"We use failure to describe events in life which sometimes it's not really a failure if you think about it at a higher level." Chemistry laureate Carolyn Bertozzi reflects on the term "failure" and what failing can teach us. #IWD2024

* Language is low bandwidth: less than 12 bytes/second. A person can read 270 words/minutes, or 4.5 words/second, which is 12 bytes/s (assuming 2 bytes per token and 0.75 words per token). A modern LLM is typically trained with 1x10^13 two-byte tokens, which is 2x10^13 bytes.

The amount of AI/ML tools that are being released in the last ~3 years and that are actively changing structural biology –with immediate implications on faster and informed development of drugs– is absolutely staggering and adds hope for an even better and healthier future.

Very interesting: doi.org/10.1038/s41586…

We’re excited to share our preprint where we show, for the first time, the atomically accurate design of VHH antibodies!

📣¡Iniciamos una colaboración pionera en el campo de la #diabetes! Es la ‘Alianza por el abordaje precoz de la #diabetestipo1 autoinmune’, que hemos creado con Federación Española de Diabetes (FEDE) y 10 sociedades científicas para avanzar en la detección de la patología. #SanofiEsDiabetes #DiabetESP

Combinatorial High-Throughput Screening of Complex Polymeric Enzyme Immobilization Supports | Journal of the American Chemical Society CU Boulder Engineering 🦬 CU Boulder 🦬 #HighThroughPut #Screening #Enzyme #Immobilization #Supports pubs.acs.org/doi/10.1021/ja…

Is there anything that neural networks cannot do?

While details are limited, Sanofi and OpenAI announced a partnership focused on customizing large language models for drug development Another (early) example of expanding relationships between AI & biopharma worlds: endpts.com/sanofi-openai-…

Discovery of a major underpinning of inflammatory bowel disease in a gene desert nature.com/articles/s4158… nature The Francis Crick Institute

Occasional reminder that we should do this:

Well, this definitely couldn’t not happen.

Is it time for the protein emoji to return? Can we overcome the past unicode rejection now with the tailwinds of the Nobel Prize? Can proteins be recognized as important as 🫘 or 🙎or 🥀?

I am now realizing that I follow every single person that has ever been a PhD student with David Baker.

This is the best paper written so far about the impact of AI on scientific discovery

The wait for trainable SoTA protein folding model is over! We are happy to introduce Protenix (Protein + X Molecules!), our Open Source reproduction of AF3, including inference code, dataset, weights, and training pipeline. Check our code: github.com/bytedance/Prot… 🧵 1/N

This summarizes things in Europe really well

This is a truly remarkable moment for omics.

We're living in the future.