Hoping to accelerate drug discovery through AI, scientists have announced the Billion Cell Atlas, which, if successful, is touted to become the world’s largest genome-wide genetic perturbation dataset. The creation of an ‘atlas’ that captures how 1 billion cells respond to genetic changes across disease‑relevant cell lines is underway, Illumina (CA, USA) has announced. Aptly dubbed the ‘Billion Cell Atlas’, it has been billed as a future means of characterizing drug and disease mechanisms of action, validating candidate targets and exploring potential new indications. Built in collaboration with AstraZeneca (Cambridge, UK), Merck (Darmstadt, Germany) and Eli Lilly (IN, USA), the Billion Cell Atlas is the first instalment of a program that aims to build a 5 billion cell atlas in the next 3 years, with a view to drive drug target validation, train AI models and advance research into disease mechanisms that have evaded researchers until now. The Atlas will rely on Illumina’s Single Cell 3′ RNA prep platform, which enables millions of individual cells to be captured in a single experiment, and is expected to generate around 20 petabytes of transcriptomic data within the first year. Single-cell RNA-sequencing data will be processed using Illumina’s DRAGEN pipeline and then hosted on the Connected Analytics cloud platform for large-scale analysis. Combining comprehensive, disease-specific perturbation datasets with advanced AI algorithms, Illumina say the Atlas will usher in a new era of cellular modeling. Ultimately, it is hoped that the Atlas will reveal how a billion individual cells respond to CRISPR editing across…
