Contrastive learning-based model ConPLEx elevates drug-protein interaction predictions

[Generative AI image from Tahsin/Adobe Stock]

Drug discovery, traditionally a labor-intensive process, often involves extensive computational work during experimental screening. Advances in AI, however, promise to streamline this process. To that end, a team from MIT and Tufts has introduced ConPLex, a computational model that uses large language model techniques, similar to those behind ChatGPT. The model analyzes vast amounts of text data to discern patterns and relationships among amino acids. The technique matches potential drug molecules to their target proteins without requiring complex molecular structure computation. The system’s efficiency allows it to sift through an array of more than 100 million compounds in a single day.

Bonnie Berger, head of the Computation and Biology group in MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), and one of the senior authors of the new study, ex…

Read more
  • 0