October 28, 2013
In what's being heralded as a breakthrough in bioinformatics research, European researchers have developed a new software suite, called eXtasy, that automatically generates the most likely cause of a given genetic disorder. A team of scientists from iMinds, STADIUS, and Katholieke Universiteit Leuven (KU Leuven) built the new tool using advanced artificial intelligence techniques that enable the automated analysis of huge amounts of genetic data.
The research is directly relevant to the millions of people who are affected by a hereditary disease, roughly 5 percent of the world's population. Pinpointing treatments for hereditary disorders has been difficult because until recently the genetic basis for the disease origins could only be identified in half the presented cases. The lack of a definitive diagnosis made treatment more problematic and created further strain on the patient who had to undergo unnecessary treatments in an effort to find the most effective one.
The unraveling of the human genome has led to quicker and more accurate diagnoses of hereditary diseases. But despite the enormous benefits, the advance came with its own challenges, related to processing all that data.
"The genomes of two healthy individuals show no less than four million differences or mutations," notes an official release from the partners. "Most of these mutations are harmless, but just one extra, malignant mutation can be enough to cause a genetic anomaly. Existing analytical methods simply do not have the means to reliably and quickly find this needle in the haystack."
The eXtasy software suite cuts this problem down to size by tracing the origins of genetic disorders twenty times more accurately than previous analytical methods, while demonstrating a 10-fold reduction of false positives.
"eXtasy uses advanced artificial intelligence to combine whole sets of complex data into a global score that reflects how important a certain mutation is for a certain disease. This data can consist of networks of interacting proteins, but could also include scientific publications or even scores that estimate how harmful a mutation is for the protein in question," explains Prof. Dr. Yves Moreau of iMinds - STADIUS - KU Leuven. "In this way, we can detect disease-causing mutations twenty times more accurately, and provide patients and their families with a much faster and more conclusive diagnosis. We hope this can considerably improve and accelerate the treatment of millions of patients."
The breakthrough is part of the emerging era of personalized medicine. As Dr. Yves Moreau Accurate attests, accurate diagnoses are essential for customized treatments. Dr. Moreau will be speaking more about this important topic at TEDx Brussels (on October 28) as part of a talk entitled "Mining a Million Genomes."
iMinds is an independent research group, founded by the Flemish government, that works with a number of public and private institutions – including KU Leuven in Flanders, Belgium – to stimulate digital innovation. ESAT-STADIUS (the Department of Electrical Engineering - STADIUS Center of Dynamical Systems, Signal Processing and Data Analytics) is a division within iMinds that focuses on such domains as industrial automation, digital communications, the processing of biomedical signals and bioinformatics.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?