Posted in | News | Machine-Vision

New Citizen Science Project Seeks to Train Artificial Intelligence to Identify Virus Particles

Diamond Light Source—the UK’s national synchrotron science facility—has recently launched a new Citizen Science Project.

Professor Dave Stuart FRS from Diamond Light Source examines a model of a virus structure (Image credit: Diamond Light Source Ltd)

In this project, a crowdsourcing model has been used to implore people of all ages across the globe to help in expediting the analysis of the terabytes of data that are produced by Diamond Light Source on a daily basis. For citizen researchers, the initial task is to devote some time to look at an array of screens to detect viruses. Over the next three years, additional tasks will also be set for other targets. This will help in training artificial intelligence systems (AI) and, at the same time, will aid in developing innovative methods for separating data, with the goal to automate the processes of data segmentation. This approach will considerably expedite the ability of researchers to interpret their research data in just a matter of days instead of many weeks that are currently involved, thus providing a faster way to figure out disease structures, and possibly accelerate the development of new drugs.

The Diamond “Science Scribbler–Virus Project”—launched at the American Association for the Advancement of Science in Washington DC—is the first-of-its-kind project in which public members can help with in such a major way. The Wellcome Trust, the world’s biggest biomedical charity, has funded the project, which is being developed in association with Zooniverse, the leading citizen science web platform.

The ultimate goal is to completely automate segmentation using advances in deep learning. Such methods require significant quantities of already segmented data to train the systems we use. To build segmented data for this development, Zooniverse will offer members of the public across the globe the chance to partake in segmenting datasets to help researchers. This project aims to address these issues by providing tools to help researchers label features of interest, and to gather the data that is produced by citizen scientists in a standardised way that can be used to automate the process in the future, thereby helping fasten the analysis process from weeks to days or less.

Dave Stuart FRS, MRC Professor, Division of Structural Biology, University of Oxford

Stuart is also the Life Sciences Director at Diamond Light Source.

Every month, Diamond generates 500 terabytes of biological data, from low-resolution data to high-resolution comprehensive atomic maps, which make the existing methods of data segmentation rather difficult. Data are usually blurred and low contrast, and can be large in such a way that they become extremely labor-intensive to examine.

What we are doing now is to use cryo-electron tomography to visualise virus particles from the reovirus family in very thin slices cut from frozen infected cells. Our aim is, ultimately, to understand the full life cycle, how the virus gets into the cell, replicates, assembles and finally leaves the cell. In the tomograms here we have taken a snapshot 12 hours after infection and are aiming to visualise intermediate steps in the assembly process which have not been visible before, and to then work out how virus assembly is organised in time and space within the cell.

Dave Stuart FRS, MRC Professor, Division of Structural Biology, University of Oxford

Part of a large family of viruses, reoviruses infect many different plants and animals. Certain members of the virus family promote widespread disease, particularly Rotaviruses, which causes serious gastroenteritis worldwide. On the contrary, while reoviruses are known to persistently infect humans, they do not usually produce symptoms. These viruses are definitely being trialed as potential anti-cancer agents, as they particularly replicate in a number of tumor cells triggered for division. Hence, they offer a good starting point to attempt to figure out the life-cycle of this type of viruses.

We simply need as many people as possible to view images and locate what they recognise to be virus particles. This is based on real data and exciting work already underway at Diamond looking at the reovirus. This is screen time we can all advocate and we are not making too great a claim when we say it could benefit all of mankind in terms of accelerating scientists’ analysis of their research.

Mark Basham, Project Coordinator, Diamond Light Source

You don’t need any specialised background, training, or expertise to participate in any of the Zooniverse projects. We make it easy for anyone interested to contribute to real academic research, on their own computer or through a mobile Application, at their own convenience. We hope The Diamond ‘Science Scribbler–Virus Project’ will entice you to become a regular volunteer.

Chris Lintott, Professor and Zooniverse PI, University of Oxford

Artificial Intelligence has begun to have a massive impact on the world in the last few years, from beating humans in games such as Go, to the amazing advances in self-driving cars. These dramatic developments have been aided by the availability of vast quantities of data with which AI systems can be trained with. Alongside these developments, 3D imaging of frozen cells, for example, has also developed rapidly, but as yet, very little training data is available. Researchers spend much of their time manually processing their data and this is an area where AI could be heavily used. However, for, machine learning to be possible, we need human input to guide the process and this is where members of the public can make a huge difference to our work.

Dr Mark Basham, Project Coordinator, Diamond Light Source

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.