Registration for the 2021 RDKit virtual UGM is now open: eventbrite.com/e/virtual-10th…

Five great choices! These plus Wyatt and Warren's "strategy and control" will always hold the top spots on my organic book shelf! 📚👑#OrgChem

There is nothing quite like quite sleeping in the same room as a PC training an ML model during these hot days. I imagine sleeping under a Falcon 9 rocket would be just as quiet and cooling. Can't wait for the summer. 🥲🔥🖥️

Want to know more about AlphaFold 2? I wrote a commentary explaining how it works, why it performs so well, and what it might do for biology now that it is freely available. blopig.com/blog/2021/07/a…

A structural model of the SARS-CoV-2 spike protein as the virus fuses with host human cells reveals an opportunity to disrupt dynamics and halt transmission elifesciences.org/articles/70362…

Ever wanted to view protein structures directly in #VSCode? I put together an extension for exactly that! marketplace.visualstudio.com/items?itemName…

A new Science analysis of data from U.S. military recruits suggests multiple sclerosis—a disease considered of unknown etiology—is a complication of infection with Epstein-Barr virus. Learn more ⬇ fcld.ly/sicotxm #SciencePerspective: fcld.ly/ehqno7q

I "grew up" as a statistician. When I later learned about machine learning, I found it a mind-blowing new perspective on data modeling. The best data modelers don't ideologically follow one mindset but have many at their disposal. But which modeling mindsets are there? 🧵

Born #OTD 1917: Robert Burns Woodward, the greatest organic chemist of the 20th century. Woodward's feat in complex organic synthesis and his sheer stamina made him a living legend. Woodward has the most Nobel Prize nominations - 111 - and won it in 1965

This is hands down the greatest talk on Machine Learning ever made. It was a keynote at ICLR and is now public! Thank you Been Kim for being such an incredible person and always taking your time to articulate your thoughts so well. Watch it at: youtube.com/watch?v=Ub45cG… 👀‼️

I got a special surprise for you all... We just released the first 5.5 hours of our new course "From Deep Learning Foundations to Stable Diffusion", for free! fast.ai/posts/part2-20…

💯 RL, especially outside of the gym scene, is exceptionally hard to make efficient. Training sufficiently deep networks on high-D data or in computationally expensive environments is v difficult. But it is one of many challenges holding back the field, especially for drug disc💊

I usually let this stuff go, but this is too over the top In splashy #JPM23 PR, Absci claim they can de novo design antibodies from scratch, but they actually design just the CDR3 (of 6 total) of existing Tx antibodies to their orig targets. That's not de novo design

This is a really exciting position to work on some great problems within a welcoming and insanely experienced team! ⚛️💊🧑‍💻 #QMMM #AI #drugdiscovery

This is the most surprising and exciting result of my career: we were running simulations of NaCl with a neural network potential that implicitly accounts for the effect of the water, ie a continuum solvent model (trained on normal MD) when Junji noticed something strange: 1/n

We were named 'Best Performing R&D Services Provider' at the One Nucleus Awards last night! A real testament to our award-winning team's expertise, dedication, and innovation in driving impact in #drugdiscovery and development. Congratulations to all the finalists and winners!