Follow Datanami:
October 6, 2023

New AI Technique Helps Find Alzheimer’s Drug Targets

The use of artificial intelligence in discovering and developing new medication has been in progress for more than a decade. However, the recent advancement in AI technology and research has truly enabled us to bridge the gap between theory and realistic treatment options. 

Incilico Medicine and the University of Cambridge jointly published a paper in Proceedings of the National Academy of Sciences (PNAS), on the success of an AI-based technique that has enabled a major breakthrough in identifying new targets for  Alzheimer’s and other diseases with protein phase separation (PPS).  

Dr. Michele Vendruscolo, lead author and co-director of the Centre for Misfolding Diseases at the University of Cambridge has called the breakthrough a “game changer.” 

PPS can lead to different types of neurodegenerative diseases and cancers as it causes “clogging” of molecules. Dr. Vendrucolo pioneered a new method, called FuzDrop, to determine which proteins in the body will undergo PPS. The FuzDrop method is able to predict which proteins will undergo phase separation by performing a sequence-based identification of both droplet-promoting regions and aggregation-promoting regions within droplets.

However,  it has been a challenge to find the link between these proteins and the relevant diseases so new treatments can be developed. Now for the first time, AI technology has allowed us to bridge this gap.

A team of researchers headed by Dr. Vendruscolo and Insilico Medicine’s AI target discovery platform, PandaOmics, has enabled the FuzDrop method to discover three new targets associated with Alzheimer’s disease. This has paved the way for future drug development not just for Alzheimer’s but also for other diseases and cancers. 


Insilico Medicine is one of the leading generative AI drug discovery and biomarker development companies. Based out of Hong Kong, the company is advancing new therapeutics using gen AI. Insilico uses clinical trial analysis with next-generation AI systems to help in the discovery and development of innovative drugs. It has been collaborating with the University of Cambridge since September 2021 to find new ways to identify solutions to PSS-prone diseases, such as Parkinson’s’ and Alzheimer’s.  

Commenting on the breakthrough, Insilico Medicine founder and CEO Alex Zhavoronkov, told Datanami that “ Protein phase separation has been a key research focus for scientists like Dr. Vendruscolo who have long understood the important role it plays in diseases like Alzheimer’s and Parkinson’s, as well as cancer. But until this method was applied, they were not able to connect the proteins involved in this process with diseases in order to identify actionable targets for the development of new drugs.”

He also told Datanami that “PandaOmics uses AI to sift through massive quantities of data – including OMICs data, and data from clinical trials, grants, patents, and publications, in order to identify targets – connections between biological processes and diseases that can be acted on by drugs to stop a disease progression.”

(Panchenko Vladimir/Shutterstock)

Dr. Vendruscolo’s FuzDrop method was combined with Incilco Medicine’s AI target discovery engine, PandaOmics, to discover that connection with specific diseases to find targets. PandaOmics uses AI technology to search through huge quantities of data – including OMICs data, and data from clinical trials, patents, publications, and grants,  in order to identify targets – connections between biological processes and diseases that can be acted on by drugs to stop a disease progression. 

“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.”

Related Items

Med-PaLM 2: Google Cloud Unveils AI Medical Language Model

Policlinico Gemelli and Palantir Technologies Partner to Use AI to Advance Data Science for Healthcare

Know Your Virome? The Reason Why AI Is Helping Our Health