There's no one way to build a company. The best you can do is get exposure to multiple methodologies and triangulate what's right for your vision. The Fifty Years energy, philosophy, and community is one I recommend adding to your arsenal if you have the opportunity.

I know our industry gets a lot of crap, but it is patient stories like this that make it worth it.

ML models like Evo + AlphaFold are emerging to engineer molecules. It is sometimes unclear how to use these tools to build drugs. We trace a realistic design, build and test loop of virus capsids on LatchBio.

A sneak peek of what's coming...

Big presentation from Manifold Bio's Co-founder/CSO Pierce this Wednesday at one of the major annual protein engineering conferences PEGS Boston.

If you're at PEGS Boston right now, come check out Manifold Bio's poster being presented by one of our talented scientists Alex Reis

I just had an email attachment of phage genomes blocked because the scanner found a virus. I'm in awe

Brain delivery BBB-penetrating antibodies can dramatically improve protein drugs for the CNS, but we lack good shuttles especially for the newer BBB-transport targets. Manifold Bio combines ML with an in-vivo screen to identify new designs for next-gen brain shuttles

From a scientist at Manifold Bio today who is integrating nanopore sequencing into our library protein engineering workflows: "We asked Oxford's product development people a few questions and they said no one has pushed their technology in that way before."

Highly recommend for engineers/scientists looking to catalyze their own founder journey:

Anyone else attempting to reprogram over a decade of muscle memory with Superhuman changing the 'reply-all' keyboard shortcut from 'A' to 'enter' today?

Fixed! Nice response from rahulvohra and Superhuman team.

veni, *vivo*, vici

Great to hang out with Gleb and Pierce Manifold Bio on a beautiful day in Boston!

Many new machine learning tools for protein engineering have popped up in the last year. In these early days, it might be unclear how to actually use them for real molecular design tasks in industry. We demonstrate how to engineer a cholesterol drug and plastic degrading

Great lab and mentor to consider for Yale students interested in synbio / developmental biology.

cool 3D viz of how LLMs (GPT) works bbycroft.net/llm

To predict the future in biotech, study and understand the tools. Stories of new drugs, platforms, data generation strategies are usually stories of new measurement techniques. Progress in assay development has been breakneck this past year but masked by widespread industry

The same archetype is emerging in drug discovery among teams that can rapidly generate data. The same person can generate designs, rapidly grok new data integrated with historical data, and iterate on models, molecule designs, and follow-up experiment designs.

When you're trying to do something hard, you need the best people who are not afraid to find and develop even better people. A pleasure building a generational company alongside Alex Reis.