AI · Data Science · Drug Discovery

Thinking out loud
about science and AI.

Some of the biggest transformations happening in science are being driven by AI - and I think they should be accessible to everyone, not just people with a computer science or machine learning background. I write here about how industries are constantly adapting, the most significant implications for drug discovery, what models exist and what they've unlocked - and, most importantly, how to use them. But also where the gaps are, what the field is still working out, and how to tell the difference between advances and hype. I also write about teams and collaboration - and why bringing different disciplines together is what turns a model into a discovery, or a new method into something clinically useful. A mix of opinion, industry analysis, technical posts, and coding tutorials.

Tutorials & Guides Coming soon Linear algebra for scientists - a coding-first guide A plain-language, code-first walkthrough of the linear algebra behind machine learning. Based on Chapter 2 of the Deep Learning textbook - written for scientists who didn't come from the maths side.

Opinion Coming soon Great science needs more than scientists The benefits of diversity within teams extends beyond workplace culture. In my experience, diversity of background has consistently improved scientific outcomes - a pattern I believe has a specific and often underappreciated explanation.

Industry & Research Coming soon How AI is changing drug discovery The industry is reorganising. AI-designed drugs are reaching clinical trials. Pharma companies are embedding AI infrastructure directly into their R&D pipelines. This post covers the most recent milestones, what the evidence suggests, and the honest open questions about whether this could lead to better medicines.

Tutorials & Guides Coming soon Probability and information theory for scientists: the Deep Learning book, Chapter 2 The follow-up to the linear algebra tutorial. Probability distributions, expectations, entropy, KL divergence - with Python code to support. The mathematical foundations that underpin nearly every modern ML model.

Technical Coming soon A working scientist's guide to biological foundation models: what exists, what it does, and how to use it A long-form reference covering the major foundation models reshaping biology - AlphaFold, ESM-2, RFdiffusion, DiffDock, Geneformer and others. For each: what biological question it answers, what you need to run it, and where to start depending on your research area. Written for researchers with domain knowledge but aren't sure what tools exist to help answer their questions.

Thinking out loudabout science and AI.

Thinking out loud
about science and AI.