University of Cambridge uses AI in drug design process for Parkinson

To expedite the drug-making process for Parkinson's disease, the researchers of Cambridge University have used AI and machine learning which resulted in a ten-fold initial screening process and a reduction of cost by a thousandfold.

The University of Cambridge used the latest technologies of AI and machine learning to find compounds that block the clumping, or aggregation, of alpha-synuclein, the protein that characterises Parkinson’s. The researchers have designed and used an AI-based strategy for this process.

Parkinson’s affects more than six million people worldwide, and it is expected to triple by 2040. In Parkinson's patients, the proteins responsible for important cell processes go rogue and cause the death of nerve cells. The proteins misfold and form abnormal clusters called Lewy bodies within brain cells which results in stopping the brain from functioning properly.

“One route to search for potential treatments for Parkinson’s requires the identification of small molecules that can inhibit the aggregation of alpha-synuclein, which is a protein closely associated with the disease. But this is an extremely time-consuming process – just identifying a lead candidate for further testing can take months or even years," said Professor Michele Vendruscolo from the Yusuf Hamied Department of Chemistry, who led the research.

The research is being conducted in the Chemistry of Health Laboratory in Cambridge. The laboratory was founded with the support of the UK Research Partnership Investment Fund (UKRPIF) to promote the translation of academic research into clinical programmes.

AI model GPT-4 significantly exceeds assessment of non-specialist eye doctors

As per the researchers of the university, the clinical knowledge and reasoning skills of GPT-4 are approaching the level of specialist eye doctors. The researchers have said that the large language models aren’t expected to replace the eye specialists but can help them to improve healthcare as part of the clinical workflow.

Dr Arun Thirunavukarasu, lead author of the study, which he carried out while a student at the University of Cambridge’s School of Clinical Medicine said, “We could realistically deploy AI in triaging patients with eye issues to decide which cases are emergencies that need to be seen by a specialist immediately, which can be seen by a GP, and which don’t need treatment."

The official statement said that GPT-4 - a ‘large language model’ - was tested against doctors at different stages in their careers. These doctors include trainees, expert eye doctors, and junior doctors. Each of these health professionals was presented with a series of 87 patient scenarios involving a specific eye problem and asked to give a diagnosis or advise on treatment by selecting from four options.

Read more:

• Antisemitism has no place in Columbia University, says President
• University Of Houston, Heriot-Watt University announce strategic alliance; Details Here