I write about machine learning and biology, with a focus on practical applications in drug discovery, AI strategy for biotech, and career guidance for computational scientists. Below are featured articles that give an idea for what I like to write about - read the full posts on Substack.
Companies that scaled before ChatGPT (Nov 2022) are “AI-encumbered”—structurally disadvantaged against AI-native startups. The real dividing line isn’t age, it’s whether your organization was built with AI from day one versus bolting it onto existing systems.
Protein structure prediction advanced dramatically, but therapeutic antibody design faces a bottleneck: accurately predicting CDR loops, especially CDR H3, for novel sequences.
Breaking into AI for Bio requires 1-5 years of sustained effort: solid fundamentals, meaningful research experience, demonstrated execution ability, and strong engineering practices. What actually matters when hiring managers review candidates.
AI/ML value in drug discovery comes from automating routine decision-making and data synthesis. Protein binding prediction grabs headlines but misses the actual bottlenecks where ROI lives.