{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T08:19:54Z","timestamp":1778055594640,"version":"3.51.4"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"19","license":[{"start":{"date-parts":[[2017,5,12]],"date-time":"2017-05-12T00:00:00Z","timestamp":1494547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/about_us\/legal\/notices"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U01 ES017166"],"award-info":[{"award-number":["U01 ES017166"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["K25 AR063761"],"award-info":[{"award-number":["K25 AR063761"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>5-Methylcytosine and 5-Hydroxymethylcytosine in DNA are major epigenetic modifications known to significantly alter mammalian gene expression. High-throughput assays to detect these modifications are expensive, labor-intensive, unfeasible in some contexts and leave a portion of the genome unqueried. Hence, we devised a novel, supervised, integrative learning framework to perform whole-genome methylation and hydroxymethylation predictions in CpG dinucleotides. Our framework can also perform imputation of missing or low quality data in existing sequencing datasets. Additionally, we developed infrastructure to perform in silico, high-throughput hypotheses testing on such predicted methylation or hydroxymethylation maps.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We test our approach on H1 human embryonic stem cells and H1-derived neural progenitor cells. Our predictive model is comparable in accuracy to other state-of-the-art DNA methylation prediction algorithms. We are the first to predict hydroxymethylation in silico with high whole-genome accuracy, paving the way for large-scale reconstruction of hydroxymethylation maps in mammalian model systems. We designed a novel, beam-search driven feature selection algorithm to identify the most discriminative predictor variables, and developed a platform for performing integrative analysis and reconstruction of the epigenome. Our toolkit DIRECTION provides predictions at single nucleotide resolution and identifies relevant features based on resource availability. This offers enhanced biological interpretability of results potentially leading to a better understanding of epigenetic gene regulation.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>http:\/\/www.pradiptaray.com\/direction, under CC-by-SA license.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btx316","type":"journal-article","created":{"date-parts":[[2017,5,11]],"date-time":"2017-05-11T20:58:32Z","timestamp":1494536312000},"page":"2986-2994","source":"Crossref","is-referenced-by-count":25,"title":["DIRECTION: a machine learning framework for predicting and characterizing DNA methylation and hydroxymethylation in mammalian genomes"],"prefix":"10.1093","volume":"33","author":[{"given":"Milos","family":"Pavlovic","sequence":"first","affiliation":[{"name":"Department of Biological Sciences, Center for Systems Biology, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pradipta","family":"Ray","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, Center for Systems Biology, The University of Texas at Dallas, Richardson, TX, USA"},{"name":"School of Behavioral and Brain Sciences, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kristina","family":"Pavlovic","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, Center for Systems Biology, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron","family":"Kotamarti","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, Center for Systems Biology, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Clinical Sciences, The University of Texas Southwestern Medical Center, Dallas, TX, USA"},{"name":"Department of Mathematical Sciences, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael Q","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, Center for Systems Biology, The University of Texas at Dallas, Richardson, TX, USA"},{"name":"TNLIST, Center for Synthetic and Systems Biology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2017,5,12]]},"reference":[{"key":"2023020206431643600_btx316-B1","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1038\/nchem.2064","article-title":"5-Hydroxymethylcytosine is a predominantly stable DNA modification","volume":"6","author":"Bachman","year":"2014","journal-title":"Nat. Chem"},{"key":"2023020206431643600_btx316-B2","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1016\/j.neuron.2009.08.005","article-title":"The cell-intrinsic requirement of Sox6 for cortical interneuron development","volume":"63","author":"Batista-Brito","year":"2009","journal-title":"Neuron"},{"key":"2023020206431643600_btx316-B3","doi-asserted-by":"crossref","first-page":"4302","DOI":"10.1016\/j.febslet.2005.07.002","article-title":"Prediction of methylated CpGs in DNA sequences using a support vector machine","volume":"579","author":"Bhasin","year":"2005","journal-title":"FEBS Lett"},{"key":"2023020206431643600_btx316-B4","volume-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","author":"Bishop","year":"2007","edition":"1st ed."