Loading…

A Novel Computational Method for Detecting DNA Methylation Sites with DNA Sequence Information and Physicochemical Properties

DNA methylation is an important biochemical process, and it has a close connection with many types of cancer. Research about DNA methylation can help us to understand the regulation mechanism and epigenetic reprogramming. Therefore, it becomes very important to recognize the methylation sites in the...

Full description

Saved in:
Bibliographic Details
Published in:International journal of molecular sciences 2018-02, Vol.19 (2), p.511
Main Authors: Pan, Gaofeng, Jiang, Limin, Tang, Jijun, Guo, Fei
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c478t-2b9dc62a659d489510a52f98093a1cf71081256d339d467a39dc5a819f308dd3
cites cdi_FETCH-LOGICAL-c478t-2b9dc62a659d489510a52f98093a1cf71081256d339d467a39dc5a819f308dd3
container_end_page
container_issue 2
container_start_page 511
container_title International journal of molecular sciences
container_volume 19
creator Pan, Gaofeng
Jiang, Limin
Tang, Jijun
Guo, Fei
description DNA methylation is an important biochemical process, and it has a close connection with many types of cancer. Research about DNA methylation can help us to understand the regulation mechanism and epigenetic reprogramming. Therefore, it becomes very important to recognize the methylation sites in the DNA sequence. In the past several decades, many computational methods-especially machine learning methods-have been developed since the high-throughout sequencing technology became widely used in research and industry. In order to accurately identify whether or not a nucleotide residue is methylated under the specific DNA sequence context, we propose a novel method that overcomes the shortcomings of previous methods for predicting methylation sites. We use -gram, multivariate mutual information, discrete wavelet transform, and pseudo amino acid composition to extract features, and train a sparse Bayesian learning model to do DNA methylation prediction. Five criteria-area under the receiver operating characteristic curve (AUC), Matthew's correlation coefficient (MCC), accuracy (ACC), sensitivity (SN), and specificity-are used to evaluate the prediction results of our method. On the benchmark dataset, we could reach 0.8632 on AUC, 0.8017 on ACC, 0.5558 on MCC, and 0.7268 on SN. Additionally, the best results on two scBS-seq profiled mouse embryonic stem cells datasets were 0.8896 and 0.9511 by AUC, respectively. When compared with other outstanding methods, our method surpassed them on the accuracy of prediction. The improvement of AUC by our method compared to other methods was at least 0.0399 . For the convenience of other researchers, our code has been uploaded to a file hosting service, and can be downloaded from: https://figshare.com/s/0697b692d802861282d3.
doi_str_mv 10.3390/ijms19020511
format article
fullrecord <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_7e3ade4ee29248b496e8601f030a3a5e</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_7e3ade4ee29248b496e8601f030a3a5e</doaj_id><sourcerecordid>1999679696</sourcerecordid><originalsourceid>FETCH-LOGICAL-c478t-2b9dc62a659d489510a52f98093a1cf71081256d339d467a39dc5a819f308dd3</originalsourceid><addsrcrecordid>eNpdkktvEzEQgFcIRB9w44wsceHQgB9rr31BilIekUqp1N4tx57NOtpdB9tblAP_HZOUKuU0lufzp5nxVNUbgj8wpvBHvxkSUZhiTsiz6pTUlM4wFs3zo_NJdZbSBmPKKFcvqxOqaqIaTk-r33N0He6hR4swbKdssg-j6dF3yF1wqA0RXUIGm_24RpfX831i1-8xdOszJPTL526fuoWfE4wW0HIs74YDY0aHbrpd8jbYDgZvi_wmhi3E7CG9ql60pk_w-iGeV3dfPt8tvs2ufnxdLuZXM1s3Ms_oSjkrqBFcuVoqTrDhtFUSK2aIbRuCJaFcuDIPV4vGlGC5kUS1DEvn2Hm1PGhdMBu9jX4wcaeD8Xp_EeJam1KP7UE3wIyDGoAqWstVrQRIgUmLGTbMcCiuTwfXdloN4CyMOZr-ifRpZvSdXod7zSXnDWNF8P5BEEMZWMp68MlC35sRwpQ0UUqJRgklCvruP3QTplj-J2mKSd0oRYQs1MWBsjGkFKF9LIZg_XdF9PGKFPztcQOP8L-dYH8ABw639A</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2014799168</pqid></control><display><type>article</type><title>A Novel Computational Method for Detecting DNA Methylation Sites with DNA Sequence Information and Physicochemical Properties</title><source>Publicly Available Content Database</source><source>PubMed Central</source><creator>Pan, Gaofeng ; Jiang, Limin ; Tang, Jijun ; Guo, Fei</creator><creatorcontrib>Pan, Gaofeng ; Jiang, Limin ; Tang, Jijun ; Guo, Fei</creatorcontrib><description>DNA methylation is an important biochemical process, and it has a close connection with many types of cancer. Research about DNA methylation can help us to understand the regulation mechanism and epigenetic reprogramming. Therefore, it becomes very important to recognize the methylation sites in the DNA sequence. In the past several