My life & career
Imagine a medicine designed to interact with a precise biological target rather than relying on a long search for something that might work. This is a promising direction of research—not a cure on demand.
Imagine a researcher describing the exact biological job a treatment needs to perform, then designing a protein to try doing it.
Think of proteins as tiny machines that perform much of the work inside our bodies. For a long time, scientists had to discover their shapes through difficult experiments before they could begin to understand how they behaved. Computer systems can now predict enormous numbers of protein structures, giving researchers new starting points for the search for treatments. They are also beginning to design proteins with particular jobs in mind. The remarkable possibility is that future medicines could be built for specific biological tasks rather than found largely through trial and error. But every promising design still needs careful testing to prove it actually works and is safe.
Big change is fascinating. Its implications are what matter.
Imagine a medicine designed to interact with a precise biological target rather than relying on a long search for something that might work. This is a promising direction of research—not a cure on demand.
Drug developers may be able to search more potential designs and focus experiments on better candidates. Success will still be measured in safe, effective treatments, not the number of structures generated.
Pharma, biotechnology and diagnostics may see parts of their discovery processes redesigned around AI and automated experiments. The opportunity is speed with better evidence.
Jim has discussed the shift from reactive healthcare to predictive and increasingly personalized medicine throughout his work with healthcare and life-science organizations.
Meet the futurist behind YottaBit ↗Look at one difficult disease. What specific experiment would show whether a new designed protein actually helps?
Here's what researchers have demonstrated, what's still ahead, and where to check the source. It should deepen the story—not get in the way of understanding it.
What's happening today: 200m+ structure predictions enlarge hypothesis space.
The next challenge: A predicted protein is not a treatment. It still has to work in living systems and survive clinical testing.
How the technologies connect: Structure prediction + protein design + high-throughput wet labs.
EMBL-EBI & DeepMind — AlphaFold Protein Structure Database ↗