},{"key":"2023020206431643600_btx316-B5","doi-asserted-by":"crossref","first-page":"e26.","DOI":"10.1371\/journal.pgen.0020026","article-title":"CpG island methylation in human lymphocytes is highly correlated with DNA sequence, repeats, and predicted DNA structure","volume":"2","author":"Bock","year":"2006","journal-title":"PLoS Genet"},{"key":"2023020206431643600_btx316-B6","doi-asserted-by":"crossref","first-page":"934","DOI":"10.1126\/science.1220671","article-title":"Quantitative sequencing of 5-methylcytosine and 5-hydroxymethylcytosine at single-base resolution","volume":"336","author":"Booth","year":"2012","journal-title":"Science"},{"key":"2023020206431643600_btx316-B7","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn"},{"key":"2023020206431643600_btx316-B8","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1101\/gr.082800.108","article-title":"Global analysis of the insulator binding protein CTCF in chromatin barrier regions reveals demarcation of active and repressive domains","volume":"19","author":"Cuddapah","year":"2009","journal-title":"Genome Res"},{"key":"2023020206431643600_btx316-B9","doi-asserted-by":"crossref","first-page":"10713","DOI":"10.1073\/pnas.0602949103","article-title":"Computational prediction of methylation status in human genomic sequences","volume":"103","author":"Das","year":"2006","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"2023020206431643600_btx316-B10","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1038\/nmeth.1906","article-title":"ChromHMM: automating chromatin-state discovery and characterization","volume":"9","author":"Ernst","year":"2012","journal-title":"Nat. Methods"},{"key":"2023020206431643600_btx316-B11","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1038\/nbt.3157","article-title":"Large-scale imputation of epigenomic datasets for systematic annotation of diverse human tissues","volume":"33","author":"Ernst","year":"2015","journal-title":"Nat. Biotechnol"},{"key":"2023020206431643600_btx316-B12","first-page":"132","volume-title":"Genomics","author":"Fan","year":"2016"},{"key":"2023020206431643600_btx316-B13","doi-asserted-by":"crossref","first-page":"1827","DOI":"10.1073\/pnas.89.5.1827","article-title":"A genomic sequencing protocol that yields a positive display of 5-methylcytosine residues in individual DNA strands","volume":"89","author":"Frommer","year":"1992","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"2023020206431643600_btx316-B14","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1038\/nprot.2010.190","article-title":"Preparation of reduced representation bisulfite sequencing libraries for genome-scale DNA methylation profiling","volume":"6","author":"Gu","year":"2011","journal-title":"Nat. Protoc"},{"key":"2023020206431643600_btx316-B15","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1126\/science.1229277","article-title":"Germline DNA demethylation dynamics and imprint erasure through 5-hydroxymethylcytosine","volume":"339","author":"Hackett","year":"2013","journal-title":"Science"},{"key":"2023020206431643600_btx316-B16","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1016\/j.neuron.2013.03.031","article-title":"Protocadherin 17 regulates presynaptic assembly in topographic corticobasal Ganglia circuits","volume":"78","author":"Hoshina","year":"2013","journal-title":"Neuron"},{"key":"2023020206431643600_btx316-B17","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nrg3230","article-title":"Functions of DNA methylation: islands, start sites, gene bodies and beyond","volume":"13","author":"Jones","year":"2012","journal-title":"Nat. Rev. Genet"},{"key":"2023020206431643600_btx316-B18","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1016\/j.ygeno.2006.01.002","article-title":"The length of CpG islands is associated with the distribution of Alu and L1 