Groups craft algorithms to rank drug contenders

Here's the latest on Google-like strategies in drug design. Early this year, Andrew Hopkins of the University of Dundee in Scotland published an article in Nature Chemistry about his "QED" algorithm for ranking the "drug-likeness" of compounds based on attributes of 771 approved oral meds, Bio-IT World reports. And now his research has sparked more work on applying such algorithms in the biopharma industry.

British biotech software outfit Optibrium, for instance, has been trying to optimize the "QED" (quantitative estimate of drug-likeness) for use in biopharma, incorporating variables beyond those from approved drugs to make sure drug developers don't miss a winner, the magazine reports. But don't count on these algorithms to put medicinal chemists out of work anytime soon.

"We can't make perfect predictions. We need to think about what decisions we can make with confidence without throwing away potentially good compounds," Matt Segall, CEO of Optibrium, told Bio-IT World.

Labs may still need to verify the insights from algorithms in wet lab experiments, but there's no question that software and analytics have become more popular instruments in determining the side-effect profiles and bioavailability of compounds before expensive human clinical trials, as biopharma outfits try to limit costly failures in their pipelines.

- get more in the Bio-IT World article

Related Articles:
Novartis predicts drug side effects with computers
Stanford algorithm uncovers drug side effects

Like what you're reading
Click here to get more news delivered to your inbox every week>>

Suggested Articles

The new solution aims to streamline the incorporation of human genomic data into clinical trial designs.

TriNetX's platform uses EHR data to help drug developers with clinical trial protocol design and study site and participant identification.

The $58 million financing round represents biopharma industry's growing interest in genomics data.