decades, many computational methods-especially machine learning methods-have been developed since the high-throughout sequencing technology became widely used in research and industry. In order to accurately identify whether or not a nucleotide residue is methylated under the specific DNA sequence context, we propose a novel method that overcomes the shortcomings of previous methods for predicting methylation sites. We use -gram, multivariate mutual information, discrete wavelet transform, and pseudo amino acid composition to extract features, and train a sparse Bayesian learning model to do DNA methylation prediction. Five criteria-area under the receiver operating characteristic curve (AUC), Matthew's correlation coefficient (MCC), accuracy (ACC), sensitivity (SN), and specificity-are used to evaluate the prediction results of our method. On the benchmark dataset, we could reach 0.8632 on AUC, 0.8017 on ACC, 0.5558 on MCC, and 0.7268 on SN. Additionally, the best results on two scBS-seq profiled mouse embryonic stem cells datasets were 0.8896 and 0.9511 by AUC, respectively. When compared with other outstanding methods, our method surpassed them on the accuracy of prediction. The improvement of AUC by our method compared to other methods was at least 0.0399 . For the convenience of other researchers, our code has been uploaded to a file hosting service, and can be downloaded from: https://figshare.com/s/0697b692d802861282d3.</description><identifier>ISSN: 1422-0067</identifier><identifier>ISSN: 1661-6596</identifier><identifier>EISSN: 1422-0067</identifier><identifier>DOI: 10.3390/ijms19020511</identifier><identifier>PMID: 29419752</identifier><language>eng</language><publisher>Switzerland: MDPI AG</publisher><subject>Amino acid composition ; Bayesian analysis ; Biochemistry ; Cancer ; Computation ; Computer applications ; Correlation coefficients ; Deoxyribonucleic acid ; Discrete Wavelet Transform ; DNA ; DNA methylation ; Embryo cells ; feature selection ; k-gram ; Learning algorithms ; Methods ; multivariate mutual information ; Nucleotide sequence ; Physicochemical properties ; PseAAC ; scBS-seq profiled mouse embryonic stem cells ; Sensitivity analysis ; Sequences ; Sparse Bayesian learning ; Stem cell transplantation ; Stem cells ; support vector machine</subject><ispartof>International journal of molecular sciences, 2018-02, Vol.19 (2), p.511</ispartof><rights>Copyright MDPI AG 2018</rights><rights>2018 by the authors. 2018</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c478t-2b9dc62a659d489510a52f98093a1cf71081256d339d467a39dc5a819f308dd3</citedby><cites>FETCH-LOGICAL-c478t-2b9dc62a659d489510a52f98093a1cf71081256d339d467a39dc5a819f308dd3</cites><orcidid>0000-0003-0545-2754</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/2014799168/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/2014799168?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,25753,27924,27925,37012,37013,44590,53791,53793,75126</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/29419752$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Pan, Gaofeng</creatorcontrib><creatorcontrib>Jiang, Limin</creatorcontrib><creatorcontrib>Tang, Jijun</creatorcontrib><creatorcontrib>Guo, Fei</creatorcontrib><title>A Novel Computational Method for Detecting DNA Methylation Sites with DNA Sequence Information and Physicochemical Properties</title><title>International journal of molecular sciences</title><addtitle>Int J Mol Sci</addtitle><description>DNA methylation is an important biochemical process, and it has a close connection with many types of cancer. Research about DNA methylation can help us to understand the regulation mechanism and epigenetic reprogramming. Therefore, it becomes very important to recognize the methylation sites in the DNA sequence. In the past several decades, many computational methods-especially machine learning methods-have been developed since the high-throughout sequencing technology became widely used in research and industry. In order to accurately identify whether or not a nucleotide residue is methylated under the specific DNA sequence context, we propose a novel method that overcomes the shortcomings of previous methods for predicting methylation sites. We use -gram, multivariate mutual information, discrete wavelet transform, and pseudo amino acid composition to extract features, and train a sparse Bayesian learning model to do DNA methylation prediction. Five criteria-area under the receiver operating characteristic curve (AUC), Matthew's correlation coefficient (MCC), accuracy (ACC), sensitivity (SN), and specificity-are used to evaluate the prediction results of our method. On the benchmark dataset, we could reach 0.8632 on AUC, 0.8017 on ACC, 0.5558 on MCC, and 0.7268 on SN. Additionally, the best results on two scBS-seq profiled mouse embryonic stem cells datasets were 0.8896 and 0.9511 by AUC, respectively. When compared with other outstanding methods, our method surpassed them on the accuracy of prediction. The improvement of AUC by our method compared to other methods was at least 0.0399 . For the convenience of other researchers, our code has been uploaded to a file hosting service, and can be downloaded from: https://figshare.com/s/0697b692d802861282d3.