Deep learning models for predicting phenotypic traits from omics data
Loading...
Date
2017-04-11
Authors
Islam, Md. Mohaiminul
Journal Title
Journal ISSN
Volume Title
Publisher
Springer
BMC proceedings
BMC proceedings
Abstract
Computational and statistical analysis of high throughput omics data, such as gene expressions, copy number alterations (CNAs), single nucleotide polymorphisms (SNPs) and DNA methylation (DNAm) has become very popular in cancer studies in recent decades because such analysis can be very helpful to predict whether a patient has certain disease or its subtypes. However, due to the high-dimensional nature of the data sets with hundreds of thousands of variables and very small numbers of samples, traditional machine learning approaches, such as Support Vector Machines (SVMs) and Random Forests (RFs), have limitations to analyze these data efficiently. In this thesis, we propose deep neural network (DNN) based models for classifying molecular subtypes of breast cancer and DNN-based regression models to account for interindividual variation in triglyceride concentrations measured at different visits of peripheral blood samples using epigenome-wide DNAm profiles.
Description
Keywords
Deep learning, Bioinformatics, Omics data, Classification, Regression
Citation
Islam, M. M., Ajwad, R., Chi, C., Domaratzki, M., Wang, Y., & Hu, P. (2017, May). Somatic Copy Number Alteration-Based Prediction of Molecular Subtypes of Breast Cancer Using Deep Learning Model. In Canadian Conference on Artificial Intelligence (pp. 57-63). Springer, Cham.
Islam, M. M., Tian, C., Cheng, Y., Wang, Y., & Hu, P. (2017). A deep neural network based regression model for triglyceride concentrations prediction using epigenome-wide DNA methylation profiles. In BMC proceedings. In press.
Islam, M. M., Tian, C., Cheng, Y., Wang, Y., & Hu, P. (2017). A deep neural network based regression model for triglyceride concentrations prediction using epigenome-wide DNA methylation profiles. In BMC proceedings. In press.