Imperial College London

Jupiter mission and AI acceleration: News from the College

by , ,

An illustration of the JUICE spacecraft in orbit around Jupiter

An illustration of the JUICE spacecraft in orbit around Jupiter

Here’s a batch of fresh news and announcements from across Imperial.

From an Imperial-designed magnetometer for listening to Jupiter’s icy moons, to a new method for accelerating drug discovery with AI, here is some quick-read news from across the College.

Getting ready for Jupiter

The JUICE magnetometer
The ‘qualification model’ of the magnetometer

The Department of Physics staff have delivered to Airbus and the European Space Agency a near-final model of an instrument for the JUpiter ICy moons Explorer (JUICE), which is due to launch in mid-2022.

Imperial’s magnetometer instrument will measure the magnetic environment the spacecraft encounters, particularly the magnetic field of the moon Ganymede. Beneath its thick icy crust, Ganymede is suspected to have an ocean, which the magnetometer can help to characterise.

Despite lockdown challenges, the Imperial team this week delivered the ‘qualification model’ (QM) of the magnetometer, which will go through rigorous testing on board the spacecraft as it goes through thermal and vacuum tests to ensure it will survive the journey and orbit at Jupiter.

The team are now preparing the final ‘flight model’, which will be delivered in January 2021 and will replace the QM instrument on the spacecraft. 

Read more about Imperial’s involvement in the JUICE mission.

Leader in management thinking 

Professor George Yip
Professor George Yip

Professor George Yip, Emeritus Professor of Marketing and Strategy at the Business School, has been inducted into the Thinkers50 Hall of Fame – a body which recognises the achievements of distinguished thinkers from the world of management.

His research looks at how companies need to develop more globally integrated strategies to be successful. Professor Yip’s work also addresses how China is moving from imitation to innovation and what Western companies can learn from this phenomenon.

The mission of the Thinkers50 is to identify, rank and share the best management ideas and acknowledge experts who have made valuable contributions to management thinking. 

Accelerating drug discovery with AI

An illustration of parasite data as analysed by the machine learning algorithmMany human infections are becoming increasingly resistant to antimicrobial drugs, so new drugs are needed that work in new ways. However, potential new drugs are often tested in simple cell-based screens that only reveal whether the infection is killed or not, and not how the drug works.

Machine learning methods that examine images of the screening are increasingly being used, but they are not very effective when cells vary greatly and often require time-consuming training by humans that teach the algorithm what it is looking at.

Now, researchers from Imperial and Google Research have developed an algorithm that requires less human input. They tested it with human malaria parasites, finding that it reliably sorted images into parasite life stages and grouped potential drugs by their mechanism of action.

Read the full paper in Science Advances: A machine learning approach to define antimalarial drug action from heterogeneous cell-based screens 

– 

Want to be kept up to date on news at Imperial?

Sign up for our free quick-read daily e-newsletter, Imperial Today

Imperial Today on an iPad

Reporters

Andrew Youngson

Andrew Youngson
Communications and Public Affairs

Hayley Dunning

Hayley Dunning
Communications and Public Affairs

Click to expand or contract

Contact details

Tel: +44 (0)20 7594 2412
Email: h.dunning@imperial.ac.uk

Show all stories by this author

Laura Singleton

Laura Singleton
Communications and Public Affairs

Tags:

News-in-brief, Artificial-intelligence, Space
See more tags

Leave a comment

Your comment may be published, displaying your name as you provide it, unless you request otherwise. Your contact details will never be published.