A team led by John Karanicolas, PhD, created a computer program that identifies drugs that fit with proteins specific to particular diseases.

"[Lead author] Yusuf [Adeshina, PhD] developed this machine learning classifier that we trained to distinguish between things that work and things that wouldn't," Karanicolas said in a statement released by Fox Chase. "We did this by showing it examples of real drugs bound to their protein targets and a series of very compelling decoys that we had generated."

The researchers tested the model by evaluating protein-drug combinations it hadn't encountered before, then programmed it to identify which combinations would be effective. It outperformed every other approach the team has used to determine which compounds should be lab tested, according to the group.

"For many different projects in my lab, we're already trying to target different oncoproteins, and we've been using this tool because it works so well," Karanicolas said in the statement. "In addition to that, it's really a resource for the scientific community. Others can also use this so that their virtual screening approaches work better."

Machine learning helps identify antimicrobial-resistant bacteria
A new graphical user interface-driven, machine learning-based approach has successfully identified antimicrobial resistance genes for gram-positive and...

Computer tools shorten development time for SARS-CoV-2 drugs
Computer-based tools are helping researchers find potentially promising candidates for vaccines and treatments for SARS-CoV-2 -- and much more quickly...

Big data analysis of images may aid vaccine development
A new pipeline that combines high-dimensional microscopy with big data analysis to gain molecular insights in T-cell biology and vaccine development was...

Scientists explore SARS-CoV-2 main protease as a drug target
A team of researchers report the structure of the main protease of the novel coronavirus and have identified several drugs that show promise in combating...