The research team, led by the University of Cambridge, presented an approach to identify therapeutic targets for human diseases associated with a phenomenon known as protein phase separation, a recently discovered phenomenon widely present in cells that drives a variety of important biological functions.

Protein phase separation at the wrong place or time could disrupt key cellular functions or create aggregates of molecules linked to neurodegenerative diseases. It is believed that poorly formed cellular condensates could contribute to cancers and might help explain the aging process.

The Cambridge researchers, working in collaboration with generative artificial intelligence (AI)-driven drug discovery company Insilico Medicine, developed a method for finding new targets for drug discovery in diseases caused by dysregulation of the protein phase separation process. The team found that they could replicate disease characteristics in cells by controlling the behaviour of these targets. Their results are reported in the Proceedings of the National Academy of Sciences (PNAS)

In the study, researchers combined Insilico’s proprietary target identification engine PandaOmics with the FuzDrop method to identify disease-associated proteins prone to phase separation. PandaOmics is an AI-driven therapeutic target discovery tool that integrates multiple omics and text AI bioinformatics models to assess the potential of proteins as therapeutic targets.

FuzDrop is a tool introduced by the Cambridge team, which calculates the propensity of a protein to undergo spontaneous phase separation, aiding in the identification of proteins prone to form liquid-liquid phase-separated condensates.

Using this approach, the researchers conducted a large-scale study of human sample data, quantified the relative impact of protein phase separation in regulating various pathological processes associated with human disease, prioritised candidates with high PandaOmics and FuzDrop scores and generated a list of possible therapeutic targets for human diseases linked with protein phase separation.

The researchers validated the differential phase separation behaviours of three predicted Alzheimer’s disease targets (MARCKS, CAMKK2 and p62) in two cell models of Alzheimer’s disease, which provides experimental validation for the involvement of these predicted targets in Alzheimer's disease and support their potential as therapeutic targets. By modulating the formation and behaviour of these condensates, it may be possible to develop new interventions to mitigate the pathological processes associated with Alzheimer's disease.

Source: https://www.cam.ac.uk/research/news/ai-driven-techniques-reveal-new-targets-for-drug-discovery