Anthropic benchmarked their newest Claude models on protein engineering tasks, and we at @adaptyvbio ran the wet lab work behind it.
They picked 16 targets from our past protein design competitions on @proteinbase and sent us an anonymised list of designs, so we had no idea which model produced which sequence. We then ran those protein designs through our automated wet lab workflow to characterize protein expression and binding affinities.
Here are the results:
- 95% of the designs expressed, which three years ago would have been the headline on its own. That matches the best expert expression rates from our competitions
- 354 of 1,320 designs bound their target on SPR, a 26.8% hit rate overall. Claude got binders on 14 of the 15 targets we could evaluate. Compared to our own data from public competitions, Claude beat de novo hit rates, for one target by more than three times the rate on Proteinbase
So can AI now solve all diseases? Well no, not yet.
This case study shows that Claude is at least expert-level at orchestrating protein design tools. That’s great news, since protein design tools are hard to use. Before AI, even setting up a protein structure prediction tool could take hours of debugging opaque conda errors.
Of course, those proteins that we tested here are not real therapeutics. They completed only the first step of the process: demonstrating that they can function as binders. Still, this study shows a path towards making actual therapeutics with AI.
Imagine making a drug is like climbing a mountain. We have clearly been able to climb some mountains, as humanity has made many drugs already. But the way to the top is a dangerous narrow path and climbing it takes many years and costs billions of dollars (and the lives of many biotechs).
The goal of AI for drug discovery is turning this narrow mountain path into a highway, making it easier and cheaper to get to the top so that we can develop 100x more therapeutics than we have right now. Similarly, writing code was a more of a high-expertise craft before LLMs, now it’s mostly automated and it has made generating software accessible for anyone.
Today we’re expanding Microsoft 365 Copilot with the addition of Anthropic’s Claude models. Customers can now use both OpenAI and Claude — starting in Researcher and Copilot Studio, and coming to more experiences soon.
Our multi-model approach goes beyond choice. It's all about bringing the best AI from across the industry to Copilot, tuned for work and tailored to every business.
Read more: https://t.co/QQEIjKzNfS
How on earth is the government justifying prioritising tens of thousands of people going to football stadiums via public transport and hundreds rammed into airplanes to go on holiday before allowing unrestricted weddings? I know I shouldn't tweet in anger, but this is too much
At Visa, we believe in acceptance everywhere - from the pitch to the boardroom. It's because of this, that we're proud to announce our ground-breaking partnership with UEFA in the hope of supporting the growth of women's football. #WePlayStrong
Some personal news... After 8 fantastic years at #Bloomberg@business I'm happy to report I start at the @FT next week as European banking correspondent, working with @patrickjenkins_, @MAmdorsky, @LauraNoonanFT et al.
#Barclays CEO Staley is worried: “it's a little bit like 2006 when we were all talking whether we've solved the riddle of economic crises... everything seems rosy at 4% growth... equity markets are at all time high & volatility is at an all time low. That isn’t sustainable.”