There's a glorious story of the first computationally designed personal mRNA cancer vaccine for a dog. A civilian with no cancer or biology training—but with AI experience—used LLMs to plan and help design a cancer vaccine for his dog. Come on! This is wonderful. It's doubly wonderful because of his persistence and the...

There's an upbeat article in The Economist: An AI revolution in drugmaking is under way (5 January 2026).  It rehashes figures from a 2024 study: AI-designed drugs are whizzing through the preclinical phase (that before human trials begin) in only 12-18 months, compared with three to five years previously. And the...

During drug development, you want to know the affinity between a molecule (potential drug) and its target, such as a protein on the surface of a cell. That is: does this particular molecule tightly fit at a specific place and stay there? Key in a lock, hand in a glove, are the analogies.Today ML can't solve...

Reading: Scalable synthetic biology revolutionizes targeted therapy with logic-gate proteins, News Medical, 10 October 2025.This is right up my street: building up a logic gate in a protein. It goes something like this. You have some therapeutic payload (a drug, say), connected (tethered) to other molecules that are...

A quote from around 18 minutes into the David Liu: A Master Class on the Future of Genome Editing podcast: Virtually every substance we've ever put into a person, including just about every medicine we've ever put into a person, has off-target effects, meaning [the substance] modulates the function of biological...

I’m interested in the idea of replacing animal models with human-derived ways to assess drugs. Animal models make sense in that we share evolutionary history, but that’s not the same as human testing. One new approach is to use microphysiological systems (MPS), colloquially known as “organ-on-a-chip” (OOC). Why MPS To...

From a speech by Secretary of State for Science, Innovation and Technology, 10 June 2025: Boston might be the birthplace of biotech. But – with Google DeepMind on one side and the Crick on the other - King’s Cross is emerging as a global powerhouse for AI-driven drug discovery. Today, we’re launching a new project,...

ChEMBL is a database of drug targets, molecules, and measurements of the activity of the molecules on targets. It has an online interface, but I’m more of a SQL person, and so I download the PostgreSQL or SQLite copies of the data. There is a large and comprehensive schema diagram, supporting descriptions, and an FAQ....

Figuring out what happens when two molecules come together is computationally hard. Free Energy Perturbation (FEP) calculations are powerful, but wow, they take a while to run. The last estimate I had for this was something like 1 GPU per protein-ligand (“drug”) per day. Not the same, but related, is Boltz-1. It’s an...

One step in drug discovery is a claim on intellectual property. There are various form of this, including rights on data from experiments, but a patent on “composition of matter” is an obvious one. This means, if you’re generating molecules, it would be useful to know if the molecule is subject to a patent—although not...

The two main kinds of drug discovery projects I’m familiar-ish with are small molecules (e.g., oral drugs) and antibodies. There are others, and proximity therapeutics is one I know nothing of. I know a bit more now, after attending a one-day single-track conference on this topic at The Francis Crick Institute on...

I’ve been digging through some old notes recently, and found a list of resources to share. Some of these are from a while back, but still useful I think, if this is an area of interest to you. Modern drug design for dummies. A blog by Tomasz Wegrzanowski from 2006, covering the fundamentals of (small molecule) drug...

Yesterday I was at UCL for a presentation called “Target 2035: A 2000-protein experiment to ligand the human proteome”. It’s a project from the Structural Genomics Consortium (SGC, which UCL has just joined). The aim is to create large and open dataset for drug discovery Thinking of the success of AlphaFold in...

Interview with Helen Berman: The huge protein database that spawned AlphaFold and biology’s AI revolution, Nature, 18 October 2024. PDB is an important database of protein structures. I’ve always thought the file format (.pdb) was unusual—not bad unusual, just a fun and quirky. I now have a glimpse of why: Q: How did...

Schrödinger’s software is something I’ve wrangled for molecule screening. Here are my notes on set up, management, and general clues I’ve accumulated. No warranties express or implied. License manager We’re running on cloud hardware, using the FlexNet license manager. For the license manager node, you need a fixed MAC...