A geometric deep-learning model is faster and more accurate than state-of-the-art computational models, reducing the chances and costs of drug trial failures.
Many approved drugs work on the body in ways that researchers still aren’t entirely clear about. Seeing this as an opportunity instead of a flaw may lead to better treatments for complex conditions.
While technological advancements have quickened the drug discovery process, some chemical compounds remain a common thorn in a researcher’s side.
Semarion Ltd, a University of Cambridge spin-out company from the Cavendish Laboratory, combines materials engineering and cell biology to help biopharma
Researchers have developed a new approach to machine learning that ‘learns how to learn’ and out-performs current machine learning methods for drug design,
Regulatory loopholes for research conducted off US soil allow for questionable trials and misleading data to slip under the FDA’s radar.
If no action is taken to address antibiotic resistance, infections from multidrug-resistant bacteria could cause 10 million deaths each year by 2050.
Machine learning is great at finding patterns but doesn’t know what those patterns mean. Combine it with knowledge gained from genetic research and you have a powerful view into the workings of cells.
/
7
