Learning to encode cellular responses to systematic perturbations with deep generative models

Evolution of precision oncology-guided treatment paradigms

Cancer treatment is gradually evolving from the classical use of nonspecific cytotoxic drugs targeting generic mechanisms of cell growth and proliferation. Instead, new "patient-specific treatment paradigms" that are based on an individual patient's tumor-specific molecular features are emerging, and these include "druggable" genomic alterations such as oncogenic driver mutations, downstream activities of cancer-signaling pathways, and the expression of specific genes involved in tumorigenesis and cancer progression. This evolving landscape of making evidence-based treatment decisions forms the foundation of precision oncology, which aims to deliver "the right drug, to the right patient and at the right time". The long-term vision for this approach is to maximize the treatment efficacy while minimizing exposure to ineffective therapy and reducing co-morbidity-related side effects. Successful clinical translation and implementation of this vision have the potential to revolutionize treatment paradigms from predominantly reactive, to more evidence-based, proactive and predictive care. In this article, we review the past and current approaches in precision oncology, and describe their remarkable power and limitations. We also speculate on the evolution of newly emerging methodologies of the future that can be used to address some of the key challenges associated with the existing paradigms. This article is categorized under: Cancer > Genetics/Genomics/Epigenetics Cancer > Molecular and Cellular Physiology Cancer > Computational Models.

Predicting drug polypharmacology from cell morphology readouts using variational autoencoder latent space arithmetic

A variational autoencoder (VAE) is a machine learning algorithm, useful for generating a compressed and interpretable latent space. These representations have been generated from various biomedical data types and can be used to produce realistic-looking simulated data. However, standard vanilla VAEs suffer from entangled and uninformative latent spaces, which can be mitigated using other types of VAEs such as β-VAE and MMD-VAE. In this project, we evaluated the ability of VAEs to learn cell morphology characteristics derived from cell images. We trained and evaluated these three VAE variants-Vanilla VAE, β-VAE, and MMD-VAE-on cell morphology readouts and explored the generative capacity of each model to predict compound polypharmacology (the interactions of a drug with more than one target) using an approach called latent space arithmetic (LSA). To test the generalizability of the strategy, we also trained these VAEs using gene expression data of the same compound perturbations and found that gene expression provides complementary information. We found that the β-VAE and MMD-VAE disentangle morphology signals and reveal a more interpretable latent space. We reliably simulated morphology and gene expression readouts from certain compounds thereby predicting cell states perturbed with compounds of known polypharmacology. Inferring cell state for specific drug mechanisms could aid researchers in developing and identifying targeted therapeutics and categorizing off-target effects in the future.

De novo Prediction of Cell-Drug Sensitivities Using Deep Learning-based Graph Regularized Matrix Factorization

Application of artificial intelligence (AI) in precision oncology typically involves predicting whether the cancer cells of a patient (previously unseen by AI models) will respond to any of a set of existing anticancer drugs, based on responses of previous training cell samples to those drugs. To expand the repertoire of anticancer drugs, AI has also been used to repurpose drugs that have not been tested in an anticancer setting, i.e., predicting the anticancer effects of a new drug on previously unseen cancer cells de novo. Here, we report a computational model that addresses both of the above tasks in a unified AI framework. Our model, referred to as deep learning-based graph regularized matrix factorization (DeepGRMF), integrates neural networks, graph models, and matrix-factorization techniques to utilize diverse information from drug chemical structures, their impact on cellular signaling systems, and cancer cell cellular states to predict cell response to drugs. DeepGRMF learns embeddings of drugs so that drugs sharing similar structures and mechanisms of action (MOAs) are closely related in the embedding space. Similarly, DeepGRMF also learns representation embeddings of cells such that cells sharing similar cellular states and drug responses are closely related. Evaluation of DeepGRMF and competing models on Genomics of Drug Sensitivity in Cancer (GDSC) and Cancer Cell Line Encyclopedia (CCLE) datasets show its superiority in prediction performance. Finally, we show that the model is capable of predicting effectiveness of a chemotherapy regimen on patient outcomes for the lung cancer patients in The Cancer Genome Atlas (TCGA) dataset*.