List view / Grid view
Can automation and AI finally make science run at the speed of thought? Eric Ma shares how disciplined systems, not new models, will drive the next wave of discovery.
Everyone talks about AI speeding up drug discovery, but Eric Ma explains why, without clean data and statistical discipline, it can actually do the opposite.
Part II shows that the predictive validity crisis can be solved by rethinking how the industry chooses models, measures outcomes and integrates systems. Success stories from Vertex, Regeneron and AstraZeneca illustrate how aligning biology, measurement and strategy can reverse decades of declining productivity.
Drug discovery now costs 100 times more per FDA-approved drug than in 1950, despite vast advances in biology and computing. The core problem is the collapse of predictive validity in preclinical models, which sits at the heart of pharma’s productivity paradox.
AI is starting to transform drug discovery, but progress is still slow and big challenges remain. Thibault Géoui explores the gaps, hurdles and breakthroughs needed before it can truly change pharma R&D.
Thibault Géoui explains why AI could finally help pharma overcome its productivity crisis and why the payoff won’t come as quickly as the optimists claim.
What role could large language models and AI agents play in drug safety? In Part 3, Layla Hosseini-Gerami of Ignota Labs discusses how emerging technologies might make toxicity analysis faster, more accessible and part of the drug discovery workflow from day one.
Why do so many drug candidates fail before reaching patients – and can AI help stop the losses? In Part 2, Layla Hosseini-Gerami of Ignota Labs outlines the scope of the toxicity problem and explains why failures often come too late to fix.
Why do so many drug candidates fail before reaching patients – and can AI help stop the losses? In Part 1, Layla Hosseini-Gerami of Ignota Labs outlines the scope of the toxicity problem and explains why failures often come too late to fix.
As the lab–data science divide continues, Ian Kerman looks ahead to a future of deeper collaboration – one where shared skills, smarter tools and a shift in mindset could finally break down the barriers. In this second interview, he shares his vision, practical ideas and advice for the next generation…
Lab scientists and data scientists often speak different languages and that miscommunication can slow down important research. In this interview, Ian Kerman shares how his team is working to break down those walls and spark better collaboration.
As AI reshapes scientific work, two founders debate how best to build tools scientists can trust — should we embed expertise into the model or the team? From agent-powered labs to hypothesis-generating machines, the future of drug discovery is being reimagined right now.
AI is reshaping drug discovery – but not without resistance. In this two-part conversation, André França and Eli Pollock share honest insights about the real barriers to AI adoption in life sciences and how embedding domain expertise into AI workflows might be the key to unlocking its full potential.
In this second interview of the series, Andreas Kolleger, Head of GenAI Innovation at Neo4j, discusses how knowledge graphs and AI are transforming scientific discovery and improving life sciences workflows.
In this first interview of a two-part series, Andreas Kolleger explores the convergence of knowledge graphs and large language models. As the head of GenAI innovation at Neo4j, Andreas brings a unique cross-industry perspective on how these technologies can enhance life sciences workflows.
