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

Abstract

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.

Integrating Cell Morphology with Gene Expression and Chemical Structure to Aid Mitochondrial Toxicity Detection

“…Future studies would benefit from larger datasets, such as the announced future data depositions from the JUMP consortium 80 , and also more and better annotated compounds that show mitochondrial toxicity under different assays and dosages such as from the Mitotox database 46 . It may also be possible to apply different types of machine learning or deep learning models, such as deep neural networks, gradient boosting, or a variational autoencoder (which has been previously shown to reveal an interpretable latent space 81 ) to improve the model’s predictions and generally improve the interpretability of models.…”

Cross-modal Graph Contrastive Learning with Cellular Images

“…As shown in Figure 1, small molecules enter into cells and affect their biological functions and pathways, leading to morphological changes in cell shape, number, structure, etc., that are visible in microscopy images after staining. Analysis and modeling based on these high-content images have shown great success in molecular bioactivity prediction [20], mechanism identification [21], polypharmacology prediction [22], etc. The stained cell images contain rich morphological information that reflects the biological changes induced by chemical structures on cell cultures.…”