Sharing Evo 2, a new foundation model for biomolecular sciences, now available on NVIDIA BioNeMo. This is a collaboration between the Arc Institute, Stanford, UC Berkeley, UCSF, and NVIDIA. It's significant because it's trained on a massive dataset – nearly 9 trillion nucleotides of DNA, RNA, and protein sequences from across the tree of life.
Key aspects:
🧬 Genomic Scale: Trained on an enormous dataset covering diverse species. 🔬 Multimodal: Understands DNA, RNA, and protein sequences. 🧠 Long Context: Can process sequences up to 1 million nucleotides at once. 🚀 Powerful Architecture: Uses a "StripedHyena 2" architecture for efficiency. ✅ Open Components: Key parts, including fine-tuning, are available via the open-source NVIDIA BioNeMo Framework. 🔓Available as NVIDIA NIM microservice.
They've already shown it can predict the effects of gene mutations with high accuracy, and even design functional CRISPR-Cas systems. It's a powerful tool for anyone working with biological sequence data.
So, while AlphaFold primarily predicted existing structures, Evo 2 opens the door to designing entirely new biological sequences for things like drug discovery, agriculture, and materials science. What new possibilities does this unlock?
Congratulations on the launch of Evo 2! This powerful biomolecular AI model is truly a remarkable achievement in the field of technology. The ability to offer insights into DNA, RNA, and proteins across various species is not only groundbreaking but also holds great potential for advancing our understanding of biology. The fact that it's free and available on GitHub makes it accessible to a wide range of researchers and developers, fostering collaboration and innovation. Kudos to the team behind Evo 2 for bringing such a valuable tool to the scientific community. Here's to many exciting discoveries and applications that will surely come from this amazing AI model! 🌟
This is massive. A model that not only interprets but designs new biological sequences could push biotech into entirely new territory. The ability to process million-nucleotide sequences means we’re looking at real potential for breakthroughs in genetic engineering, synthetic biology, and even personalized medicine. Excited to see how researchers put Evo 2 to work!
Congrats on the launch!
Best wishes and sending lots of wins to the team behind it :)
Congratulations on the launch of Evo 2! This groundbreaking model has the potential to revolutionize multiple fields, from drug discovery to agricultural innovation. The ability to design novel biological sequences is a game-changer for the entire scientific community. I'm excited to see the amazing impact it will have in research and industry. 🚀
Replies
Hi everyone!
Sharing Evo 2, a new foundation model for biomolecular sciences, now available on NVIDIA BioNeMo. This is a collaboration between the Arc Institute, Stanford, UC Berkeley, UCSF, and NVIDIA. It's significant because it's trained on a massive dataset – nearly 9 trillion nucleotides of DNA, RNA, and protein sequences from across the tree of life.
Key aspects:
🧬 Genomic Scale: Trained on an enormous dataset covering diverse species.
🔬 Multimodal: Understands DNA, RNA, and protein sequences.
🧠 Long Context: Can process sequences up to 1 million nucleotides at once.
🚀 Powerful Architecture: Uses a "StripedHyena 2" architecture for efficiency.
✅ Open Components: Key parts, including fine-tuning, are available via the open-source NVIDIA BioNeMo Framework.
🔓Available as NVIDIA NIM microservice.
They've already shown it can predict the effects of gene mutations with high accuracy, and even design functional CRISPR-Cas systems. It's a powerful tool for anyone working with biological sequence data.
So, while AlphaFold primarily predicted existing structures, Evo 2 opens the door to designing entirely new biological sequences for things like drug discovery, agriculture, and materials science. What new possibilities does this unlock?
Congratulations on the launch of Evo 2! This powerful biomolecular AI model is truly a remarkable achievement in the field of technology. The ability to offer insights into DNA, RNA, and proteins across various species is not only groundbreaking but also holds great potential for advancing our understanding of biology. The fact that it's free and available on GitHub makes it accessible to a wide range of researchers and developers, fostering collaboration and innovation. Kudos to the team behind Evo 2 for bringing such a valuable tool to the scientific community. Here's to many exciting discoveries and applications that will surely come from this amazing AI model! 🌟
It's weird but good.
Shram
This is massive. A model that not only interprets but designs new biological sequences could push biotech into entirely new territory. The ability to process million-nucleotide sequences means we’re looking at real potential for breakthroughs in genetic engineering, synthetic biology, and even personalized medicine. Excited to see how researchers put Evo 2 to work!
Congrats on the launch!
Best wishes and sending lots of wins to the team behind it :)
Awesome project Zac!
Высокий уровень!
Congratulations on the launch of Evo 2! This groundbreaking model has the potential to revolutionize multiple fields, from drug discovery to agricultural innovation. The ability to design novel biological sequences is a game-changer for the entire scientific community. I'm excited to see the amazing impact it will have in research and industry. 🚀