Incorporating methylation genome information improves prediction accuracy for drug treatment responses
Abstract Background An accumulation of evidence has revealed the important role of epigenetic factors in explaining the etiopathogenesis of human diseases. Several empirical studies have successfully incorporated methylation data into models for disease prediction. However, it is still a challenge t...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2018-09-01
|
| Series: | BMC Genetics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12863-018-0644-5 |
| _version_ | 1818538975846989824 |
|---|---|
| author | Xiaoxuan Xia Haoyi Weng Ruoting Men Rui Sun Benny Chung Ying Zee Ka Chun Chong Maggie Haitian Wang |
| author_facet | Xiaoxuan Xia Haoyi Weng Ruoting Men Rui Sun Benny Chung Ying Zee Ka Chun Chong Maggie Haitian Wang |
| author_sort | Xiaoxuan Xia |
| collection | DOAJ |
| description | Abstract Background An accumulation of evidence has revealed the important role of epigenetic factors in explaining the etiopathogenesis of human diseases. Several empirical studies have successfully incorporated methylation data into models for disease prediction. However, it is still a challenge to integrate different types of omics data into prediction models, and the contribution of methylation information to prediction remains to be fully clarified. Results A stratified drug-response prediction model was built based on an artificial neural network to predict the change in the circulating triglyceride level after fenofibrate intervention. Associated single-nucleotide polymorphisms (SNPs), methylation of selected cytosine-phosphate-guanine (CpG) sites, age, sex, and smoking status, were included as predictors. The model with selected SNPs achieved a mean 5-fold cross-validation prediction error rate of 43.65%. After adding methylation information into the model, the error rate dropped to 41.92%. The combination of significant SNPs, CpG sites, age, sex, and smoking status, achieved the lowest prediction error rate of 41.54%. Conclusions Compared to using SNP data only, adding methylation data in prediction models slightly improved the error rate; further prediction error reduction is achieved by a combination of genome, methylation genome, and environmental factors. |
| first_indexed | 2024-12-11T21:35:57Z |
| format | Article |
| id | doaj.art-884aa8ac31be49c9bfd5065ae2ecdc70 |
| institution | Directory Open Access Journal |
| issn | 1471-2156 |
| language | English |
| last_indexed | 2024-12-11T21:35:57Z |
| publishDate | 2018-09-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Genetics |
| spelling | doaj.art-884aa8ac31be49c9bfd5065ae2ecdc702022-12-22T00:50:00ZengBMCBMC Genetics1471-21562018-09-0119S1677110.1186/s12863-018-0644-5Incorporating methylation genome information improves prediction accuracy for drug treatment responsesXiaoxuan Xia0Haoyi Weng1Ruoting Men2Rui Sun3Benny Chung Ying Zee4Ka Chun Chong5Maggie Haitian Wang6Division of Biostatistics, Centre for Clinical Research and Biostatistics, JC School of Public Health and Primary Care, The Chinese University of Hong KongDivision of Biostatistics, Centre for Clinical Research and Biostatistics, JC School of Public Health and Primary Care, The Chinese University of Hong KongDivision of Biostatistics, Centre for Clinical Research and Biostatistics, JC School of Public Health and Primary Care, The Chinese University of Hong KongDivision of Biostatistics, Centre for Clinical Research and Biostatistics, JC School of Public Health and Primary Care, The Chinese University of Hong KongDivision of Biostatistics, Centre for Clinical Research and Biostatistics, JC School of Public Health and Primary Care, The Chinese University of Hong KongDivision of Biostatistics, Centre for Clinical Research and Biostatistics, JC School of Public Health and Primary Care, The Chinese University of Hong KongDivision of Biostatistics, Centre for Clinical Research and Biostatistics, JC School of Public Health and Primary Care, The Chinese University of Hong KongAbstract Background An accumulation of evidence has revealed the important role of epigenetic factors in explaining the etiopathogenesis of human diseases. Several empirical studies have successfully incorporated methylation data into models for disease prediction. However, it is still a challenge to integrate different types of omics data into prediction models, and the contribution of methylation information to prediction remains to be fully clarified. Results A stratified drug-response prediction model was built based on an artificial neural network to predict the change in the circulating triglyceride level after fenofibrate intervention. Associated single-nucleotide polymorphisms (SNPs), methylation of selected cytosine-phosphate-guanine (CpG) sites, age, sex, and smoking status, were included as predictors. The model with selected SNPs achieved a mean 5-fold cross-validation prediction error rate of 43.65%. After adding methylation information into the model, the error rate dropped to 41.92%. The combination of significant SNPs, CpG sites, age, sex, and smoking status, achieved the lowest prediction error rate of 41.54%. Conclusions Compared to using SNP data only, adding methylation data in prediction models slightly improved the error rate; further prediction error reduction is achieved by a combination of genome, methylation genome, and environmental factors.http://link.springer.com/article/10.1186/s12863-018-0644-5MethylationPredictionSNPsNeural networkTreatment responses |
| spellingShingle | Xiaoxuan Xia Haoyi Weng Ruoting Men Rui Sun Benny Chung Ying Zee Ka Chun Chong Maggie Haitian Wang Incorporating methylation genome information improves prediction accuracy for drug treatment responses BMC Genetics Methylation Prediction SNPs Neural network Treatment responses |
| title | Incorporating methylation genome information improves prediction accuracy for drug treatment responses |
| title_full | Incorporating methylation genome information improves prediction accuracy for drug treatment responses |
| title_fullStr | Incorporating methylation genome information improves prediction accuracy for drug treatment responses |
| title_full_unstemmed | Incorporating methylation genome information improves prediction accuracy for drug treatment responses |
| title_short | Incorporating methylation genome information improves prediction accuracy for drug treatment responses |
| title_sort | incorporating methylation genome information improves prediction accuracy for drug treatment responses |
| topic | Methylation Prediction SNPs Neural network Treatment responses |
| url | http://link.springer.com/article/10.1186/s12863-018-0644-5 |
| work_keys_str_mv | AT xiaoxuanxia incorporatingmethylationgenomeinformationimprovespredictionaccuracyfordrugtreatmentresponses AT haoyiweng incorporatingmethylationgenomeinformationimprovespredictionaccuracyfordrugtreatmentresponses AT ruotingmen incorporatingmethylationgenomeinformationimprovespredictionaccuracyfordrugtreatmentresponses AT ruisun incorporatingmethylationgenomeinformationimprovespredictionaccuracyfordrugtreatmentresponses AT bennychungyingzee incorporatingmethylationgenomeinformationimprovespredictionaccuracyfordrugtreatmentresponses AT kachunchong incorporatingmethylationgenomeinformationimprovespredictionaccuracyfordrugtreatmentresponses AT maggiehaitianwang incorporatingmethylationgenomeinformationimprovespredictionaccuracyfordrugtreatmentresponses |