Abstract 863: Transfer learning for gene expression prediction with deep neural networks

Abstract

Abstract Conventional machine learning approaches try to solve problems in an isolated manner whereas humans utilize previous experiences between similar tasks. Transfer learning (TL) imitates this efficient approach and transfer knowledge that was learned in a source/domain task and employ that knowledge to improve learning in a related target task. We propose a deep convolutional neural networks (CNNs) structure to predict gene expression via epigenomic signals around the TSS. This structure allows to transfer knowledge that we learn in a cancer type to another one. We use H3K4me1, H3K4me3, H3K27Ac, H3K4me3, H3K27me3 histone modification marks for breast, lung, colon, glioma, ovarian, melanoma, and pancreas cancers as input and predict gene expression for each sample. Our model with transfer learning has improved prediction rates for various cancer types compared to the other established methods like Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost). We also compared performances for different percentages of data with previously proposed DeepChrome algorithm. We checked normal datasets contribution for cancer samples as well. For this purpose, we train our model with normal samples from Roadmap Epigenome Project (REMC) repository first and passed the learned parameters to cancer datasets. It seems normal samples do not have common epigenomic patterns with cancer ones as we do not see any prediction of gene expression improvement. To our knowledge, there is no proposed transfer learning method in epigenetic data analysis. The proposed transfer learning mechanism will lead to avoid generating a significant amount of epigenomic data for different cancer types and will accelerate epigenomic studies in different cancer types. Citation Format: Emre Arslan, Kunal Rai. Transfer learning for gene expression prediction with deep neural networks [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 863.