You are here: Home

slider_DPDL

Translate NAMSE

software kick-off meeting

Button

GPI anchor

GPI biosynthesis defects

a rare monogenic disorder

GPIBDs

slider_PEDIA_resized.jpg

PEDIA scoring approach

contact us if you need support

pedia-study

Welcome to the IGSB

We are recruiting!

 

Welcome to the Institute for Genomic Statistics and Bioinformatics. We are convinced that precision medicine can only be achieved when human and artificial intelligence join efforts. That's why we are currently building up a strong research team. Please have a look at some of our ongoing projects and our open positions!

Apr 10, 2018

NGP for IEM

Significant improvements in automated image analysis have been achieved in recent years and tools are now increasingly being used in computer-assisted syndromology. However, the ability to recognize a syndromic facial gestalt might depend on the syndrome and may also be confounded by severity of phenotype, size of available training sets, ethnicity, age, and sex. Therefore, benchmarking and comparing the performance of deep-learned classification processes is inherently difficult. For a systematic analysis of these influencing factors we chose the lysosomal storage diseases mucolipidosis as well as mucopolysaccharidosis type I and II that are known for their wide and overlapping phenotypic spectra. For a dysmorphic comparison we used Smith-Lemli-Opitz syndrome as another inborn error of metabolism and Nicolaides-Baraitser syndrome as another disorder that is also characterized by coarse facies. A classifier that was trained on these five cohorts, comprising 289 patients in total, achieved a mean accuracy of 62%. We also developed a simulation framework to analyze the effect of potential confounders, such as cohort size, age, sex, or ethnic background on the distinguishability of phenotypes. We found that the true positive rate increases for all analyzed disorders for growing cohorts (n = [10...40]) while ethnicity and sex have no significant influence. The dynamics of the accuracies strongly suggest that the maximum distinguishability is a phenotype-specific value, which has not been reached yet for any of the studied disorders. This should also be a motivation to further intensify data sharing efforts, as computer-assisted syndrome classification can still be improved by enlarging the available training sets.

Sep 25, 2017

IGSB, IHG, and FDNA team up in Diagnostics for Rare Genetic Disorders

The Institute for Genome Statistics and Bioinformatics, IGSB, and the Institute of Human Genetics, IHG, Bonn, announce a new initiative to further precision medicine through integration with FDNA’s (www.FDNA.com) Face2Gene suite of applications. This integration is expected to dramatically increase and transform the diagnostic power of genetic testing in rare diseases, and is the first of its kind in Germany. In most instances, genetic testing of rare disease patients yields a diagnosis in only 25% of cases. This collaboration will augment genetic testing with facial analysis and artificial intelligence technologies that is expected to increase the diagnostic yield of molecular testing for thousands of rare diseases.

Oct 01, 2018

Typical mutations in children of radar soldiers

A higher occurence of gene mutations can be found in offspring of radar soldiers, who where exposed to high dosages of X-radiation during their service, than in families who weren't exposed. This was shown by a research team from the Charité-Universitätsmedizin Berlin, the Berlin Institute of Health (BIH), the Max-Delbrück-Centrums for Molecular Medicine, the Radboud University Nijmegen (Netherlands) and the Universitätsklinikum Bonn in a pilot study, which is now published in the journal "Scientific Reports". The results of this pilot study are to be verified by a larg-scale study. Radarsoldiers who, until 1985, where tasked with the maintenance of radar equipment and their families can participate.

Jan 08, 2018

Computer assisted facial analysis improves diagnosis

For rare diseases the computer assisted analysis of patient's portraits can simplify and significantly improve the diagnosis. This is proven by an international team of scientists, led by the Universitätsklinikum Bonn and the Charité Universitätsmedizin Berlin, via the so called GPI-biosynthesis deficiency. The scientists used methods of artificial intelligence to simulate models of the disease from genome data, surface texture of cells and typical facial features. The results are potentially groundbreaking for other diseases and will be published in the journal "Genome Medicine".

Aug 12, 2017

New network of excellence for handling rare disease cases is launched

For the future the accomodation of people with unclear diagnoses and rare diseases shall be improved. Therefore a network of university clinics -one of which is the Universitätsklinikum Bonn-, the patient organisation Achse and the statuatory health insurances will implement the 2009 to 2013 wrought national agenda for people with rare diseases ("NAMSE"). „TRANSLATE-NAMSE“ will be funded by ca. 13.4 million Euro from the Innovationfund of the Gemeinsamer Bundesausschuss.

Jan 30, 2019

DeepGestalt

The deep learning technology discussed, in the DeepGestalt paper is a novel facial analysis framework that highlights the facial phenotypes of hundreds of diseases and genetic variations.

Document Actions