What do we do?
We are interested in modern machine learning techniques suitable for the analysis of problems that arise in medicine and biology. In particular, we develop new learning techniques that are capable of dealing with large amounts of genomic data, allow for very accurate predictions on the phenomenon at hand and are able to comprehensibly provide reasons for their prognoses, and thereby assist in gaining new biomedical insights.
In May 2016, our group moved from MSKCC in New York to ETH Zurich. We are excited about the new environment and the newly formed collaborations with the SIB Swiss Institute for Bioinformatics, the Max Planck-ETH Center for Learning Systems and with the University Hospital Zurich. In 2016 we started a new project on distributed storage and compute on very large graph genomes, an effort that will be funded by the National Research Program 75 “Big Data”. We are also heavily involved in the International Cancer Genome Consortium (ICGC) Pan Cancer Analysis Working Group and the The Cancer Genome Atlas (TCGA) PanCanAtlas project. The lab is actively involved in the BRCA Challenge, a demonstration project of the Global Alliance for Genomics and Health (GA4GH). The BRCA Challenge aims to advance understanding of the genetic basis of breast, ovarian, and other cancers that are driven by germline variants in BRCA1 and BRCA2 (BRCAexchange.org). In this context, we presented the project at a session of the Human Variome Project at UNESCO in Paris and at ASHG session in Vancouver. Gunnar Rätsch is participating and leading multiple efforts related to the Swiss Personalized Health network.
Main publications 2016
- S L Hyland, T Karaletsos, G Rätsch (2016) Knowledge Transfer with Medical Language Embeddings In: Proc. Data Mining for Medicine and Healthcare, May 5-7, 2016, Miami
- RiboDiff: detecting changes of mRNA translation efficiency from ribosome footprints.
Zhong Y, Karaletsos T, Drewe P, Sreedharan VT, Kuo D, Singh K, Wendel HG, Rätsch G.
Bioinformatics. 2017 Jan 1;33(1):139-141. doi: 10.1093/bioinformatics/btw585. PMID: 27634950
- Alternative Splicing Substantially Diversifies the Transcriptome during Early Photomorphogenesis and Correlates with the Energy Availability in Arabidopsis. Hartmann L, Drewe-Boß P, Wießner T, Wagner G, Geue S, Lee HC, Obermüller DM, Kahles A, Behr J, Sinz FH, Rätsch G, Wachter A. Plant Cell. 2016 Nov;28(11):2715-2734. PMID: 27803310