{"id":660252,"date":"2025-04-02T23:35:14","date_gmt":"2025-04-02T20:35:14","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/ai-model-predicts-drug-properties-to-speed-up-development\/"},"modified":"2025-04-02T23:35:14","modified_gmt":"2025-04-02T20:35:14","slug":"ai-model-predicts-drug-properties-to-speed-up-development","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/ai-model-predicts-drug-properties-to-speed-up-development\/","title":{"rendered":"AI model predicts drug properties to speed up development"},"content":{"rendered":"
\n
\n
\n
\n \"Accelerating
\n The image from the study shows a correlation between pairs of pharmacokinetic (PK) properties for a single drug. Each drug has its unique chemical profile and set of PK property values. The goal of the diagram is to show the distribution similarity between the real reported pairs of PK properties correlation from in vitro studies and those generated by the researchers’ model. Credit: arXiv<\/i> (2024). DOI: 10.48550\/arxiv.2408.07636
\n <\/figcaption><\/figure>\n<\/p><\/div>\n<\/div>\n

Developing new drugs to treat illnesses has typically been a slow and expensive process. However, a team of researchers at the University of Waterloo uses machine learning to speed up the development time.<\/p>\n

The Waterloo research team has created Imagand, a generative artificial intelligence model that assesses existing information about potential drugs and then suggests their potential properties. Trained on and tested against existing drug data, Imagand successfully predicts important properties of different drugs that have already been independently verified in lab studies, demonstrating the AI’s accuracy.<\/p>\n

The research<\/a>, titled “Drug discovery SMILES-to-pharmacokinetics diffusion models with deep molecular understanding,” is currently available on the arXiv<\/i> preprint server.<\/p>\n

Traditionally, bringing a successful drug candidate to market can cost between US$2 billion and US$3 billion and take over a decade to complete. Generative AI is poised to transform drug discovery by harnessing large amounts of drug data across diverse areas.<\/p>\n

“There’s an enormous pool of possible chemicals and proteins to investigate when developing a new drug, which makes it very expensive to do drug discovery because you have to test millions of molecules with thousands of different targets,” said Bing Hu, a Ph.D. candidate in Computer Science<\/a> and the lead author on the research. “We are figuring out ways that AI can make that faster and cheaper.”<\/p>\n

One of the major challenges in pharmaceutical medicine development is understanding not only how a drug might affect the body in isolation but also how it might interact with other drugs or a person’s lifestyle. This information is particularly difficult to gather because scientific studies of drugs usually only focus on the drugs’ predetermined properties, not on how they may interact with other drugs.<\/p>\n

Ultimately, the team hopes medical researchers can use Imagand in the future to understand how drugs interact, allowing them to eliminate potential new drug candidates that would have bad side effects or interactions.<\/p>\n

“For example, this AI-enabled process can help us understand how toxic a drug is, how it affects the heart, or how it might interact negatively with other drugs commonly used in treating an illness,” said Helen Chen, a professor in the School of Public Health Science and Computer Science at Waterloo. “This is one example of how AI is helping us move towards more precise, personalized care.”<\/p>\n

\n

More information:<\/strong>
\n\t\t\t\t\t\t\t\t\t\t\t\tBing Hu et al, Drug Discovery SMILES-to-Pharmacokinetics Diffusion Models with Deep Molecular Understanding, arXiv<\/i> (2024). DOI: 10.48550\/arxiv.2408.07636<\/a><\/p>\n

\n

\n\t\t\t\t\t\t\t\t\t\t\t\t\tJournal information:<\/strong>
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tarXiv<\/cite>
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/svg>
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/p>\n<\/p><\/div>\n<\/p><\/div>\n

\n

\n\t\t\t\t\t\t\t\t\t\t\t\t\tProvided by
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tUniversity of Waterloo
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/svg>
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/p>\n<\/p><\/div>\n

\t\t\t\t\t\t\t\t\t\t<\/p>\n

\n

\n\t\t\t\t\t\t\t\t\t\t\t\tCitation<\/strong>:
\n\t\t\t\t\t\t\t\t\t\t\t\tAI model predicts drug properties to speed up development (2025, April 2)
\n\t\t\t\t\t\t\t\t\t\t\t\tretrieved 2 April 2025
\n\t\t\t\t\t\t\t\t\t\t\t\tfrom https:\/\/phys.org\/news<\/a>\/2025-04-ai-drug-properties.html\n\t\t\t\t\t\t\t\t\t\t\t <\/p>\n

\n\t\t\t\t\t\t\t\t\t\t\t This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
\n\t\t\t\t\t\t\t\t\t\t\t part may be reproduced without the written permission. The content is provided for information purposes only.\n\t\t\t\t\t\t\t\t\t\t\t <\/p>\n<\/p><\/div>\n<\/p><\/div>\n