Research Article

School of Information Science & Technology, Dalian Maritime University, Dalian, 116026, China

*Author for correspondence:

E-mail Address: mabaoshan@dlmu.edu.cn

https://orcid.org/0000-0003-1629-1968

School of Information Science & Technology, Dalian Maritime University, Dalian, 116026, China

Search for more papers by this author

Yu Liu

School of Information Science & Technology, Dalian Maritime University, Dalian, 116026, China

Search for more papers by this author

Yiwen Shen

School of Information Science & Technology, Dalian Maritime University, Dalian, 116026, China

Search for more papers by this author

Di Li

Department of Neuro Intervention, Dalian Medical University affiliated Dalian Municipal Central Hospital, Dalian, 116033, China

Search for more papers by this author

Shuxin Liu

Department of Nephrology, Dalian Medical University affiliated Dalian Municipal Central Hospital, Dalian, 116033, China

Search for more papers by this author

Fengju Song

Department of Epidemiology & Biostatistics, Key Laboratory of Molecular Cancer Epidemiology, Tianjin, National Clinical Research Center of Cancer, Tianjin Medical University Cancer Institute & Hospital, Tianjin, 300060, China

Search for more papers by this author

Published Online:13 Mar 2024https://doi.org/10.2217/epi-2023-0114

View article

Abstract

Aim: To predict base-resolution DNA methylation in cancerous and paracancerous tissues. Material & methods: We collected six cancer DNA methylation datasets from The Cancer Genome Atlas and five cancer datasets from Gene Expression Omnibus and established machine learning models using paired cancerous and paracancerous tissues. Tenfold cross-validation and independent validation were performed to demonstrate the effectiveness of the proposed method. Results: The developed cross-tissue prediction models can substantially increase the accuracy at more than 68% of CpG sites and contribute to enhancing the statistical power of differential methylation analyses. An XGBoost model leveraging multiple correlating CpGs may elevate the prediction accuracy. Conclusion: This study provides a powerful tool for DNA methylation analysis and has the potential to gain new insights into cancer research from epigenetics.

Keywords:

Papers of special note have been highlighted as: • of interest; •• of considerable interest

