Translucent robotic looking hand holding a test tube next to a screen showing code and a digital pill to symbolize the use of AI to develop new protein phase separation drugs
Credit: Yuuji/Getty Images

A collaboration between artificial intelligence (AI) biotech Insilico Medicine and the University of Cambridge has presented a new technique to identify drug targets for diseases where protein phase separation regulation is abnormal, such as Alzheimer’s and Parkinson’s disease and some cancers.

Using a combination of Insilico’s AI-driven target identification engine PandaOmics and the FuzDrop method for predicting PPS, the investigators identified a method to identify PPS-prone disease-associated proteins.

“It has been challenging so far to understand the role of protein phase separation in cellular functions,” said Michele Vendruscolo, a professor at the University of Cambridge and lead author on the PNAS paper, in a press statement.

“Even more difficult has been to clarify the exact nature of its association with human disease. By working with Insilico Medicine, we have developed a multi-omic approach to systematically address this problem and identify a variety of possible targets for therapeutic intervention. We have thus provided a roadmap for researchers to navigate this complex terrain.”

Protein phase separation (PPS) is an important cellular process that drives the formation of membraneless organelles within cells. These are important for a number of different processes including packing molecules for transport, sensing environmental changes, and assembling proteins, among others.

Due to its wide use in the cell, abnormal PPS can contribute to various diseases, for example, by creating aggregates of molecules such as those seen in neurodegenerative diseases such as Alzheimer’s and Parkinson’s.

In this study, the researchers used PandaOmics, which uses omics data and text-based AI models to estimate whether proteins will make good therapeutic targets or not. They also used the FuzDrop method, developed by Vendruscolo and team, to assess the likelihood of a protein spontaneously going through phase separation. Combining this data together, the researchers created a possible therapeutic target list for diseases with a link to abnormal PPS.

To validate their method, the team analyzed three potential Alzheimer’s disease target proteins –MARCKS, CAMKK2 and p62– in two different cell-based models of the disease. The results suggest abnormal phase separation of these proteins is involved in Alzheimer’s disease and that they could be useful drug targets.

“We are pleased to reach this milestone in our collaboration with the University of Cambridge,” said Frank Pun, PhD, head of Insilico Medicine Hong Kong, and co-author of the paper.

“The study is intended to provide initial directions for targeting PPS-prone disease-associated proteins. With ongoing technical advancements in studying the PPS process, coupled with growing data about its roles in both cellular function and dysfunction, it is now possible to comprehend the causal relationship between PPS targets and diseases. We anticipate facilitating the translation of this preclinical research into novel therapeutic interventions in the near future.”

Also of Interest