<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Leon Ross</title><description>Leon Ross — MPhil Computational Biology at Cambridge. ML for perturbation biology, drug target discovery, and early-stage startups.</description><link>https://leonross.me/</link><item><title>Example · Company: Recursion — industrialising phenotypic screening</title><link>https://leonross.me/writing/recursion-pharmaceuticals/</link><guid isPermaLink="true">https://leonross.me/writing/recursion-pharmaceuticals/</guid><description>Recursion bet that massive automated cell imaging plus ML beats hypothesis-driven discovery. The platform is real; the open question is whether it produces differentiated clinical assets faster than the money runs out.</description><pubDate>Tue, 27 Oct 2026 00:00:00 GMT</pubDate><category>company</category><category>techbio</category><category>drug-discovery</category><category>platform</category></item><item><title>Example · Paper: GEARS — predicting transcriptional outcomes of novel multigene perturbations</title><link>https://leonross.me/writing/gears-perturbation-prediction/</link><guid isPermaLink="true">https://leonross.me/writing/gears-perturbation-prediction/</guid><description>GEARS uses a gene-relationship graph to predict expression changes for unseen single and two-gene perturbations. The headline numbers are strong, but later benchmarks suggest simple baselines close much of the gap.</description><pubDate>Tue, 20 Oct 2026 00:00:00 GMT</pubDate><category>paper</category><category>perturbation</category><category>single-cell</category><category>graph-neural-networks</category></item></channel></rss>