References

1. Li E. Chromatin modification and epigenetic reprogramming in mammalian development. Nat. Rev. Genet. 3(9), 662–673 (2002).
Medline CASGoogle Scholar
2. Berdasco M, Esteller M. Aberrant epigenetic landscape in cancer: how cellular identity goes awry. Dev. Cell 19(5), 698–711 (2010).
Medline CASGoogle Scholar
3. Koch A, Joosten SC, Feng Z et al. Analysis of DNA methylation in cancer: location revisited. Nat. Rev. Clin. Oncol. 15(7), 459–466 (2018).
Medline CASGoogle Scholar
4. Das PM, Singal R. DNA methylation and cancer. J. Clin. Oncol. 22(22), 4632–4642 (2004).
Medline CASGoogle Scholar
5. Crowley E, Di Nicolantonio F, Loupakis F, Bardelli A. Liquid biopsy: monitoring cancer-genetics in the blood. Nat. Rev. Clin. Oncol. 10(8), 472–484 (2013).
Medline CASGoogle Scholar
6. Li ADR, Liu Y, Plott J, Chen L, Montgomery JS, Shih A. Multi-bevel needle design enabling accurate insertion in biopsy for cancer diagnosis. IEEE Trans. Biomed. Eng. 68(5), 1477–1486 (2021).
MedlineGoogle Scholar
7. Kashiwagi S, Asano Y, Goto W et al. Optical see-through head-mounted display (OST-HMD)-assisted needle biopsy for breast tumor: a technical innovation. In Vivo 36(2), 848–852 (2022).
MedlineGoogle Scholar
8. Santiago L, Candelaria RP, Huang ML. MR imaging-guided breast interventions: indications, key principles, and imaging-pathology correlation. Magn. Reson. Imaging Clin. N. Am. 26(2), 235–246 (2018).
MedlineGoogle Scholar
9. Xu W, Liu X, Leng F, Li W. Blood-based multi-tissue gene expression inference with Bayesian ridge regression. Bioinformatics 36(12), 3788–3794 (2020).
Medline CASGoogle Scholar
10. Okada H, Uza N, Matsumori T et al. A novel technique for mapping biopsy of bile duct cancer. Endoscopy 53(6), 647–651 (2021).
MedlineGoogle Scholar
11. Stępniak P, Maycock M, Wojdan K et al. Microarray Inspector: tissue cross contamination detection tool for microarray data. Acta Biochim. Pol. 60(4), 647–655 (2013).
MedlineGoogle Scholar
12. Guibert N, Tsukada H, Hwang DH et al. Liquid biopsy of fine-needle aspiration supernatant for lung cancer genotyping. Lung Cancer 122, 72–75 (2018).
MedlineGoogle Scholar
13. Masse R, Duvernay J, Korbi S, Majoufre C, Schlund M. Oral carcinoma cuniculatum, a rare variant of squamous cell carcinoma. J. Stomatol. Oral Maxillofac. Surg. 125(4), 101729 (2023).
MedlineGoogle Scholar
14. Halin S, Hammarsten P, Adamo H, Wikström P, Bergh A. Tumor indicating normal tissue could be a new source of diagnostic and prognostic markers for prostate cancer. Expert Opin. Med. Diagn. 5(1), 37–47 (2011). • A biopsy of prostate cancer commonly contains only normal prostate tissue.
MedlineGoogle Scholar
15. Ogawa T, Ito K, Koshita S et al. Usefulness of cholangioscopic-guided mapping biopsy using SpyGlass DS for preoperative evaluation of extrahepatic cholangiocarcinoma: a pilot study. Endosc. Int. Open 6(2), e199–e204 (2018).
MedlineGoogle Scholar
16. Deftereos G, Sandoval A, Furtado LV, Bronner M, Matynia AP. Successful lung cancer EGFR sequencing from DNA extracted from TTF-1 immunohistochemistry slides: a new means to extend insufficient tissue. Hum. Pathol. 97, 52–59 (2020).
Medline CASGoogle Scholar
17. Teschendorff A, Gao Y, Jones A et al. DNA methylation outliers in normal breast tissue identify field defects that are enriched in cancer. Nat. Commun. 7, 10478 (2016).
Medline CASGoogle Scholar
18. Møller M, Strand SH, Mundbjerg K et al. Heterogeneous patterns of DNA methylation-based field effects in histologically normal prostate tissue from cancer patients. Sci. Rep. 7(1), 1–14 (2017).
Medline CASGoogle Scholar
19. Hsu C-H, Hsiao C-W, Sun C-A et al. Multiple gene promoter methylation and clinical stage in adjacent normal tissues: effect on prognosis of colorectal cancer in Taiwan. Sci. Rep. 10(1), 1–11 (2020).
MedlineGoogle Scholar
20. Johnson KC, Houseman EA, King JE, Christensen BC. Normal breast tissue DNA methylation differences at regulatory elements are associated with the cancer risk factor age. Breast Cancer Res. 19(1), 81 (2017).
MedlineGoogle Scholar
21. Sun JX, He Y, Sanford E et al. A computational approach to distinguish somatic vs. germline origin of genomic alterations from deep sequencing of cancer specimens without a matched normal. PLoS Comp. Biol. 14(2), e1005965 (2018). • A key constraint in genomic testing in oncology is that matched normal specimens are not commonly obtained in clinical practice.
MedlineGoogle Scholar
22. Utsunomiya T, Ishikawa D, Asanoma M et al. Specific miRNA expression profiles of non-tumor liver tissue predict a risk for recurrence of hepatocellular carcinoma. Hepatol. Res. 44(6), 631–638 (2014).
Medline CASGoogle Scholar
23. Tomimaru Y, Sasaki Y, Yamada T et al. Fibrosis in non-cancerous tissue is the unique prognostic factor for primary hepatocellular carcinoma without hepatitis B or C viral infection. World J. Surg. 30(9), 1729–1735 (2006).
MedlineGoogle Scholar
24. Gao K, Zhang F, Chen K et al. Expression patterns and prognostic value of RUNX genes in kidney cancer. Sci. Rep. 11(1), 14934 (2021).
Medline CASGoogle Scholar
