DGLinker: flexible knowledge-graph prediction of disease–gene associations

Abstract

As a result of the advent of high-throughput technologies, there has been rapid progress in our understanding of the genetics underlying biological processes. However, despite such advances, the genetic landscape of human diseases has only marginally been disclosed. Exploiting the present availability of large amounts of biological and phenotypic data, we can use our current understanding of disease genetics to train machine learning models to predict novel genetic factors associated with the disease. To this end, we developed DGLinker, a webserver for the prediction of novel candidate genes for human diseases given a set of known disease genes. DGLinker has a user-friendly interface that allows non-expert users to exploit biomedical information from a wide range of biological and phenotypic databases, and/or to upload their own data, to generate a knowledge-graph and use machine learning to predict new disease-associated genes. The webserver includes tools to explore and interpret the results and generates publication-ready figures. DGLinker is available at https://dglinker.rosalind.kcl.ac.uk. The webserver is free and open to all users without the need for registration.

Artificial Intelligence, Healthcare, Clinical Genomics, and Pharmacogenomics Approaches in Precision Medicine

“…By doing so, the gene–disease relationship can improve precision while detecting abnormalities in patients. They can also predict patient susceptibility to a particular disease and open the possibility of treatment options of rare diseases ( Strande et al, 2017 ; Hu et al, 2021 ; Megías-Vericat et al, 2021 ). The study of this association can also help elucidate gene function ( Van Dam et al, 2018 ), estimate the prevalence of genes in populations ( Zhou and Skolnick, 2016 ), differentiate among subtypes of diseases ( Nakatsuka et al, 2017 ) and trace how genes may predispose to ( Sørlie et al, 2003 ) or protect against illnesses ( Pirmohamed, 2006 ), and improve medical intervention ( Ahmed et al, 2020b ; Wickenhagen et al, 2021 ).…”

The potential of a data centred approach & knowledge graph data representation in chemical safety and drug design

“…Data integration and the application of KGs can provide a feasible computational infrastructure for large scale drug repositioning candidate detection [16] , [17] , [18] . Such KG based frameworks have gained a lot of attention recently in their possible application for new occurring diseases where a rapid response is required, such as COVID - 19 [16] , [20] , [125] , drug target prediction applications [116] as well as closing the genotype-phenotype gap [126] .…”

GenePlexus: a web-server for gene discovery using network-based machine learning

“…Web-servers such as GeneMania ( 12 ), HumanNet ( 28 ), ToppGene ( 29 ) and MaxLink ( 30 ) provide predictions using the method of label propagation, a semi-supervised method which our model has been shown to outperform ( 22 ). DGLinker ( 31 ) is a powerful and comprehensive web-server that trains a supervised machine learning model on the user-supplied gene set. However, the supervised learning model in DGLinker uses three features that are mined from a vast amount of data sources.…”