Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

This Startup Says It Can Beat Deepmind’s Gamechanging Protein AI

Mar 12, 2024 - forbes.com
London-based biotech startup Basecamp Research has developed an AI model, BaseFold, that improves upon Google's AlphaFold2 in predicting protein structures, a key aspect of biotech research. BaseFold, which is trained on a broader dataset, can reportedly produce more accurate protein structure predictions than AlphaFold2, and Basecamp is working with Nvidia to optimize BaseFold for use with Nvidia's generative AI platform for drug discovery, BioNeMo. Basecamp's CEO, Glen Gowers, claims that BaseFold offers a threefold improvement in predicting how protein structures will change when they interact with small molecules, a crucial factor in drug discovery.

Since its founding in 2020, Basecamp has been working with researchers globally to sequence genomic information from tens of millions of microbes, plants, and animals, diversifying the protein dataset that its models are trained on. The company is already generating revenue by using its predictive modeling to solve customer problems, such as designing new proteins for fabric dyeing and discovering new proteins for plastic recycling. Basecamp also plans to collaborate with pharmaceutical companies to develop new drugs using its computational capabilities.

Key takeaways:

  • London-based Basecamp Research has developed a new AI model, BaseFold, which is built on top of AlphaFold2’s open-source algorithms and can produce more accurate protein structure predictions.
  • Basecamp Research is working with Nvidia to optimize BaseFold for use with the chip giant’s generative AI platform for drug discovery, BioNeMo.
  • Basecamp Research has been working with researchers around the world to sequence high-quality genomic information from tens of millions of microbes, plants, and animals from around the world to diversify the protein dataset that its models are trained on.
  • Basecamp Research is already generating revenue by using its predictive modeling to solve customer problems, such as designing new proteins that can be used to dye fabrics without using harsh chemicals and discovering new proteins that can break down plastics for recycling.
View Full Article

Comments (0)

Be the first to comment!