25. Pan R, Zhou C, Dai J et al. Endothelial PAS domain protein 1 gene hypomethylation is associated with colorectal cancer in Han Chinese. Exp. Ther. Med. 16(6), 4983–4990 (2018).
Medline CASGoogle Scholar
26. Jia Z, Wang Y, Xue J et al. DNA methylation patterns at and beyond the histological margin of early-stage invasive lung adenocarcinoma radiologically manifested as pure ground-glass opacity. Clin. Epigenetics 13(1), 153 (2021).
Medline CASGoogle Scholar
27. Byun HM, Siegmund KD, Pan F, Weisenberger DJ, Yang AS. Epigenetic profiling of somatic tissues from human autopsy specimens identifies tissue- and individual-specific DNA methylation patterns. Hum. Mol. Genet. 18(24), 4808–4817 (2009).
Medline CASGoogle Scholar
28. Edgar RD, Jones MJ, Meaney MJ, Turecki G, Kobor MS. BECon: a tool for interpreting DNA methylation findings from blood in the context of brain. Transl. Psychiatry 7(8), e1187 (2017).
Medline CASGoogle Scholar
29. Smith AK, Kilaru V, Klengel T et al. DNA extracted from saliva for methylation studies of psychiatric traits: evidence tissue specificity and relatedness to brain. Am. J. Med. Genet. B Neuropsychiatr. Genet. 168(1), 36–44 (2015).
CASGoogle Scholar
30. Lee Y-S, Zhang H, Jiang Y et al. Epigenome-scale comparison of DNA methylation between blood leukocytes and bronchial epithelial cells. Epigenomics 13(7), 485–498 (2021).
CASGoogle Scholar
31. Abraham JE, Maranian MJ, Spiteri I et al. Saliva samples are a viable alternative to blood samples as a source of DNA for high throughput genotyping. BMC Med. Genomics 5(1), 1–6 (2012).
MedlineGoogle Scholar
32. De Carli MM, Baccarelli AA, Trevisi L et al. Epigenome-wide cross-tissue predictive modeling and comparison of cord blood and placental methylation in a birth cohort. Epigenomics 9(3), 231–240 (2017).
Google Scholar
33. Ma B, Allard C, Bouchard L et al. Locus-specific DNA methylation prediction in cord blood and placenta. Epigenetics 14(4), 405–420 (2019). •• This study built prediction models for placenta methylation based on cord blood data.
MedlineGoogle Scholar
34. Ma B, Wilker EH, Willis-Owen SA et al. Predicting DNA methylation level across human tissues. Nucleic Acids Res. 42(6), 3515–3528 (2014). •• Using DNA methylation in easy-to-access tissues to predict DNA methylation in hard-to-access tissues is very meaningful.
Medline CASGoogle Scholar
35. Chen T, Guestrin C. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, NY, USA, 785–794 (2016).
Google Scholar
36. Li W, Yin Y, Quan X, Zhang H. Gene expression value prediction based on XGBoost algorithm. Front. Genet. 10, 1077 (2019).
Medline CASGoogle Scholar
37. Ma B, Chai B, Dong H et al. Diagnostic classification of cancers using DNA methylation of paracancerous tissues. Sci. Rep. 12(1), 10646 (2022).
Medline CASGoogle Scholar
38. Zhou W, Triche TJ Jr, Laird PW, Shen H. SeSAMe: reducing artifactual detection of DNA methylation by Infinium BeadChips in genomic deletions. Nucleic Acids Res. 46(20), e123 (2018).
MedlineGoogle Scholar
39. Zhou W, Laird PW, Shen H. Comprehensive characterization, annotation and innovative use of Infinium DNA methylation BeadChip probes. Nucleic Acids Res. 45(4), e22 (2017).
MedlineGoogle Scholar
40. Chen YA, Lemire M, Choufani S et al. Discovery of cross-reactive probes and polymorphic CpGs in the Illumina Infinium HumanMethylation450 microarray. Epigenetics 8(2), 203–209 (2013).
Medline CASGoogle Scholar
41. Vapnik VN. An overview of statistical learning theory. IEEE Trans. Neural Netw. 10(5), 988–999 (1999).
Medline CASGoogle Scholar
42. Bell JT, Pai AA, Pickrell JK et al. DNA methylation patterns associate with genetic and gene expression variation in HapMap cell lines. Genome Biol. 12(1), R10 (2011).
Medline CASGoogle Scholar
43. Cecilia L, Dodd IB, Kim S, Haerter JO. DNA methylation in human epigenomes depends on local topology of CpG sites. Nucleic Acids Res. 44(11), 5123–5132 (2016).
MedlineGoogle Scholar
44. Eckhardt F, Lewin J, Cortese R et al. DNA methylation profiling of human chromosomes 6, 20 and 22. Nat. Genet. 38(12), 1378–1385 (2006).
Medline CASGoogle Scholar
45. Morris TJ, Butcher LM, Feber A et al. ChAMP: 450k chip analysis methylation pipeline. Bioinformatics 30(3), 428–430 (2014).
Medline CASGoogle Scholar
46. Phipson B, Maksimovic J, Oshlack A. missMethyl: an R package for analyzing data from Illumina's HumanMethylation450 platform. Bioinformatics 32(2), 286–288 (2016).
Medline CASGoogle Scholar
47. Sato T, Arai E, Kohno T et al. Epigenetic clustering of lung adenocarcinomas based on DNA methylation profiles in adjacent lung tissue: its correlation with smoking history and chronic obstructive pulmonary disease. Int. J. Cancer 135(2), 319–334 (2014).
Medline CASGoogle Scholar
48. Robin X, Turck N, Hainard A et al. pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinformatics 12(1), 1–8 (2011).
MedlineGoogle Scholar
49. Çalışkan M, Cusanovich DA, Ober C, Gilad Y. The effects of EBV transformation on gene expression levels and methylation profiles. Hum. Mol. Genet. 20(8), 1643–1652 (2011).
Medline CASGoogle Scholar
50. Sandoval J, Heyn H, Moran S et al. Validation of a DNA methylation microarray for 450,000 CpG sites in the human genome. Epigenetics 6(6), 692–702 (2011).
