New Computational Approach to Predicting Adverse Drug Reactions with Higher Confidence

A new integrated computational method helps predicting adverse drug reaction - which are often lethal - more reliably than with traditional computing methods. This improved ability to foresee the possible adverse effects of drugs may entail saving many lives in the future. The study that is being conducted by researchers from IMIM (Hospital del Mar Medical Research Institute), Pompeu Fabra University, and the company Chemotargets, within the framework of the European eTOX project, was chosen for the cover of the journal Chemical Research in Toxicology.

Most computer tools employed today to detect possible adverse effects of compounds that are candidates for new medicines are based on detecting labile fragments in the drug's structure. These fragments can potentially transform to form reactive metabolites, which can have toxic properties. This is what is known as idiosyncratic toxicity and is a big headache for the pharmaceutical industry, as it tends to be detected in late development stages of the drug and even when it is already on the market, often causing the drug to be withdrawn.

Jordi Mestres, coordinator of the IMIM and UPF research group on Systems Pharmacology at the Biomedical Informatics Program (GRIB) states "With this study we have contributed to complementing the detection of these quite unstable fragments, with information on the mechanism of action of the drug, based on three aspects: similarity to other medicines, prediction of their pharmacological profile, and interference with specific biological pathways. The optimal integration of these four aspects results in a clear improvement of our ability to anticipate adverse effects with higher confidence, which entails an extremely positive impact on society."

In Europe, nearly 200,000 people die every year from adverse drug reactions, seven times more than in traffic accidents. An estimated 5% of hospitalisations are due to adverse effects and they are the fifth most common cause of hospital death. In addition, elderly people tend to take more than one drug at the same time, which multiplies the chances of suffering from adverse effects due to potential drug-drug interactions. In an increasingly ageing society, this problem is becoming much more serious.

The human and financial costs of adverse effects are very high. That is why the discovery of new medicines is increasingly focused more on predicting possible adverse effects at the initial stages of developing a new drug. This work hopes to contribute to setting the path toward a new generation of more reliable computational tools with regard to predicting the adverse effects of therapeutically-relevant small molecules. Advancing large-scale predictive safety at the pre-clinical phase is now becoming closer than ever, with expectations to lead to safer drugs for the entire population.

Large-Scale Predictive Drug Safety: from Structural Alerts to Biological Mechanisms. Ricard Garcia-Serna, David Vidal, Nikita Remez, and Jordi Mestres. Chemical Research in Toxicology 28 (2015) 1875. http://pubs.acs.org/doi/abs/10.1021/acs.chemrestox.5b00260

Most Popular Now

Philips Foundation 2024 Annual Report: E…

Marking its tenth anniversary, Philips Foundation released its 2024 Annual Report, highlighting a year in which the Philips Foundation helped provide access to quality healthcare for 46.5 million people around...

Giving Doctors an AI-Powered Head Start …

Detection of melanoma and a range of other skin diseases will be faster and more accurate with a new artificial intelligence (AI) powered tool that analyses multiple imaging types simultaneously...

Scientists Argue for More FDA Oversight …

An agile, transparent, and ethics-driven oversight system is needed for the U.S. Food and Drug Administration (FDA) to balance innovation with patient safety when it comes to artificial intelligence-driven medical...

New AI Transforms Radiology with Speed, …

A first-of-its-kind generative AI system, developed in-house at Northwestern Medicine, is revolutionizing radiology - boosting productivity, identifying life-threatening conditions in milliseconds and offering a breakthrough solution to the global radiologist...

AI Agents for Oncology

Clinical decision-making in oncology is challenging and requires the analysis of various data types - from medical imaging and genetic information to patient records and treatment guidelines. To effectively support...

New Research Finds Specific Learning Str…

If data used to train artificial intelligence models for medical applications, such as hospitals across the Greater Toronto Area, differs from the real-world data, it could lead to patient harm...

Start-ups in the Spotlight at MEDICA 202…

17 - 20 November 2025, Düsseldorf, Germany. MEDICA, the leading international trade fair and platform for healthcare innovations, will once again confirm its position as the world's number one hotspot for...

AI Detects Hidden Heart Disease Using Ex…

Mass General Brigham researchers have developed a new AI tool in collaboration with the United States Department of Veterans Affairs (VA) to probe through previously collected CT scans and identify...

AI Medical Receptionist Modernizing Doct…

A virtual medical receptionist named "Cassie," developed through research at Texas A&M University, is transforming the way patients interact with health care providers. Cassie is a digital-human assistant created by Humanate...

AI Tool Set to Transform Characterisatio…

A multinational team of researchers, co-led by the Garvan Institute of Medical Research, has developed and tested a new AI tool to better characterise the diversity of individual cells within...

MHP-Net: A Revolutionary AI Model for Ac…

Liver cancer is the sixth most common cancer globally and a leading cause of cancer-related deaths. Accurate segmentation of liver tumors is a crucial step for the management of the...

Human-AI Collectives Make the Most Accur…

Diagnostic errors are among the most serious problems in everyday medical practice. AI systems - especially large language models (LLMs) like ChatGPT-4, Gemini, or Claude 3 - offer new ways...