More about Protein Language Models

Estimated Reading Time: 2 minutes

TL;DR

We briefly discuss a recent paper from Salesforce research using protein language models to design functioning enzymes.

Designing new protein sequences with the help of LLMs

Protein language models have gained in prominence over the last few years. A team from Salesforce research used their protein language model, Progen, to generate sequences for artificial lysozymes. Researchers then selected 100 sequences to synthesize and test and found that ~70 of the generated sequences worked in practice. Getting 70% biological activity from a computational method is a powerful milestone.

Interesting Links from Around the Web

• https://www.science.org/content/blog-post/wonderful-progress-against-severe-lupus: An interesting write-up of recent progress made in treating serious Lupus.

• https://www.amazon.com/dp/B0BTNSJRKD: A new book on using Haskell for production. Haskell engineers continue to push the boundary for turning Haskell and functional programming into a technology suitable for production engineering. 

Feedback and Comments

Please feel free to email me directly (bharath@deepforestsci.com) with your feedback and comments! 

About

Deep Into the Forest is a newsletter by Deep Forest Sciences, Inc. We’re a deep tech R&D company building Chiron, an AI-powered scientific discovery engine. Deep Forest Sciences leads the development of the open source DeepChem ecosystem. Partner with us to apply our foundational AI technologies to hard real-world problems in drug discovery. Get in touch with us at partnerships@deepforestsci.com! 

Credits

Author: Bharath Ramsundar, Ph.D.

Editor: Sandya Subramanian, Ph.D.