In 2007, John Van Drie wrote a perspective on what the next two decades of progress in computer-assisted drug design (CADD) might entail.

This post is an attempt to capture some thoughts I have about ML models for predicting protein–ligand binding affinity, sequence- and structure-based approaches to protein modeling, and what the interplay between generative models and simulation may look like in the future.

(This is a bit of a departure from my usual chemistry-focused writing.)

(Previously: 2022, 2023.) #1. Baldassar Castiglione, The Book of the Courier This book gets cited from time to time as a sort of historical guide to "being cool," since the characters spend some time discussing the idea of sprezzatura , basically grace or effortlessness. More interesting to me was the differences between Renaissance conceptions of virtue, character, &

This post assumes some knowledge of molecular dynamics and forcefields/molecular mechanics.

Abhishaike Mahajan recently wrote an excellent piece on how generative ML in chemistry is bottlenecked by synthesis (disclaimer: I gave some comments on the piece, so I may be biased).

I've been playing around with generating non-equilibrium conformations by molecular dynamics recently, and I've been thinking about how to best parse the outputs of a dynamics simulation.

Scientific software can be confusing, particularly when you're doing something that the software isn't primarily intended for.

Much molecular design today can be boiled down to “put the right functional groups in exactly the right places.” In catalysis, proper positioning of functional groups to complement developing charge or engage in other stabilizing non-covalent interactions with the transition state can lead to vast rate accelerations.

Pure mathematics has all sorts of unexpected connections to other fields, and chemistry is no exception.

Apologies for the long hiatus: we've had some health issues in the family, and startup life has been particularly overwhelming.