Advancing discovery of better drugs and medicine

With the help of AlphaFold, researchers are designing more effective drugs like never before

Karen Akinsanya is President of R&D, Therapeutics, at Schrödinger in New York City. She shares her AlphaFold story.

What has always captivated me is the idea that you can go from the bench to the bedside.

I have worked in academia and in drug discovery and development. This means I’ve not only studied proteins and genes and understand how to make a therapeutic molecule against a disease-causing target, but I’ve also been at the bedside of a patient as they receive that new medicine.

But the real question is, how can we improve the way we do that? People are still dying of cancer and heart disease every single day while they wait for us to find solutions.

I always say that mother nature is thrifty. When you come across a target for a new drug, you often find other potential targets that are like brothers and sisters and cousins. Each target is a protein on the surface of a cell that the drug binds to, called a receptor. The challenge for people working in drug discovery is finding a drug or molecule that binds one member of that family – the target – and inhibits that family member, but doesn’t inhibit the rest of the family. In part, this is where AlphaFold has worked so brilliantly for us.

In some cases AlphaFold – in combination with our own physics-based software that simulates how atoms interact – is enabling us to begin to simulate not just what single family members are doing, but how different family groups are behaving.

Being able to design a selective drug that hits just one specific target is one of the most important things in drug discovery.

This is particularly important when designing drugs for our endocrine hormone system, which is regulated by the pituitary gland and a number of hormones and messengers that circulate in the body.

As part of our recent work we’ve been looking at ways we could design molecules that selectively replicate the actions of natural messengers, in particular those that affect how our brain functions. In this case we’re focused on neurotransmitters for many neurological diseases, including conditions like schizophrenia and bipolar disorder.

What we’ve found exciting is that using predictive structures from AlphaFold alongside our structure-refinement and drug-design software potentially allows us to design a molecule that targets a family member of interest – in this case a signaling partner in the brain – with exquisite accuracy. This is something that people have been trying to do for years and has a whole host of potential outcomes for treatment.

Still, at the end of the day, it’s not until this medicine reaches a real person that you see what the culmination of all of that research is. Is it actually going to make a difference?

Since way back when James Watson and Francis Crick discovered the double-helix structure of DNA, we’ve been trying to better understand the building blocks of how and why our bodies work, and how and why they sometimes go wrong. As a human race we’re asking: what is the code for life? In terms of drug discovery, AlphaFold is an additional piece of that puzzle. Each of the pieces needed for drug design is extremely complex. But putting a few of the pieces together could accelerate drug discovery in a way we’ve never seen ever before.