James McCabe

Hi, I'm James, a second-year PhD student working where evolutionary biology, structural biology and artificial intelligence meet.

Cytokines are the proteins cells use to talk to one another, and that conversation sits at the centre of three diseases at once: viruses counterfeit cytokines to switch the immune system off, inherited faults in the same receptors cause immunodeficiency and chronic inflammation, and tumours lose them to escape immune control. The same handful of amino acids tends to matter in all three.

My PhD, EVOLVE-AI, asks which individual residues carry that function. AI protein language models learn what a protein can tolerate from sequence alone, but they are trained on databases that cover some branches of life far better than others. So I set them against the record of natural selection across thousands of vertebrate genomes, asking where the model goes blind and whether that blindness can be predicted. The aim is a map of the positions worth acting on: the sites viruses exploit, the ones that drive disease when they go wrong, and the ones worth engineering into better therapeutics.

Alongside the PhD I write open-source scientific software, including SCEPTR, a tool for characterising transcriptomes built at the Institute of Microbiology of the Czech Academy of Sciences. It lives on my GitHub.