Drug Potential from Protein-Protein Interactions

Instead of seeing the future of pharmaceuticals as the end of blockbusters, maybe it is more like the beginning of precision drug discovery. In BMC Bioinformatics, Nobuyoshi Sugaya and Kazuyoshi Ikeda of PharmaDesign in Tokyo describe one higher-precision approach in “Assessing the druggability of protein-protein interactions by a supervised machine-learning method.” Here, the authors describe a supervised machine-learning method that searches for protein-protein interactions that could make good targets for small molecules.

Such an approach can look at lots of potential targets quickly—potentially reducing breadth of the protein space to explore. As the authors write:

… there is both need and opportunity for development of a methodology that can efficiently select drug target PPIs [protein-protein interactions] by holistic assessment of the druggability of PPIs with the omics data.

Moreover, in the best cases, Sugaya and Ikeda’s technique found known examples of good targets in protein-protein interactions from others with an accuracy of 81 percent.

So technologies such as this one, could enhance the precision of drug discovery by going after the targets with the most potential.

To share this with colleagues ...

Close Bookmark and Share This Page

Save to Browser Favorites / Bookmarks