✳flâneur — a map of the web's best reading

An idiot's guide to lead optimisation for proteins | Magnus Ross

magnusross.github.io · 3,962 words · saved by 1 readers

Lead optimisation is the step in drug design where you take a molecule that sort of works and try to make it actually work, and it’s arguably the step where most real-world design campaigns succeed or die. Due to the influence of a couple of my pals, I have recently become interested in using machine learning to do lead optimisation for proteins. Said pals have been kind enough to indulge my extremely beginner level questioning over the few weeks. I’m going to use this post to share what they have taught me, in the hope it might in turn help you understand a bit more about this fascinating area. Like any field, there are some established principles that are never spelled out explicitly in the literature, which can make it confusing for newcomers. We’re going to try to understand how we could actually build a real system for lead optimisation but studying one that has been shown to work well in real life. Firstly, before we get into it, what actually is a protein? I think to answer this

An idiot's guide to lead optimisation for proteins | Magnus Ross An idiot's guide to lead optimisation for proteins 2026/05/08 Or, understanding the Cradle-1 pipeline. Lead optimisation is the step in drug design where you take a molecule that sort of works and try to make it actually work, and it's arguably the step where most real-world design campaigns succeed or die. Due to the influence of a couple of my pals , I have recently become interested in using machine learning to do lead optimisation for proteins. Said pals have been kind enough to indulge my extremely beginner level questioning

Explore this link on the map →

saved by

related reading