Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Explore a comprehensive talk by Garyk Brixi from Valence Labs discussing Evo 2, a groundbreaking biological foundation model trained on 9.3 trillion DNA base pairs from a curated genomic atlas spanning all domains of life. Learn about this 7B and 40B parameter model with its unprecedented 1 million token context window and single-nucleotide resolution. Discover how Evo 2 accurately predicts functional impacts of genetic variation without task-specific fine-tuning, autonomously learns biological features like exon-intron boundaries and transcription factor binding sites, and generates mitochondrial, prokaryotic, and eukaryotic sequences with greater naturalness than previous methods. The talk covers how Evo 2's inference-time search enables controllable generation of epigenomic structure and discusses the open-source availability of the model parameters, training code, inference code, and the OpenGenome2 dataset to accelerate biological complexity exploration and design. Connect with the speaker and AI drug discovery community through the Valence Labs portal.