</description><subject>Amino acid composition</subject><subject>Bayesian analysis</subject><subject>Biochemistry</subject><subject>Cancer</subject><subject>Computation</subject><subject>Computer applications</subject><subject>Correlation coefficients</subject><subject>Deoxyribonucleic acid</subject><subject>Discrete Wavelet Transform</subject><subject>DNA</subject><subject>DNA methylation</subject><subject>Embryo cells</subject><subject>feature selection</subject><subject>k-gram</subject><subject>Learning algorithms</subject><subject>Methods</subject><subject>multivariate mutual information</subject><subject>Nucleotide sequence</subject><subject>Physicochemical properties</subject><subject>PseAAC</subject><subject>scBS-seq profiled mouse embryonic stem cells</subject><subject>Sensitivity analysis</subject><subject>Sequences</subject><subject>Sparse Bayesian learning</subject><subject>Stem cell transplantation</subject><subject>Stem cells</subject><subject>support vector machine</subject><issn>1422-0067</issn><issn>1661-6596</issn><issn>1422-0067</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><sourceid>DOA</sourceid><recordid>eNpdkktvEzEQgFcIRB9w44wsceHQgB9rr31BilIekUqp1N4tx57NOtpdB9tblAP_HZOUKuU0lufzp5nxVNUbgj8wpvBHvxkSUZhiTsiz6pTUlM4wFs3zo_NJdZbSBmPKKFcvqxOqaqIaTk-r33N0He6hR4swbKdssg-j6dF3yF1wqA0RXUIGm_24RpfX831i1-8xdOszJPTL526fuoWfE4wW0HIs74YDY0aHbrpd8jbYDgZvi_wmhi3E7CG9ql60pk_w-iGeV3dfPt8tvs2ufnxdLuZXM1s3Ms_oSjkrqBFcuVoqTrDhtFUSK2aIbRuCJaFcuDIPV4vGlGC5kUS1DEvn2Hm1PGhdMBu9jX4wcaeD8Xp_EeJam1KP7UE3wIyDGoAqWstVrQRIgUmLGTbMcCiuTwfXdloN4CyMOZr-ifRpZvSdXod7zSXnDWNF8P5BEEMZWMp68MlC35sRwpQ0UUqJRgklCvruP3QTplj-J2mKSd0oRYQs1MWBsjGkFKF9LIZg_XdF9PGKFPztcQOP8L-dYH8ABw639A</recordid><startdate>20180208</startdate><enddate>20180208</enddate><creator>Pan, Gaofeng</creator><creator>Jiang, Limin</creator><creator>Tang, Jijun</creator><creator>Guo, Fei</creator><general>MDPI AG</general><general>MDPI</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>8G5</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>GUQSH</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>M2O</scope><scope>MBDVC</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0003-0545-2754</orcidid></search><sort><creationdate>20180208</creationdate><title>A Novel Computational Method for Detecting DNA Methylation Sites with DNA Sequence Information and Physicochemical Properties</title><author>Pan, Gaofeng ; Jiang, Limin ; Tang, Jijun ; Guo, Fei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c478t-2b9dc62a659d489510a52f98093a1cf71081256d339d467a39dc5a819f308dd3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Amino acid composition</topic><topic>Bayesian analysis</topic><topic>Biochemistry</topic><topic>Cancer</topic><topic>Computation</topic><topic>Computer applications</topic><topic>Correlation coefficients</topic><topic>Deoxyribonucleic acid</topic><topic>Discrete Wavelet Transform</topic><topic>DNA</topic><topic>DNA methylation</topic><topic>Embryo cells</topic><topic>feature selection</topic><topic>k-gram</topic><topic>Learning algorithms</topic><topic>Methods</topic><topic>multivariate mutual information</topic><topic>Nucleotide sequence</topic><topic>Physicochemical properties</topic><topic>PseAAC</topic><topic>scBS-seq profiled mouse embryonic stem cells</topic><topic>Sensitivity analysis</topic><topic>Sequences</topic><topic>Sparse Bayesian learning</topic><topic>Stem cell transplantation</topic><topic>Stem cells</topic><topic>support vector machine</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Pan, Gaofeng</creatorcontrib><creatorcontrib>Jiang, Limin</creatorcontrib><creatorcontrib>Tang, Jijun</creatorcontrib><creatorcontrib>Guo, Fei</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Health &amp; Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>Research Library (Alumni Edition)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>Research Library Prep</collection><collection>ProQuest Health &amp; Medical Complete (Alumni)</collection><collection>Health &amp; Medical Collection (Alumni Edition)</collection><collection>PML(ProQuest Medical Library)</collection><collection>Research Library</collection><collection>Research Library (Corporate)</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>ProQuest Central Basic</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>Directory of Open Access Journals</collection><jtitle>International journal of molecular sciences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Pan, Gaofeng</au><au>Jiang, Limin</au><au>Tang, Jijun</au><au>Guo, Fei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Novel Computational Method for Detecting DNA Methylation Sites with DNA Sequence Information and Physicochemical Properties</atitle><jtitle>International journal of molecular sciences</jtitle><addtitle>Int J Mol Sci</addtitle><date>2018-02-08</date><risdate>2018</risdate><volume>19</volume><issue>2</issue><spage>511</spage><pages>511-</pages><issn>1422-0067</issn><issn>1661-6596</issn><eissn>1422-0067</eissn><abstract>DNA methylation is an important biochemical process, and it has a close connection with many types of cancer. Research about DNA methylation can help us to understand the regulation mechanism and epigenetic reprogramming. Therefore, it becomes very important to recognize the methylation sites in the DNA sequence. In the past several decades, many computational methods-especially machine learning methods-have been developed since the high-throughout sequencing technology became widely used in research and industry. In order to accurately identify whether or not a nucleotide residue is methylated under the specific DNA sequence context, we propose a novel method that overcomes the shortcomings of previous methods for predicting methylation sites. We use -gram, multivariate mutual information, discrete wavelet transform, and pseudo amino acid composition to extract features, and train a sparse Bayesian learning model to do DNA methylation prediction. Five criteria-area under the receiver operating characteristic curve (AUC), Matthew's correlation coefficient (MCC), accuracy (ACC), sensitivity (SN), and specificity-are used to evaluate the prediction results of our method. On the benchmark dataset, we could reach 0.8632 on AUC, 0.8017 on ACC, 0.5558 on MCC, and 0.7268 on SN. Additionally, the best results on two scBS-seq profiled mouse embryonic stem cells datasets were 0.8896 and 0.9511 by AUC, respectively. When compared with other outstanding methods, our method surpassed them on the accuracy of prediction. The improvement of AUC by our method compared to other methods was at least 0.0399 . For the convenience of other researchers, our code has been uploaded to a file hosting service, and can be downloaded from: https://figshare.com/s/0697b692d802861282d3.</abstract><cop>Switzerland</cop><pub>MDPI AG</pub><pmid>29419752</pmid><doi>10.3390/ijms19020511</doi><orcidid>https://orcid.org/0000-0003-0545-2754</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1422-0067
ispartof International journal of molecular sciences, 2018-02, Vol.19 (2), p.511
issn 1422-0067
1661-6596
1422-0067
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_7e3ade4ee29248b496e8601f030a3a5e
source Publicly Available Content Database; PubMed Central
subjects Amino acid composition
Bayesian analysis
Biochemistry
Cancer
Computation
Computer applications
Correlation coefficients
Deoxyribonucleic acid
Discrete Wavelet Transform
DNA
DNA methylation
Embryo cells
feature selection
k-gram
Learning algorithms
Methods
multivariate mutual information
Nucleotide sequence
Physicochemical properties
PseAAC
scBS-seq profiled mouse embryonic stem cells
Sensitivity analysis
Sequences
Sparse Bayesian learning
Stem cell transplantation
Stem cells
support vector machine
title A Novel Computational Method for Detecting DNA Methylation Sites with DNA Sequence Information and Physicochemical Properties
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T00%3A59%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Novel%20Computational%20Method%20for%20Detecting%20DNA%20Methylation%20Sites%20with%20DNA%20Sequence%20Information%20and%20Physicochemical%20Properties&rft.jtitle=International%20journal%20of%20molecular%20sciences&rft.au=Pan,%20Gaofeng&rft.date=2018-02-08&rft.volume=19&rft.issue=2&rft.spage=511&rft.pages=511-&rft.issn=1422-0067&rft.eissn=1422-0067&rft_id=info:doi/10.3390/ijms19020511&rft_dat=%3Cproquest_doaj_%3E1999679696%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c478t-2b9dc62a659d489510a52f98093a1cf71081256d339d467a39dc5a819f308dd3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2014799168&rft_id=info:pmid/29419752&rfr_iscdi=true