Healx scientists develops new ways of predicting disease relationships

Healx scientists develops new ways of predicting disease relationships

Healx scientists, in a study led by Erin Oerton, have evaluated different types of biological information for their value of relating diseases to each in other, in a publication that has just appeared in the journal Bioinformatics.

The study took six different types of data sets into account, namely ontological, phenotypic,
literature co-occurrence, genetic association, gene expression, and drug indication data, in order to
create a ‘Disease Map’ of 84 diseases. The constructed map was able to re-create already
established relationship between diseases, as well as to identify novel links between them. Many of
the novel links could be corroborated by clinical evidence, such as shared drugs that can be used to
treat related diseases. Learnings from the study will be implemented for future use in Healnet,
Healx’ unique AI-driven drug discovery platform for rare diseases.

Figure 3 in the article: Diseases related to psoriasis. As well as known links to other skin diseases (light blue nodes), psoriasis has links to a number of phenotypically distinct diseases with an autoimmune component, such as alopecia, arthritis, and lupus, as well as inflammatory bowel diseases (turquoise nodes) with which it shares genetic features related to drugs that can be used to treat both conditions. There is a high degree of interconnection amongst this group of diseases, which form one of the most densely connected areas in the network.


Co-authors of the study, beyond Erin Oerton, who is also a PhD student at the Centre for Molecular
Informatics at the University of Cambridge, are the Healx scientists Ian Roberts, Patrick Lewis and
Tim Guilliams, and Andreas Bender, Erin’s PhD supervisor and a PI at the Centre for Molecular


Similar Posts