Industrial Maths AI and Health study groups – discovering relationships between phenotypes and variants

Posted on: 11/04/2019

Another in a series of problems for KTN’s Industrial Maths in AI and Health event has been announced, and researchers are encouraged to apply.

This is one of several problems that will be discussed at the three-day study group in Cardiff from 22-24 May.  There is another Health and AI study group looking at different problems in Manchester from 26-28 June.

If you are a researcher working in a UK university who would like to work on this problem, please register here for the Cardiff study group.

The organisers, KTN, alongside the University of Cardiff, are looking for researchers to work on the following conundrum:

Discovering new insight into relationships between phenotypes (health measures) and genomic variants that can inform genomic diagnosis, presented by Congenica

Congenica is the provider of the genomic diagnostic decision support platform, Sapientia, and associated clinical services. Sapientia enables clinicians to interrogate the human genome to identify disease-causing variants.

The UK Biobank project has gathered healthcare data from 500,000 people aged between 40-69 years in 2006-2010 from across the country. They have undergone measures, provided blood, urine and saliva samples for future analysis, detailed information about themselves and agreed to have their health followed. Genotyping has been undertaken on all 500,000 participants.

This data set may contain new insight into relationships between phenotypes (health measures) and genomic variants. Finding relationships between data features could be new information that can inform genomic diagnosis.

The challenge for this study group involves researchers discovering relationships between phenotypes and variants. Understanding clusters of phenotypes or variants could be a useful first step and a useful output in its own right. Congenica is open to the techniques and tools used to explore this data, including supervised and unsupervised techniques. Participants are free to choose what subset of the data they would like to work with; perhaps exploring a specific hypothesis, or taking a more unsupervised approach to revealing relationships in the data.

Sapientia is built to enable the pinpointing of pathogenic genomic variants. Improving the speed and accuracy of variant interpretation is our focus.  This is done by curating a range of scientific information alongside the patient’s sequence. Where new, reliable scientific information is discovered that informs the interpretation process, this may be made available to scientists.


Data access

Congenica will apply for access to the UK Biobank data. Participants will be subject to the terms of access defined by UK Biobank. Results and code may need to be returned to UK Biobank (to be confirmed).


Background information

Rare Disease UK


About Congenica

Congenica specialises in rare disease. 80% of rare diseases are thought to have a genetic component, and patients wait an average of 4.7 years, and typically see 7.4 different clinical specialists, before getting a diagnosis. Sapientia enables clinicians to progress through workflows more quickly, optimising throughput of patients, number of patients diagnosed and reducing costs. Headquartered in Cambridge, UK, and operating in Europe, the US and China, Congenica is born out of pioneering research from the Wellcome Trust Sanger Institute and the NHS. Congenica is a partner for the pivotal Genomics England 100,000 Genomes Project and the National Genomic Medicine Service.


If you are a researcher working in a UK university who would like to work on this problem at the study group in Cardiff from 22-24 May, please register here.  Early stage career academics, Ph.D students, and postdocs are particularly welcome.

Share this article


Connect with Innovate UK Business Connect

Join Innovate UK Business Connect's mailing list to receive updates on funding opportunities, events and to access Innovate UK Business Connect's deep expertise. Please check your email to confirm your subscription and select your area(s) of interest.