Dundee researchers develop 'automatic drug designer'

Researchers say an automated design system could create drugs quickly and cheaply

Researchers at the University of Dundee believe a new automated design system could create drugs quicker and cheaper than currently possible.

The scientists have adapted the "Moneyball" approach, which uses the principles of advanced statistical and data analysis to speed up research.

They used a computer to test the evolution of drug molecules and found their predictions to be 75% correct.

The technique could lead to new cheaper and safer treatments for illness.

The University of Dundee researchers are trialling the system on the creation of drugs to treat infectious diseases.

Evolved solution

Chair of Medicinal Informatics at Dundee Prof Andrew Hopkins said: "One of the things that makes drug discovery so hard is that you're trying to improve several different properties at the same time.

"Evolution is a mechanism that can be applied to solving these kinds of problems, and the iterative (repeating) process of adaptation and selection of hundreds of thousand of possible solutions can be simulated in a computer.

"We have effectively proved the concept of automated design of new compounds showing that by using algorithms to process massive amounts of data, we can tackle problems of huge complexity."

Prof Hopkins said there were very real implications from the research.

Faster process

"Potentially the system could make the process of drug creation more efficient by reducing failure rates in testing and showing chemists which of the potential thousands of solutions would be best-suited to their problem," he added.

"The system mimics the design process of human chemists but runs it on a very large scale at a faster rate."

Prof Hopkins and colleagues used the drug donepezil, used to treat people with Alzheimer's disease, to test the automated system.

He said: "We took the structure of donepezil as a starting point and from there the system evolved its structure over many generations to a variety of different profiles across a range of drug targets.

"The predicted profiles were then tested experimentally and we found that 75% of them were confirmed to be correct.

"This proof of concept shows that we could make significant advances in discovering and designing complex drugs, which could lead to improvements in safety and efficacy, while also potentially reducing the cost of drug discovery which is a high-risk and expensive process."

The research was funded by the Biotechnology and Biological Sciences Research Council and is published in the Nature journal.