Deep generative neural network for accurate drug response imputation

Drug response differs substantially in cancer patients due to inter- and intra-tumor heterogeneity. Particularly, transcriptome context, especially tumor microenvironment, has been shown playing a significant role in shaping the actual treatment outcome. In this study, we develop a deep variational...

Full description

Saved in:
Bibliographic Details
Published in:Nature communications Vol. 12; no. 1; pp. 1740 - 16
Main Authors: Jia, Peilin, Hu, Ruifeng, Pei, Guangsheng, Dai, Yulin, Wang, Yin-Ying, Zhao, Zhongming
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 19.03.2021
Nature Publishing Group
Nature Portfolio
Subjects:
38/47
45
45/91
49
49/39
631/114/1305
631/67/69
692/699/67/1059/153
Antineoplastic Agents - pharmacology
Biotechnology
Cancer
Cell Line, Tumor
Context
Deep Learning
Gene expression
Gene Expression Regulation, Neoplastic - drug effects
Genomes
Heterogeneity
Humanities and Social Sciences
Humans
Mathematical analysis
multidisciplinary
Mutation
Neoplasms - drug therapy
Neoplasms - genetics
Neural networks
Neural Networks, Computer
Patients
Pharmaceutical Preparations
Quality assessment
Quality control
Science
Science (multidisciplinary)
Sensory evaluation
Signatures
Transcriptome
Transcriptomes
Tumor cell lines
Tumor microenvironment
Tumor Microenvironment - drug effects
Tumors
Vectors (mathematics)
ISSN:2041-1723, 2041-1723
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Drug response differs substantially in cancer patients due to inter- and intra-tumor heterogeneity. Particularly, transcriptome context, especially tumor microenvironment, has been shown playing a significant role in shaping the actual treatment outcome. In this study, we develop a deep variational autoencoder (VAE) model to compress thousands of genes into latent vectors in a low-dimensional space. We then demonstrate that these encoded vectors could accurately impute drug response, outperform standard signature-gene based approaches, and appropriately control the overfitting problem. We apply rigorous quality assessment and validation, including assessing the impact of cell line lineage, cross-validation, cross-panel evaluation, and application in independent clinical data sets, to warrant the accuracy of the imputed drug response in both cell lines and cancer samples. Specifically, the expression-regulated component (EReX) of the observed drug response achieves high correlation across panels. Using the well-trained models, we impute drug response of The Cancer Genome Atlas data and investigate the features and signatures associated with the imputed drug response, including cell line origins, somatic mutations and tumor mutation burdens, tumor microenvironment, and confounding factors. In summary, our deep learning method and the results are useful for the study of signatures and markers of drug response. Drug response in cancer patients vary dramatically due to inter- and intra-tumor heterogeneity and transcriptome context plays a significant role in shaping the actual treatment outcome. Here, the authors develop a deep variational autoencoder model to compress gene signatures into latent vectors and accurately impute drug response.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2041-1723
2041-1723
DOI:10.1038/s41467-021-21997-5