PacBio’s Revio system and SPRQ-Nx chemistry to enable an order-of-magnitude expansion of HiFi metagenomic sequencing for scaling AI-designed therapeutics
PacBio has announced that Basecamp Research, a frontier AI lab for therapeutic design, has selected PacBio HiFi sequencing on the Revio system to generate large-scale environmental and host-associated metagenomic data for the Trillion Gene Atlas: a landmark scientific initiative designed to generate and model biological data at the trillion-gene scale.
The collaboration is expected to result in approximately 100,000 deeply sequenced samples from over 31 countries across 5 continents, creating the largest and most diverse high-fidelity metagenomic dataset assembled to date.
As AI models for biological design continue to advance, the quality and diversity of training data are increasingly critical. PacBio HiFi sequencing combines high accuracy with long reads to resolve complex genomes and microbial communities, preserving genomic context to enable complete, strain-resolved assemblies, providing a strong foundation for AI model training.
PacBio joins collaborators Anthropic, NVIDIA, and Ultima Genomics in contributing to the Trillion Gene Atlas, bringing together advances in biological data generation, AI model development, and high-performance computing.
The initiative aims to expand known evolutionary genetic diversity 100-fold, paving the way for a new generation of AI systems capable of designing transformative medicines.
“Expanding the evolutionary universe available to AI requires not just more data, but better data, PacBio’s long-read sequencing allows us to capture genomic structure and context that are essential for training biological foundation models. By combining high-fidelity sequencing, accelerated compute, and our advanced models, the Trillion Gene Atlas is designed to enable a new generation of AI systems capable of designing transformative medicines.”
– Glen Gowers, Co-founder and CEO of Basecamp Research.
Attendere..