Medline CASGoogle Scholar
51. Hachiya T, Furukawa R, Shiwa Y et al. Genome-wide identification of inter-individually variable DNA methylation sites improves the efficacy of epigenetic association studies. NPJ Genom. Med. 2(1), 1–14 (2017).
Medline CASGoogle Scholar
52. Du L, Pertsemlidis A. Cancer and neurodegenerative disorders: pathogenic convergence through microRNA regulation. J. Mol. Cell Biol. 3(3), 176–180 (2011).
Medline CASGoogle Scholar
53. Li H, Siddiqui O, Zhang H, Guan Y. Joint learning improves protein abundance prediction in cancers. BMC Biol. 17(1), 107 (2019).
Medline CASGoogle Scholar
54. Cokus SJ, Feng S, Zhang X et al. Shotgun bisulphite sequencing of the Arabidopsis genome reveals DNA methylation patterning. Nature 452(7184), 215–219 (2008).
Medline CASGoogle Scholar
55. Fang F, Fan S, Zhang X, Zhang MQ. Predicting methylation status of CpG islands in the human brain. Bioinformatics 22(18), 2204–2209 (2006). •• It is necessary to develop in silico approaches for predicting methylation status of CpG islands.
Medline CASGoogle Scholar
56. Jones, Peter A. Functions of DNA methylation: islands, start sites, gene bodies and beyond. Nat. Rev. Genet. 13(7), 484–492 (2012).
Medline CASGoogle Scholar
57. Irizarry RA, Laddacosta C, Wen B et al. Genome-wide methylation analysis of human colon cancer reveals similar hypo- and hypermethylation at conserved tissue-specific CpG island shores. Nat. Genet. 41(2), 178–186 (2009).
Medline CASGoogle Scholar
58. Meng J, Gao L, Zhang M, Gao S, Fan S, Liang C. Systematic investigation of the prognostic value of cell division cycle-associated proteins for clear cell renal cell carcinoma patients. Biomark. Med. 14(3), 223–238 (2020).
CASGoogle Scholar
59. Angermueller C, Lee HJ, Reik W, Stegle O. DeepCpG: accurate prediction of single-cell DNA methylation states using deep learning. Genome Biol. 18(1), 67 (2017).
MedlineGoogle Scholar
60. Ni P, Huang N, Zhang Z et al. DeepSignal: detecting DNA methylation state from Nanopore sequencing reads using deep-learning. Bioinformatics 35(22), 4586–4595 (2019).
Medline CASGoogle Scholar
61. Wu C, Yao S, Li X, Chen C, Hu X. Genome-wide prediction of DNA methylation using DNA composition and sequence complexity in human. Int. J. Mol. Sci. 18(2), 420 (2017).
MedlineGoogle Scholar
62. Luo X, Wang F, Wang G, Zhao Y. Identification of methylation states of DNA regions for Illumina methylation BeadChip. BMC Genomics 21(1), 1–10 (2020).
Google Scholar
63. Tian Q, Zou J, Tang J, Fang Y, Yu Z, Fan S. MRCNN: a deep learning model for regression of genome-wide DNA methylation. BMC Genomics 20(2), 1–10 (2019).
MedlineGoogle Scholar
64. Rao JS, Zhang H, Kobetz E, Aldrich MC, Conway D. Predicting DNA methylation from genetic data lacking racial diversity using shared classified random effects. Genomics 113(1 Pt 2), 1018–1028 (2021).
Medline CASGoogle Scholar
65. Fu L, Peng Q, Chai L. Predicting DNA methylation states with hybrid information based deep-learning model. IEEE/ACM Trans. Comput. Biol. Bioinform. 17(5), 1721–1728 (2019).
MedlineGoogle Scholar
66. Zhang W, Spector TD, Deloukas P, Bell JT, Engelhardt BE. Predicting genome-wide DNA methylation using methylation marks, genomic position, and DNA regulatory elements. Genome Bio. 16(1), 14 (2015). • This research characterized genome-wide DNA methylation patterns and built a random forest classifier to predict methylation levels based on multiple features.
MedlineGoogle Scholar
67. Tang J, Zou J, Zhang X et al. PretiMeth: precise prediction models for DNA methylation based on single methylation mark. BMC Genomics 21(1), 1–15 (2020).
Google Scholar
68. Bock C, Walter J, Paulsen M, Lengauer T. CpG island mapping by epigenome prediction. PLoS Comput. Biol. 3(6), e110 (2007).
MedlineGoogle Scholar
69. Bock C, Paulsen M, Tierling S, Mikeska T, Lengauer T, Walter J. CpG island methylation in human lymphocytes is highly correlated with DNA sequence, repeats, and predicted DNA structure. PLoS Genet. 2(3), e26 (2006).
MedlineGoogle Scholar
70. Zheng H, Wu H, Li J, Jiang S-W. CpGIMethPred: computational model for predicting methylation status of CpG islands in human genome. BMC Med. Genomics 6(1), 1–12 (2013).
MedlineGoogle Scholar
71. Fan S, Zhang MQ, Zhang X. Histone methylation marks play important roles in predicting the methylation status of CpG islands. Biochem. Biophys. Res. Commun. 374(3), 559–564 (2008).
Medline CASGoogle Scholar
72. Feltus FA, Lee EK, Costello JF, Plass C, Vertino PM. Predicting aberrant CpG island methylation. Proc. Natl Acad. Sci. U. S. A. 100(21), 12253–12258 (2003).
Medline CASGoogle Scholar
73. Das R, Dimitrova N, Xuan Z et al. Computational prediction of methylation status in human genomic sequences. Proc. Natl Acad. Sci. U. S. A. 103(28), 10713–10716 (2006).
Medline CASGoogle Scholar
74. Hazra A, Gogtay N. Biostatistics series module 6: correlation and linear regression. Indian J. Dermatol. 61(6), 593–601 (2016).
MedlineGoogle Scholar
75. Hansen KD, Timp W, Bravo HC et al. Increased methylation variation in epigenetic domains across cancer types. Nat. Genet. 43(8), 768–775 (2011).
Medline CASGoogle Scholar

