Facebook AI develops tool to accelerate discovery of effective drug combinations

The new AI model - called Compositional Perturbation Autoencoder (CPA) - predicts the effects of key attributes including drug combinations, dosages, timing and even other types of interventions like gene knockout or deletion.

Facebook AI and Germany's Helmholtz Zentrum Munchen on Friday announced the development of a new artificial intelligence (AI) method that will help accelerate the discovery of effective new drug combinations to treat complex diseases faster.

The new AI model - called Compositional Perturbation Autoencoder (CPA) - predicts the effects of key attributes including drug combinations, dosages, timing and even other types of interventions like gene knockout or deletion.

CPA is a deep generative framework that uses a novel self-supervision technique to observe cells treated with a finite number of drug combinations and predicts the effect of unseen combinations. It can learn the individual impact of each drug in a cell-type-specific fashion and then recombine them to extrapolate combinations.

Pharmaceutical researchers can use CPA to generate hypotheses, guide their experimental design process and help narrow down billions of choices to run experiments in the lab.

CPA first separates and learns about key attributes in a cell and then independently recombines the attributes to predict their effects on the cell's gene expressions.

Facebook hopes that pharmaceutical, academic researchers and biologists will leverage the open-source AI tool to accelerate the process of identifying optimal combinations of drugs for various diseases. Researchers can use CPA to generate hypotheses, guide their experimental design process and help narrow down billions of choices to run experiments in the lab.

With ready-to-use APIs and Python package, researchers don't need machine learning (ML) expertise to plug in data sets and run through predictions.

"By providing pharmaceutical labs with AI-powered tools, we hope to help dramatically accelerate the process of identifying optimal combinations of drugs and other interventions that could ultimately lead to better treatments for complex diseases like cancer and novel diseases like COVID-19," Facebook wrote in a blog post.

In the future, CPA could make treatments much more personalized and tailored to individual cell responses, one of the most active challenges in the future of medicine to date.