus 7","volume":"244","author":"Megaw","year":"1998","journal-title":"J. Virol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1126\/science.7375922","article-title":"The Striking Resemblance of high-resolution G-banded chromosomes of man and chimpanzee","volume":"208","author":"Yunis","year":"1980","journal-title":"Science"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Pratas, D., Silva, R.M., Pinho, A.J., and Ferreira, P.J.S.G. (2015). An alignment-free method to find and visualise rearrangements between pairs of DNA sequences. Sci. Rep., 5.","DOI":"10.1038\/srep10203"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1038\/nature07361","article-title":"Malaria research in the post-genomic era","volume":"455","author":"Winzeler","year":"2008","journal-title":"Nature"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2825","DOI":"10.1093\/nar\/gkn121","article-title":"Presence and role of cytosine methylation in DNA viruses of animals","volume":"36","author":"Hoelzer","year":"2008","journal-title":"Nucleic Acids Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1006\/mpev.1996.0002","article-title":"Human coding and noncoding DNA: Compositional correlations","volume":"5","author":"Clay","year":"1996","journal-title":"Mol. Phylogenet. Evolut."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1007\/BF00163235","article-title":"Statistical analysis of vertebrate sequences reveals that long genes are scarce in GC-rich isochores","volume":"40","author":"Duret","year":"1995","journal-title":"J. Mol. Evolut."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1139","DOI":"10.1093\/oxfordjournals.molbev.a003886","article-title":"Local Rates of Recombination Are Positively Correlated with GC Content in the Human Genom","volume":"8","author":"Fullerton","year":"2001","journal-title":"Mol. Biol. Evolut."}],"container-title":["Genes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-4425\/8\/4\/122\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T12:05:36Z","timestamp":1717761936000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-4425\/8\/4\/122"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,19]]},"references-count":31,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2017,4]]}},"alternative-id":["genes8040122"],"URL":"http:\/\/dx.doi.org\/10.3390\/genes8040122","relation":{},"ISSN":["2073-4425"],"issn-type":[{"value":"2073-4425","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,4,19]]}}}</enrichment>
    <enrichment key="local_crossrefDocumentType">journal-article</enrichment>
    <enrichment key="local_crossrefLicence">https://creativecommons.org/licenses/by/4.0/</enrichment>
    <enrichment key="local_import_origin">crossref</enrichment>
    <enrichment key="local_doiImportPopulated">PersonAuthorFirstName_1,PersonAuthorLastName_1,PersonAuthorFirstName_2,PersonAuthorLastName_2,PersonAuthorFirstName_3,PersonAuthorLastName_3,PersonAuthorFirstName_4,PersonAuthorLastName_4,PersonAuthorFirstName_5,PersonAuthorLastName_5,PersonAuthorFirstName_6,PersonAuthorLastName_6,PersonAuthorFirstName_7,PersonAuthorLastName_7,PersonAuthorIdentifierOrcid_7,PersonAuthorFirstName_8,PersonAuthorLastName_8,PublisherName,TitleMain_1,Language,TitleAbstract_1,TitleParent_1,ArticleNumber,Issue,Volume,CompletedYear,IdentifierIssn,Enrichmentlocal_crossrefLicence</enrichment>
    <enrichment key="opus.source">doi-import</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <author>Aaron Sievers</author>
    <author>Katharina Bosiek</author>
    <author>Marc Bisch</author>
    <author>Chris Dreessen</author>
    <author>Jascha Riedel</author>
    <author>Patrick Froß</author>
    <author>Michael Hausmann</author>
    <author>Georg Hildenbrand</author>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Genom</value>
    </subject>
    <collection role="institutes" number="">Medical Engineering and Data Science (Bachelor)</collection>
    <collection role="forschungsschwerpunkte" number="">Artifical Intelligence and Data Science</collection>
    <collection role="forschungsschwerpunkte" number="">Material Testing &amp; Sensor Technology</collection>
  </doc>
</export-example>
