A Novel Deep Learning Method to Predict Lung Cancer Long-Term Survival With Biological Knowledge Incorporated Gene Expression Images and Clinical Data

Shuo Wang; Hao Zhang; Zhen Liu; Yuanning Liu

doi:10.3389/fgene.2022.800853

A Novel Deep Learning Method to Predict Lung Cancer Long-Term Survival With Biological Knowledge Incorporated Gene Expression Images and Clinical Data

Front Genet. 2022 Mar 14:13:800853. doi: 10.3389/fgene.2022.800853. eCollection 2022.

Authors

Shuo Wang^{1

2}, Hao Zhang^{1

2}, Zhen Liu^{1

2

3}, Yuanning Liu^{1

2}

Affiliations

¹ College of Computer Science and Technology, Jilin University, Changchun, China.
² Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China.
³ Graduate School of Engineering, Nagasaki Institute of Applied Science, Nagasaki, Japan.

Abstract

Lung cancer is the leading cause of the cancer deaths. Therefore, predicting the survival status of lung cancer patients is of great value. However, the existing methods mainly depend on statistical machine learning (ML) algorithms. Moreover, they are not appropriate for high-dimensionality genomics data, and deep learning (DL), with strong high-dimensional data learning capability, can be used to predict lung cancer survival using genomics data. The Cancer Genome Atlas (TCGA) is a great database that contains many kinds of genomics data for 33 cancer types. With this enormous amount of data, researchers can analyze key factors related to cancer therapy. This paper proposes a novel method to predict lung cancer long-term survival using gene expression data from TCGA. Firstly, we select the most relevant genes to the target problem by the supervised feature selection method called mutual information selector. Secondly, we propose a method to convert gene expression data into two kinds of images with KEGG BRITE and KEGG Pathway data incorporated, so that we could make good use of the convolutional neural network (CNN) model to learn high-level features. Afterwards, we design a CNN-based DL model and added two kinds of clinical data to improve the performance, so that we finally got a multimodal DL model. The generalized experiments results indicated that our method performed much better than the ML models and unimodal DL models. Furthermore, we conduct survival analysis and observe that our model could better divide the samples into high-risk and low-risk groups.

Keywords: CNN; cancer precision medicine; cancer survival prediction; deep learning; multimodal; optimal threshold selection; survival analysis.