Predicting single-cell perturbation responses for unseen drugs

Leon Hetzel, Simon Boehm, Niki Kilbertus, Stephan Günnemann, Mohammad Lotfollahi, Fabian J Theis

Keywords: single cell, perturbation, disentanglement, transfer learning, drug discovery

TL;DR: We present a model which enables counterfactual response predictions for unseen drugs and evaluate how large scale bulk RNA-seq datasets can be leveraged to improve generalisation performance on single-cell data.

Abstract:

Single-cell transcriptomics enabled the study of cellular heterogeneity in response to perturbations at the resolution of individual cells. However, scaling high-throughput screens (HTSs) to measure cellular responses for many drugs remains a challenge due to technical limitations and, more importantly, the cost of such multiplexed experiments. Thus, transferring information from routinely performed bulk RNA-seq HTS is required to enrich single-cell data meaningfully.
We introduce a new encoder-decoder architecture to study the perturbational effects of unseen drugs. We combine the model with a transfer learning scheme and demonstrate how training on existing bulk RNA-seq HTS datasets can improve generalisation performance. Better generalisation reduces the need for extensive and costly screens at single-cell resolution.
We envision that our proposed method will facilitate more efficient experiment designs through its ability to generate in-silico hypotheses, ultimately accelerating targeted drug discovery.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2204.13545/code)