Regensburg Lectures in Medical Bioinformatics
“Machine Learning in HIV Diagnostics”
Prof. Dr. Dominik Heider
Bioinformatics
Straubing Center of Science
Introduction
The human immunodeficiency virus (HIV) is one of the major human diseases leading to about 2 million deaths yearly. Although antiretroviral treatment is working well in principle, the high mutation rate of HIV frequently leads to a fast adaptation of the virus and thus to the development of drug-resistant viral strains. Computational models for drug resistance prediction based on genotypic information of the viruses have entered clinical practice. These models have been developed based on virus isolates with known resistance profiles and machine learning techniques. Especially with the use of the next-generation sequencing technologies, these computational models outperform traditional resistance testing in the labs, thus enabling a personalized therapy.
References
Heider D., Senge R., Cheng W., Hüllermeier E.: Multilabel classification for exploiting cross-resistance information in HIV-1 drug resistance prediction, Bioinformatics 2013, 29(16):1946-1952.
Heider D., Verheyen J., Hoffmann D.: Predicting Bevirimat resistance of HIV-1 from genotype, BMC Bioinformatics 2010, 11:37
Dybowski J. N., Heider D., Hoffmann D.: Prediction of co-receptor usage of HIV-1 from genotype, PLoS Comp Biol 2010, 6(4): e1000743.
Dybowski J. N., Heider D., Hoffmann D.: Structure of HIV-1 quasi-species as early indicator for switches of co-receptor tropism, AIDS Research and Therapy 2010, 7:41
Tuesday, 17.06.2014, 4 p.m.
in H42 Biologie
Host: Prof. Dr. Rainer Spang