Dr.VAE: improving drug response prediction via modeling of drug perturbation effects

Abstract Motivation Individualized 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. Results We 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 implementation Processed 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.

[1]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[2]  Ryan P. Adams,et al.  Composing graphical models with neural networks for structured representations and fast inference , 2016, NIPS.

[3]  Igor Jurisica,et al.  Exploiting the mevalonate pathway to distinguish statin-sensitive multiple myeloma. , 2010, Blood.

[4]  Petr Smirnov,et al.  Gene isoforms as expression-based biomarkers predictive of drug response in vitro , 2017, Nature Communications.

[5]  Robert M. Vogel,et al.  A cancer pharmacogenomic screen powering crowd-sourced advancement of drug combination prediction , 2018 .

[6]  J. Barnholtz-Sloan,et al.  Computational identification of multi-omic correlates of anticancer therapeutic response , 2014, BMC Genomics.

[7]  Max Welling,et al.  Semi-supervised Learning with Deep Generative Models , 2014, NIPS.

[8]  Louxin Zhang,et al.  Improved anticancer drug response prediction in cell lines using matrix factorization with similarity regularization , 2017, BMC Cancer.

[9]  Francisco Azuaje,et al.  Computational models for predicting drug responses in cancer research , 2016, Briefings Bioinform..

[10]  Angela N. Brooks,et al.  A Next Generation Connectivity Map: L1000 Platform And The First 1,000,000 Profiles , 2017 .

[11]  Francisco Azuaje,et al.  Dr.Paso: Drug response prediction and analysis system for oncology research , 2017, bioRxiv.

[12]  Zhaleh Safikhani,et al.  PharmacoDB: an integrative database for mining in vitro anticancer drug screening studies , 2017, bioRxiv.

[13]  Mehmet Tan,et al.  Drug response prediction by ensemble learning and drug-induced gene expression signatures , 2018, Genomics.

[14]  Ao Li,et al.  A novel heterogeneous network-based method for drug response prediction in cancer cell lines , 2018, Scientific Reports.

[15]  Jun Wang,et al.  Predicting Anticancer Drug Responses Using a Dual-Layer Integrated Cell Line-Drug Network Model , 2015, PLoS Comput. Biol..

[16]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[17]  Shakir Mohamed,et al.  Variational Inference with Normalizing Flows , 2015, ICML.

[18]  Max Welling,et al.  Improved Variational Inference with Inverse Autoregressive Flow , 2016, NIPS 2016.

[19]  S. Ramaswamy,et al.  Systematic identification of genomic markers of drug sensitivity in cancer cells , 2012, Nature.

[20]  Benjamin Haibe-Kains,et al.  Revisiting inconsistency in large pharmacogenomic studies , 2015, bioRxiv.

[21]  Benjamin Haibe-Kains,et al.  Inconsistency in large pharmacogenomic studies , 2013, Nature.

[22]  Andrew H. Beck,et al.  PharmacoGx: an R package for analysis of large pharmacogenomic datasets , 2015, Bioinform..

[23]  Benjamin Haibe-Kains,et al.  mRMRe: an R package for parallelized mRMR ensemble feature selection , 2013, Bioinform..

[24]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[25]  Laura M. Heiser,et al.  A community effort to assess and improve drug sensitivity prediction algorithms , 2014, Nature Biotechnology.

[26]  Casey S. Greene,et al.  Extracting a Biologically Relevant Latent Space from Cancer Transcriptomes with Variational Autoencoders , 2017, bioRxiv.

[27]  Sridhar Ramaswamy,et al.  Genomics of Drug Sensitivity in Cancer (GDSC): a resource for therapeutic biomarker discovery in cancer cells , 2012, Nucleic Acids Res..

[28]  Marc Hafner,et al.  Common and cell-type specific responses to anti-cancer drugs revealed by high throughput transcript profiling , 2017, Nature Communications.

[29]  Nci Dream Community.  A community effort to assess and improve drug sensitivity prediction algorithms , 2014 .

[30]  Max Welling,et al.  The Variational Fair Autoencoder , 2015, ICLR.

[31]  Adam A. Margolin,et al.  The Cancer Cell Line Encyclopedia enables predictive modeling of anticancer drug sensitivity , 2012, Nature.

[32]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[33]  Justin Guinney,et al.  Systematic Assessment of Analytical Methods for Drug Sensitivity Prediction from Cancer Cell Line Data , 2013, Pacific Symposium on Biocomputing.

[34]  K. Kohn,et al.  CellMiner: a web-based suite of genomic and pharmacologic tools to explore transcript and drug patterns in the NCI-60 cell line set. , 2012, Cancer research.

[35]  Scott E. Martin,et al.  Reproducible pharmacogenomic profiling of cancer cell line panels , 2016, Nature.

[36]  Benjamin Haibe-Kains,et al.  Research and applications: Comparison and validation of genomic predictors for anticancer drug sensitivity , 2013, J. Am. Medical Informatics Assoc..

[37]  Julio Saez-Rodriguez,et al.  Machine Learning Prediction of Cancer Cell Sensitivity to Drugs Based on Genomic and Chemical Properties , 2012, PloS one.

[38]  Joshua A. Bittker,et al.  Correlating chemical sensitivity and basal gene expression reveals mechanism of action , 2015, Nature chemical biology.

[39]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[40]  S. Jazwinski,et al.  Common and cell type-specific responses of human cells to mitochondrial dysfunction. , 2005, Experimental cell research.

[41]  Su-In Lee,et al.  A machine learning approach to integrate big data for precision medicine in acute myeloid leukemia , 2018, Nature Communications.

[42]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[43]  Uri Shalit,et al.  Structured Inference Networks for Nonlinear State Space Models , 2016, AAAI.