retroelements","volume":"87","author":"Kang","year":"2006","journal-title":"Genomics"},{"key":"2023020206431643600_btx316-B19","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1038\/nsmb.2372","article-title":"5-hmC in the brain is abundant in synaptic genes and shows differences at the exon-intron boundary","volume":"19","author":"Khare","year":"2012","journal-title":"Nat. Struct. Mol. Biol"},{"key":"2023020206431643600_btx316-B20","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1093\/hmg\/ddt453","article-title":"Dynamic changes in DNA methylation and hydroxymethylation when hES cells undergo differentiation toward a neuronal lineage","volume":"23","author":"Kim","year":"2014","journal-title":"Hum. Mol. Genet"},{"key":"2023020206431643600_btx316-B21","first-page":"284","author":"Koller","year":"1996"},{"key":"2023020206431643600_btx316-B22","doi-asserted-by":"crossref","first-page":"1571","DOI":"10.1093\/bioinformatics\/btr167","article-title":"Bismark: a flexible aligner and methylation caller for Bisulfite-Seq applications","volume":"27","author":"Krueger","year":"2011","journal-title":"Bioinformatics"},{"key":"2023020206431643600_btx316-B23","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/nature14248","article-title":"Integrative analysis of 111 reference human epigenomes","volume":"518","author":"Kundaje","year":"2015","journal-title":"Nature"},{"key":"2023020206431643600_btx316-B24","doi-asserted-by":"crossref","first-page":"6376","DOI":"10.1073\/pnas.1216822110","article-title":"Probing DNA shape and methylation state on a genomic scale with DNase I","volume":"110","author":"Lazarovici","year":"2013","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"2023020206431643600_btx316-B25","doi-asserted-by":"crossref","first-page":"3515","DOI":"10.1093\/nar\/gkt1380","article-title":"Predicting DNA methylation level across human tissues","volume":"42","author":"Ma","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2023020206431643600_btx316-B26","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1016\/j.patcog.2009.09.003","article-title":"Optimal feature selection for support vector machines","volume":"43","author":"Nguyen","year":"2010","journal-title":"Pattern Recognit"},{"key":"2023020206431643600_btx316-B27","doi-asserted-by":"crossref","first-page":"2787","DOI":"10.1242\/jcs.015123","article-title":"Mammalian cytosine methylation at a glance","volume":"122","author":"Ooi","year":"2009","journal-title":"J. Cell. Sci"},{"key":"2023020206431643600_btx316-B28","doi-asserted-by":"crossref","first-page":"2645","DOI":"10.1093\/bioinformatics\/btt459","article-title":"MLML: consistent simultaneous estimates of DNA methylation and hydroxymethylation","volume":"29","author":"Qu","year":"2013","journal-title":"Bioinformatics"},{"key":"2023020206431643600_btx316-B29","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1038\/nrg3682","article-title":"Transcriptional enhancers: from properties to genome-wide predictions","volume":"15","author":"Shlyueva","year":"2014","journal-title":"Nat. Rev. Genet"},{"key":"2023020206431643600_btx316-B30","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1038\/nbt.1732","article-title":"Selective chemical labeling reveals the genome-wide distribution of 5-hydroxymethylcytosine","volume":"29","author":"Song","year":"2011","journal-title":"Nat. Biotechnol"},{"key":"2023020206431643600_btx316-B31","doi-asserted-by":"crossref","first-page":"R54","DOI":"10.1186\/gb-2011-12-6-r54","article-title":"5-Hydroxymethylcytosine is associated with enhancers and gene bodies in human embryonic stem cells","volume":"12","author":"Stroud","year":"2011","journal-title":"Genome Biol"},{"key":"2023020206431643600_btx316-B32","doi-asserted-by":"crossref","first-page":"e1004585","DOI":"10.1371\/journal.pgen.1004585","article-title":"Hydroxymethylated cytosines are associated with elevated C to G transversion rates","volume":"10","author":"Supek","year":"2014","journal-title":"PLoS Genet"},{"key":"2023020206431643600_btx316-B33","doi-asserted-by":"crossref","first-page":"e84","DOI":"10.1093\/nar\/gkt091","article-title":"Genome-wide comparison of DNA hydroxymethylation in mouse embryonic stem cells and neural progenitor cells by a new comparative hMeDIP-seq method","volume":"41","author":"Tan","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2023020206431643600_btx316-B34","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1101\/gr.164418.113","article-title":"Nucleosome repositioning