Illumina joins with AstraZeneca on AI-driven drug discovery project

Illumina signed up for a new collaboration with AstraZeneca with the goal of aligning their artificial intelligence development efforts in a way that combines genomic analysis and drug discovery research. 

The project will explore whether applying AI to DNA and other omics sequencing data can increase their returns in successful biological targets and promising drug candidates, according to a release from the two companies.

"By identifying genes that show evidence of human disease causality, the combined framework has the potential to prioritize drug candidates with increased likelihood of approval," Joydeep Goswami, Illumina’s chief strategy and corporate development officer and interim chief financial officer, said in the release.

The collaboration will start with Illumina’s AI-based tools for interpreting genomic data, PrimateAI and SpliceAI. PrimateAI is a deep neural network trained on hundreds of thousands of genetic variants collected from humans and animals and is designed to predict which mutations will lead to illness.

SpliceAI, meanwhile, is a separate open-source deep learning tool that aims to uncover previously overlooked and noncoding mutations that could be related to patients with rare genetic conditions and other diseases.

AstraZeneca’s Centre for Genomics Research will employ a framework that uses Illumina’s software contributions alongside the Big Pharma’s own AI programs, including Jarvis, which also scans the genome’s noncoding regions for potentially troubling variations. The drugmaker will then examine the large-scale, multi-omics data sets it keeps in its digital biobank.

"Continuous innovation in the AI tools and frameworks that are applied to the growing human genomics, transcriptomics and proteomics medical research resources will enable us to answer some of the toughest questions and contribute to our aims of uncovering novel drug targets with a higher probability of success while also characterizing patient subgroups that are most likely to benefit from the treatments we discover," said Slavé Petrovski, head of discovery sciences R&D at AstraZeneca's Centre for Genomics Research, in the release.

If the first steps of the AI collaboration are successful, the two companies said they would reevaluate their partnership for the longer term before moving forward with further target and drug development work, clinical trials and eventual regulatory submissions.