%0 Journal Article %1 noauthororeditor %A Kaushal, Akhilesh %A Zhang, Hongmei %A Karmaus, Wilfried JJ %A Ray, Meredith %A Torres, Mylin A %A Smith, Alicia K %A Wang, Shu-Li %D 2017 %J BMC Bioinformatics %K 2 arsenic cancer correction epigenetics methylation minfi reffree sva %N 1 %P 216 %R 10.1186/s12859-017-1611-2 %T Comparison of different cell type correction methods for genome-scale epigenetics studies %U http://dblp.uni-trier.de/db/journals/bmcbi/bmcbi18.html#KaushalZKRTSW17 %V 18 %X BACKGROUND: Whole blood is frequently utilized in genome-wide association studies of DNA methylation patterns in relation to environmental exposures or clinical outcomes. These associations can be confounded by cellular heterogeneity. Algorithms have been developed to measure or adjust for this heterogeneity, and some have been compared in the literature. However, with new methods available, it is unknown whether the findings will be consistent, if not which method(s) perform better. RESULTS: Methods: We compared eight cell-type correction methods including the method in the minfi R package, the method by Houseman et al., the Removing unwanted variation (RUV) approach, the methods in FaST-LMM-EWASher, ReFACTor, RefFreeEWAS, and RefFreeCellMix R programs, along with one approach utilizing surrogate variables (SVAs). We first evaluated the association of DNA methylation at each CpG across the whole genome with prenatal arsenic exposure levels and with cancer status, adjusted for estimated cell-type information obtained from different methods. We then compared CpGs showing statistical significance from different approaches. For the methods implemented in minfi and proposed by Houseman et al., we utilized homogeneous data with composition of some blood cells available and compared them with the estimated cell compositions. Finally, for methods not explicitly estimating cell compositions, we evaluated their performance using simulated DNA methylation data with a set of latent variables representing "cell types". RESULTS: Results from the SVA-based method overall showed the highest agreement with all other methods except for FaST-LMM-EWASher. Using homogeneous data, minfi provided better estimations on cell types compared to the originally proposed method by Houseman et al. Further simulation studies on methods free of reference data revealed that SVA provided good sensitivities and specificities, RefFreeCellMix in general produced high sensitivities but specificities tended to be low when confounding is present, and FaST-LMM-EWASher gave the lowest sensitivity but highest specificity. CONCLUSIONS: Results from real data and simulations indicated that SVA is recommended when the focus is on the identification of informative CpGs. When appropriate reference data are available, the method implemented in the minfi package is recommended. However, if no such reference data are available or if the focus is not on estimating cell proportions, the SVA method is suggested.

@article{noauthororeditor, abstract = {BACKGROUND: Whole blood is frequently utilized in genome-wide association studies of DNA methylation patterns in relation to environmental exposures or clinical outcomes. These associations can be confounded by cellular heterogeneity. Algorithms have been developed to measure or adjust for this heterogeneity, and some have been compared in the literature. However, with new methods available, it is unknown whether the findings will be consistent, if not which method(s) perform better. RESULTS: Methods: We compared eight cell-type correction methods including the method in the minfi R package, the method by Houseman et al., the Removing unwanted variation (RUV) approach, the methods in FaST-LMM-EWASher, ReFACTor, RefFreeEWAS, and RefFreeCellMix R programs, along with one approach utilizing surrogate variables (SVAs). We first evaluated the association of DNA methylation at each CpG across the whole genome with prenatal arsenic exposure levels and with cancer status, adjusted for estimated cell-type information obtained from different methods. We then compared CpGs showing statistical significance from different approaches. For the methods implemented in minfi and proposed by Houseman et al., we utilized homogeneous data with composition of some blood cells available and compared them with the estimated cell compositions. Finally, for methods not explicitly estimating cell compositions, we evaluated their performance using simulated DNA methylation data with a set of latent variables representing "cell types". RESULTS: Results from the SVA-based method overall showed the highest agreement with all other methods except for FaST-LMM-EWASher. Using homogeneous data, minfi provided better estimations on cell types compared to the originally proposed method by Houseman et al. Further simulation studies on methods free of reference data revealed that SVA provided good sensitivities and specificities, RefFreeCellMix in general produced high sensitivities but specificities tended to be low when confounding is present, and FaST-LMM-EWASher gave the lowest sensitivity but highest specificity. CONCLUSIONS: Results from real data and simulations indicated that SVA is recommended when the focus is on the identification of informative CpGs. When appropriate reference data are available, the method implemented in the minfi package is recommended. However, if no such reference data are available or if the focus is not on estimating cell proportions, the SVA method is suggested.}, added-at = {2017-10-02T23:00:46.000+0200}, author = {Kaushal, Akhilesh and Zhang, Hongmei and Karmaus, Wilfried JJ and Ray, Meredith and Torres, Mylin A and Smith, Alicia K and Wang, Shu-Li}, biburl = {https://www.bibsonomy.org/bibtex/2837663afd0ce7c192d0671066b12c0fc/artheibault}, description = {This article compares eight methods used to account for cell-type heterogeneity in blood samples. Two of these methods (Houseman et al. and minfi) are reference-based, five are non reference-based (EWASHer, ReFACTor, RefFreeEWAS, RefFreeCellMix, and SVA), and one (RUV) comes with a reference data set but is not used to measure cell-type proportions. This article really impressed upon me the importance of selecting reference tools carefully.}, doi = {10.1186/s12859-017-1611-2}, interhash = {e86f4915e5f0b7951250ab383a398dde}, intrahash = {837663afd0ce7c192d0671066b12c0fc}, journal = {BMC Bioinformatics}, keywords = {2 arsenic cancer correction epigenetics methylation minfi reffree sva}, month = apr, number = 1, pages = 216, timestamp = {2017-10-26T15:01:06.000+0200}, title = {Comparison of different cell type correction methods for genome-scale epigenetics studies}, url = {http://dblp.uni-trier.de/db/journals/bmcbi/bmcbi18.html#KaushalZKRTSW17}, volume = 18, year = 2017 }