Abstract
MotivationIndividualized drug response prediction is a fundamental part of personalized medicine for cancer. Great effort has been made to discover biomarkers or to develop machine learning methods for accurate drug response prediction in cancers. Incorporating prior knowledge of biological systems into these methods is a promising avenue to improve prediction performance. High-throughput cell line assays of drug-induced transcriptomic perturbation effects are a prior knowledge that has not been fully incorporated into a drug response prediction model yet.ResultsWe introduce a unified probabilistic approach, Drug Response Variational Autoencoder (Dr.VAE), that simultaneously models both drug response in terms of viability and transcriptomic perturbations. Dr.VAE is a deep generative model based on variational autoencoders. Our experimental results showed Dr.VAE to do as well or outperform standard classification methods for 23 out of 26 tested Food and Drug Administration-approved drugs. In a series of ablation experiments we showed that the observed improvement of Dr.VAE can be credited to the incorporation of drug-induced perturbation effects with joint modeling of treatment sensitivity.Availability and implementationProcessed data and software implementation using PyTorch (Paszke et al., 2017) are available at: https://github.com/rampasek/DrVAE.Supplementary information Supplementary data are available at Bioinformatics online.
Highlights
Personalized drug response prediction promises to improve the therapy response rate in life-threatening diseases, such as cancer
We evaluated our drug response prediction method, Dr.variational autoencoders (VAE), on 26 Food and Drug Administration-approved drug compounds selected from the intersection of two independent in vitro drug screening studies: (i) the CTRPv2 (Rees et al, 2016) where viability of up to 855 cell lines was measured in response to drug treatment, and (ii) drug-induced transcriptomic perturbations, assayed by NIH
supervised variational autoencoder (SSVAE) does not include any information of drug-induced transcriptomic perturbations
Summary
Personalized drug response prediction promises to improve the therapy response rate in life-threatening diseases, such as cancer. The space of all possible treatments and their combinations for a given condition is prohibitively large to be explored exhaustively in clinical settings, drastically limiting the sample size for many therapies and tissues of interest. Cancer heterogeneity among patients is very high, reducing the statistical power of biomarker detection. These two conditions make it hard to characterize the genotype-to-phenotype landscape comprehensively making it difficult to accurately stratify drug treatment options for a particular cancer patient. To fulfill the promise of precision medicine, we need predictive models that can take advantage of heterogeneous, sparsely sampled data and data generated from pre-clinical model systems, such as cancer cell lines, to improve our prediction ability
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
