A Hybrid Ensemble Approach for Identifying Robust Differentially Methylated Loci in Pan-Cancers

Abstract

DNA methylation is a widely investigated epigenetic mark that plays a vital role in tumorigenesis. Advancements in high-throughput assays, such as the Infinium 450K platform, provide genome-scale DNA methylation landscapes in single-CpG locus resolution, and the identification of differentially methylated loci has become an insightful approach to deepen our understanding of cancers. However, the situation with extremely unbalanced numbers of samples and loci (approximately 1:1,000) makes it rather difficult to explore differential methylation between the sick and the normal. In this article, a hybrid approach based on ensemble feature selection for identifying differentially methylated loci (HyDML) was proposed by incorporating instance perturbation and multiple function models. Experiments on data from The Cancer Genome Atlas showed that HyDML not only achieved effective DML identification, but also outperformed the single-feature selection approach in terms of classification performance and the robustness of feature selection. The intensive analysis of the DML indicated that different types of cancers have mutual patterns, and the stable DML sharing in pan-cancers is of the great potential to be biomarkers, which may strengthen the confidence of domain experts to implement biological validations.

Identification of clinical factors related to prediction of alcohol use disorder from electronic health records using feature selection methods

“…Transformed features have no physical meaning that can be used for deep analysis of the features and clinical factors. Thus, besides the general advantages of FS in reducing problem dimensionality and thereby improving the accuracy of classifiers, FS methods have better readability, interpretability, and explainability in a practical application such as identification of risk factors for clinical conditions [ 8 , 9 ] (i.e., AUD).…”

DNA methylation loci identification for pan-cancer early-stage diagnosis and prognosis using a new distributed parallel partial least squares method

“…It may also be one of the first detectable biomarkers for the early detection of cancer ( Xu et al, 2017 ; Luo et al, 2020 ). Correspondingly, the methylation pan-cancer study is an emerging research hotspot, which is dedicated to find common or cancer-specific diagnostic or prognostic biomarkers from a variety of cancers ( Yang et al, 2017 ; Ding et al, 2019 ; Tian et al, 2019 ).…”

AgeGuess, a Methylomic Prediction Model for Human Ages

“…A feature selection algorithm may significantly reduce the model complexity and the possibility of over-fitting (Le et al, 2017;Ma and Fan, 2017). Feature selection was not only widely used in the bioinformatics problems of genes (Tian et al, 2019), proteins (Liu et al, 2019), and metabolism system (Grissa et al, 2016), but also played an important role in the analysis of biomedical images (Pan et al, 2019) and time series data (Li et al, 2017).…”