New Developments in ImmunExplorer: From NGS Data Over Machine Learning To Health State Prediction

Susanne Schaller, Johannes Weinberger, Sandra Mayr, Thomas Stüttler, Oliver Lemp, Peter Lackner, Stephan Winkler

Research output: Contribution to conferencePoster


Online Sources University of Applied Sciences Upper Austria : Research Group Bioinformatics Hagenberg: Software HeuristicLab: Introduction The human adaptive immune system, represented mainly by the B and T cells and their receptors, plays an essential role in the recognition of potential pathogens such as microorganisms, parasites, and viruses. Knowing the immune repertoire status of individuals is of high importance in basic and medical research, transplantation medicine as well as in diagnosis and treatment of several severe diseases. In the past few years, new high-throughput sequencing technologies emerged, which allow a rapid identification of antibody and T cell receptor gene sequences. Therefore, to properly analyze NGS data in the context of the immune repertoire an immunoinformatics pipeline is required. We present a workflow to profile the immune repertoire of patients and to classify their health states using ImmunExplorer. This pipeline has been used to evaluate a set of patient data by processing NGS data using the newly implemented wrapper for MiXCR to analyze NGS data, performing clonality and diversity analysis, calculating features based on the preceding analyses and predicting the health states using machine learning approaches all integrated in the software IMEX. MiXCR is a software and universal framework for comprehensive adaptive immunity profiling, which means that it enables processing big immunome data from raw sequences to quantitated clonotypes.
Original languageEnglish
Publication statusPublished - 2016
Event15th European Conference on Computational Biology - Den Haag, Netherlands
Duration: 3 Sept 20167 Sept 2016


Conference15th European Conference on Computational Biology
CityDen Haag
Internet address


Dive into the research topics of 'New Developments in ImmunExplorer: From NGS Data Over Machine Learning To Health State Prediction'. Together they form a unique fingerprint.

Cite this