Monash University researchers develop AI tool for drug discovery

By Our Reporter
0
159
Physicochemical graph neural network for learning protein-ligand interaction fingerprints from sequence data

A new artificial intelligence (AI) tool, PSICHIC, developed by researchers at Monash University, is set to transform the landscape of drug discovery by making virtual screening more efficient and cost-effective. This breakthrough aims to enhance scientists’ ability to identify potential new medicines swiftly and accurately.

Current computational methods in drug discovery have limitations, particularly in predicting the strength of interactions between molecules and proteins. These interactions are crucial for identifying viable drug candidates. PSICHIC (PhySIcoCHemICal) addresses this gap by leveraging AI to decode protein-molecule interactions using sequence data alone, bypassing the need for costly 3D structures.

Published in Nature Machine Intelligence, the study showcases PSICHIC’s capability to perform with state-of-the-art accuracy. This tool eliminates the need for less accurate and expensive processes, such as 3D modelling, by using AI to analyse sequence data. Dr Lauren May from the Monash Institute of Pharmaceutical Sciences (MIPS) highlighted PSICHIC’s effectiveness in screening new drug candidates and conducting selectivity profiling.

Dr May shared that experimental and AI predictions of a large compound library against the A1 receptor—a potential therapeutic target for various diseases—proved PSICHIC’s ability to identify novel drug candidates. Additionally, PSICHIC could distinguish the functional effects of the compounds, providing insights into how these drugs might interact within the body.

Professor Geoff Webb from Monash’s Department of Data Science and Artificial Intelligence, who led the development, noted that while existing methods for predicting protein-molecule interactions are expensive and limited, PSICHIC offers a more affordable and accurate alternative. By eliminating the need for high-resolution 3D structures, PSICHIC significantly enhances the efficiency of drug screening.

Dr Lauren May, co-lead author from the Monash Institute of Pharmaceutical Sciences, said the team has already demonstrated that PSICHIC can effectively screen new drug candidates and perform selectivity profiling

Dr Anh Nguyen, a co-lead author from MIPS with expertise in AI and drug-receptor interactions, underscored the importance of these interactions in biological processes and drug efficacy. AI’s role in improving affordability and accuracy in drug discovery is rapidly expanding, and PSICHIC’s innovative approach addresses many of the challenges faced by traditional methods.

PhD candidate Huan Yee Koh, from Monash’s Faculty of Information Technology, pointed out that many AI systems rely on pattern matching, which can limit their ability to discover new drugs. PSICHIC overcomes this by incorporating physicochemical constraints into its AI model, allowing it to decode protein-ligand interactions from sequence data without requiring costly structures.

Professor Shirui Pan from Griffith University emphasised PSICHIC’s accessibility, as it only requires sequence data. This approach provides a more faithful representation of protein-molecule interactions, closing the performance gap between sequence-based and structure-based methods.

The PSICHIC team has made their data, code, and optimised model available to the scientific community, promoting further research and development in this field. More information can be found at www.psichicserver.com.

For those interested in the detailed study, titled “Physicochemical graph neural network for learning protein-ligand interaction fingerprints from sequence data,” it is available for reading. Co-lead authors Professor Geoff Webb and Dr Lauren May are open for interviews to discuss their groundbreaking work.

The PSICHIC team has made their data, code, and optimised model available to the broader scientific community. Visit for more information.


Support Śindependent community journalism. Support The Indian Sun.


Follow The Indian Sun on X | InstagramFacebook

 

Donate To The Indian Sun

Dear Reader,

The Indian Sun is an independent organisation committed to community journalism. We have, through the years, been able to reach a wide audience especially with the growth of social media, where we also have a strong presence. With platforms such as YouTube videos, we have been able to engage in different forms of storytelling. However, the past few years, like many media organisations around the world, it has not been an easy path. We have a greater challenge. We believe community journalism is very important for a multicultural country like Australia. We’re not able to do everything, but we aim for some of the most interesting stories and journalism of quality. We call upon readers like you to support us and make any contribution. Do make a DONATION NOW so we can continue with the volume and quality journalism that we are able to practice.

Thank you for your support.

Best wishes,
Team The Indian Sun

Comments