Insights / Technology
Posts carrying the Machine Learning tag.
10 Mar 2026 · 4 min read
Three big AI drug discovery launches in 90 days: Boltz, IsoDDE, OpenFold3. Every benchmark was built by the team that built the model. The real question isn’t which model has the best benchmark. It’s whether discovery teams have a rigorous internal framework to evaluate any model that shows up. The real moat is evaluation discipline.
3 Mar 2026 · 2 min read
Lab-in-the-loop gets talked about like it’s a model problem. The Roche/Novartis/Microsoft panel at health.tech | global summit Basel made the real point clearer: it’s an operating model problem. Most orgs are at Level 1–2 maturity, and that’s already useful — the first big value isn’t more hits, it’s faster, more confident kill decisions.
22 Jan 2026 · 2 min read
NVIDIA and Eli Lilly are putting $1B into a co-located Bay Area lab where Lilly scientists and NVIDIA engineers build drug discovery models side by side. Not a typical AI partnership. The real story is closed-loop discovery, and the moat is the loop, not the model.
9 Dec 2025 · 3 min read
Most AI drug discovery decks assume chemistry will keep up — but small molecule chemistry is still slow, manual, and spread across vendors, which is where a lot of AI 'efficiency' quietly disappears. I look at why fixing chemistry first may be the real unlock, and at the teams finally treating it as the main problem to solve.
27 Oct 2025 · 1 min read
AI implementation in healthcare in the KSA is progressing at a breathtaking speed — I was inspired by Saad Alhuzami's case study on the MOH Cortex project at Global Health Exhibition, covering agentic AI, ML modeling, digital twins, and care orchestration.
22 Oct 2025 · 1 min read
I'm hosting a round table on November 27 in Schlieren, Zurich, bringing together pharma and Big Tech leaders to discuss what actually works — and what still fails — when applying AI in R&D. Expect candid, unscripted lessons on moving from pilot to platform, data governance, and where GenAI is genuinely helping in discovery, trial design, and safety.
6 Oct 2025 · 1 min read
I attended an inspiring talk from Sergei Yakneen, CTO at Isomorphic Labs, at BiotechX2025 in Basel — and it's clear that Google's Alphabet subsidiary is really onto something with their AlphaFold3-powered approach to AI drug discovery at scale.
6 Oct 2025 · 1 min read
I attended an exciting panel on GenAI's impact in preclinical development, featuring voices from Novartis, Insilico Medicine, and INVIDIA. Key themes included the balance of AI opportunity and risk, the power of robotics combined with AI, and the ongoing challenge of data organization and institutional memory in the lab.
21 Jul 2025 · 1 min read
I explore why bigger isn't always better when it comes to data in AI — and why, in healthcare especially, the real problem is data quality, not quantity. Curated, structured, interoperable data is what will make trustworthy clinical AI possible.
15 Jul 2025 · 1 min read
Participating in the SNOMED International board meeting in Manchester reinforces my conviction that SNOMED CT is absolutely critical for healthcare AI. As a board member chairing the Technology and Innovation Committee, I see firsthand how this global standard transforms fragmented health data into a reliable, structured foundation for AI innovation.
9 Oct 2024 · 1 min read
I attended a fascinating panel on the Hype vs Hope of AI in Drug Discovery at BiotechX in Basel this morning. The conversation surfaced some sharp insights on where AI is genuinely moving the needle in drug discovery — and where the hype still outpaces reality.