Ahead of Print

Supplemental Materials

Metrics

Downloaded 41 times

History

Received 3 April 2023

Accepted 20 February 2024

Published online 13 March 2024

Information

Keywords

Supplementary data

To view the supplementary data that accompany this paper please visit the journal website at: www.futuremedicine.com/doi/suppl/10.2217/epi-2023-0114

Author contributions

Conceptualization: B Ma, S Liu, F Song and S Zhang; methodology: B Ma and S Zhang; investigation: B Ma, F Song, S Zhang and Y Liu; visualization: S Zhang; supervision: B Ma, S Liu and F Song; writing – original draft: S Zhang; writing – review and editing: B Ma, S Liu, F Song, S Zhang, Y Liu, Y Shen and D Li. All authors read and approved the final manuscript.

Financial disclosure

This work was supported by the Chinese National Key Research and Development Project (no. 2021YFC2500400) and the National Natural Science Foundation of China (no. 61471078). The authors have no other relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript apart from those disclosed.

Competing interests disclosure

The authors have no competing interests or relevant affiliations with any organization or entity with the subject matter or materials discussed in the manuscript. This includes employment, consultancies, honoraria, stock ownership or options, expert testimony, grants or patents received or pending or royalties.

Writing disclosure

No writing assistance was utilized in the production of this manuscript.

Data sharing statement

The source code and demo data have been deposited at: https://github.com/lab319/DNAm_prediction_CT_PT.

PDF download

Predicting locus-specific DNA methylation levels in cancer and paracancer tissues

Abstract

References