The team under Professor Tom Lenaerts (VUB-ULB) of the IB² has developed an AI algorithm that makes it possible to identify combinations of genetic variants or abnormalities that cause rare diseases through computer analysis. The algorithm was developed with Prof. dr. Guillaume Smits (Center for Human Genetics of the ULB, the Erasmus Hospital and the University Children's Hospital Queen Fabiola) and was designed and built in collaboration with Yves Moreau and Jan Aerts (KU Leuven), Sonia Van Dooren (UZ Brussel) and Ann Nowé (Vrije Universiteit Brussel). The method has been named VarCoPP (Variant Combinations Pathogenicity Predictor).
Almost 80% of rare diseases are genetically determined. It is therefore important for doctors to be able to predict which genetic variants in the patient's genome may be the cause of the disease. Predicting the cause of the error is not easy but predicting whether a combination of errors in different genes has the potential to cause a rare disease is even more difficult. However, this is necessary for the better diagnoses of genetic diseases since, in many cases, only a fraction of patients can be helped.
The VarCoPP algorithm offers precisely that innovative approach: it makes it possible to simultaneously test the combinations of different variants in gene pairs and to predict their potential pathogenicity. The AI that underlies VarCoPP is driven by the database of rare diseases called DIDA (dida.ibsquare.be), which was developed by the same researchers in 2015. The researchers successfully tested the effectiveness and reliability of the algorithm on 23 independent pathogenic gene combinations, and deliver confidence intervals of 95% and 99% to help doctors zoom in on the most important predictions. The team is now attempting to use these results to identify the genetic causes of rare diseases in patients for whom no cause could previously be identified. The team introduces at the same time a new online diagnostic platform for researchers and clinicians, based on the algorithm. The platform is called ‘ORVAL’ and is described in a publication in the journal Nucleic Acids Research (NAR).
ORVAL and VarCoPP provide a novel approach to study variant combinations for rare diseases for which causal genes are known or unknown, such as for example the hundreds of autism or epilepsy genes or the 20 genes of the rare Bardet-Biedl syndrome (a genetic disorder which presents blindness, obesity and motor disorders amongst others) where different combinations of genetic variations are likely to be the cause.
This research was conducted as part of the ARC project 'Deciphering Oligo- and Polygenic Genetic Architecture in Brain Developmental Disorders', funded by the Wallonia-Brussels Federation, and the BRIGHTanalysis project, funded by the European Regional Development Fund (ERDF) and the Brussels-Capital Region as part of the 2014-2020 operational program through the F11-08 project ICITY-RDI.BRU (icity.brussels) - a joint initiative of ULB, VUB and SIRRIS. Prof. Guillaume Smits's research is supported by the Belgian Kids Fund of the Iris-Recherche Fund and the Erasmus Fund. Sofia Papadimitriou is supported by a FRIA grant.
The ERDF (European Regional Development Fund) is a European regional policy tool that aims to create new opportunities for European citizens and to reduce the living standards gap between regions. Between 2007 and 2013, the ERDF programme, through the intervention of the Region and Europe, thus invested 108 million euros in 32 projects in the Brussels Capital Region. These projects concern child care, re-employment measures, training programmes, but also sustainable development, support for economic activities, and reinforcing the infrastructure and the social cohesion in the canal area. The current programme (2014-2020) contains 46 projects pertaining to access to employment, research, circular economy, innovation and improving the living environment. Europe and the Region are investing €200 million in this new programme.
For more information, please contact:
T 0032 (0)2 650 60 04
M 0032 (0)486 93 19 96
T 0032 (0)2 555 64 39
T 0032 (0)2 555 82 97
‘Predicting disease-causing variant combinations’,
Sofia Papadimitriou1,2,3, Andrea Gazzo1,2,4, Nassim Versbraegen1,2, Charlotte Nachtegael1,2, Jan Aerts5,6, Yves Moreau5,7, Sonia Van Dooren1,4,8, Ann Nowé1,3, Guillaume Smits1,9,10,* and Tom Lenaerts1,2,3,*
Published in Proceedings of the National Academy of Sciences (PNAS) on 24 May 2019.
'ORVAL: a novel platform for the prediction and exploration of disease-causing oligogenic variant combinations',
Alexandre Renaux1,2,3, Sofia Papadimitriou1,2,3, Nassim Versbraegen1,2, Charlotte Nachtegael1,2, Simon Boutry1,11, Ann Nowé1,3, Guillaume Smits1,9,10, Tom Lenaerts1,2,3,*
Published in Nucleid Acids Research on 31 May 2019.
1Interuniversity Institute of Bioinformatics in Brussels, Université libre de Bruxelles-Vrije Universiteit Brussel, 1050 Brussels, Belgium
2Machine Learning Group, Université libre de Bruxelles, 1050 Brussels, Belgium
3Artificial Intelligence lab, Vrije Universiteit Brussel, 1050 Brussels, Belgium
4Center for Medical Genetics, Reproduction and Genetics, Reproduction Genetics and Regenerative Medicine, Vrije Universiteit Brussel, UZ Brussel, 1090 Brussels, Belgium
5Center for Statistics, Universiteit Hasselt, 3590 Diepenbeek, Belgium
6Department of Electrical Engineering, STADIUS Centre for Dynamical Systems, Signal Processing and Data Analytics, Katholieke Universiteit Leuven, 3001 Leuven, Belgium
7IMEC, 3001 Leuven, Belgium
8Brussels Interuniversity Genomics High Throughput core, Université libre de Bruxelles-Vrije Universiteit Brussel, 1090 Brussels, Belgium
9Hôpital Universitaire des Enfants Reine Fabiola, Université Libre de Bruxelles, 1020 Brussels, Belgium
10Center of Human Genetics, Hôpital Erasme, Université Libre de Bruxelles, 1070 Brussels, Belgium
11Laboratory of Human Molecular Genetics, de Duve Institute, UCLouvain, 1200 Brussels, Belgium