links DNA (de) methylation and differential CTCF binding during stem cell development","volume":"24","author":"Teif","year":"2014","journal-title":"Genome Res"},{"key":"2023020206431643600_btx316-B35","doi-asserted-by":"crossref","first-page":"5500","DOI":"10.1093\/hmg\/dds394","article-title":"Genome-wide DNA hydroxymethylation changes are associated with neurodevelopmental genes in the developing human cerebellum","volume":"21","author":"Wang","year":"2012","journal-title":"Hum. Mol. Genet"},{"key":"2023020206431643600_btx316-B36","doi-asserted-by":"crossref","first-page":"19598","DOI":"10.1038\/srep19598","article-title":"Predicting DNA Methylation State of CpG Dinucleotide Using Genome Topological Features and Deep Networks","volume":"6","author":"Wang","year":"2016","journal-title":"Sci. Rep"},{"key":"2023020206431643600_btx316-B37","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1038\/nmeth.3065","article-title":"Predicting the human epigenome from DNA motifs","volume":"12","author":"Whitaker","year":"2015","journal-title":"Nat. Methods"},{"key":"2023020206431643600_btx316-B38","doi-asserted-by":"crossref","first-page":"e35327.","DOI":"10.1371\/journal.pone.0035327","article-title":"Linking the epigenome to the genome: correlation of different features to DNA methylation of CpG islands","volume":"7","author":"Wrzodek","year":"2012","journal-title":"PloS One"},{"key":"2023020206431643600_btx316-B39","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1101\/gad.2036011","article-title":"Genome-wide analysis of 5-hydroxymethylcytosine distribution reveals its dual function in transcriptional regulation in mouse embryonic stem cells","volume":"25","author":"Wu","year":"2011","journal-title":"Genes Dev"},{"key":"2023020206431643600_btx316-B40","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1038\/cr.2013.22","article-title":"Dynamics of 5-methylcytosine and 5-hydroxymethylcytosine during germ cell reprogramming","volume":"23","author":"Yamaguchi","year":"2013","journal-title":"Cell Res"},{"key":"2023020206431643600_btx316-B41","doi-asserted-by":"crossref","first-page":"8410","DOI":"10.1038\/srep08410","article-title":"Chromatin modifications and genomic contexts linked to dynamic DNA methylation patterns across human cell types","volume":"5","author":"Yan","year":"2015","journal-title":"Sci. Rep"},{"key":"2023020206431643600_btx316-B42","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1038\/onc.2012.67","article-title":"Tumor development is associated with decrease of TET gene expression and 5-methylcytosine hydroxylation","volume":"32","author":"Yang","year":"2013","journal-title":"Oncogene"},{"key":"2023020206431643600_btx316-B43","doi-asserted-by":"crossref","first-page":"1368","DOI":"10.1016\/j.cell.2012.04.027","article-title":"Base-resolution analysis of 5-hydroxymethylcytosine in the mammalian genome","volume":"149","author":"Yu","year":"2012","journal-title":"Cell"},{"key":"2023020206431643600_btx316-B44","doi-asserted-by":"crossref","first-page":"14.","DOI":"10.1186\/s13059-015-0581-9","article-title":"Predicting genome-wide DNA methylation using methylation marks, genomic position, and DNA regulatory elements","volume":"16","author":"Zhang","year":"2015","journal-title":"Genome Biol"},{"key":"2023020206431643600_btx316-B45","doi-asserted-by":"crossref","first-page":"1062","DOI":"10.1016\/j.molcel.2016.10.030","article-title":"Isoform Switch of TET1 Regulates DNA Demethylation and Mouse Development","volume":"64","author":"Zhang","year":"2016","journal-title":"Mol. Cell"},{"key":"2023020206431643600_btx316-B46","article-title":"Complete anytime beam search","author":"Zhang","year":"1998","journal-title":"Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI\/IAAI)"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/19\/2986\/49041095\/bioinformatics_33_19_2986.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/19\/2986\/49041095\/bioinformatics_33_19_2986.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T06:44:24Z","timestamp":1675320264000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/33\/19\/2986\/3823310"}},"subtitle":[],"editor":[{"given":"Inanc","family":"Birol","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2017,5,12]]},"references-count":46,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2017,10,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx316","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,10,1]]},"published":{"date-parts":[[2017,5,12]]}}}