Cancer data science
New lab
In autumn 2021 the Gerstung lab has started a new Division for AI in Oncology at the German Cancer Research Centre DKFZ in Heidelberg, Germany. There will be plenty of job openings and exciting new reseach projects available for PhD students and Postdocs in the areas of cancer evolution, data science and AI covering both theoretical and experimental work. The Resarch Group at EMBL-EBI in Hinxton, UK, will continue to operate until around mid 2023.
Background
Cancer is a genetic disease caused by mutations to the genome. International efforts such as the International Cancer Genome Consortium (ICGC) have charted the genomic lesions leading to cancer at unprecedented detail and in tens of thousands of patients. A revelation of these projects was an even greater genomic complexity of cancer genomes than previously anticipated: Despite having the same disease each patient harbours a unique constellation of mutations. The genetic complexity of cancer is a challenge and an opportunity at the same time. A challenge to understand the underlying mechanisms of cancer development - and an opportunity for finding an explanation for differences in therapy success and outcome.
Data-driven cancer research
The group uses statistical approaches to enhance the quantitative understanding of cancer. This is critical to extract meaningful signals from big molecular data sets, such as genomics and transcriptomics, as well as imaging and large longitudinal records for thousands to millions of patients.
Specific research questions address
- the molecular mechanism of mutations,
- the evolutionary dynamics driving cancer,
- translational applications to predict the future trajectory from pre-malignant to malignant disease, and
- prognostic and clinical decision support algorithms
To address these questions we develop and utilise statistical algorithms to discriminate signal from noise in large data sets using high-dimensional statistical learning theory, but also employ machine and deep learning methods. In addition to answering quantative research questions and developing algorithms we also build clinical decision support tools.
Selected publications
-
M. Gerstung, C. Jolly, I. Lechshiner, et al (2020). The evolutionary history of 2,658 cancers. Nature 578:122–128.
-
Fu, Y. et al. (2019). Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis. bioRxiv 813543. doi:10.1101/813543
-
S. Abelson, G. Collord, S. W. K. Ng, et al. (2018). Prediction of acute myeloid leukaemia risk in healthy individuals. Nature, 559:400-404.
-
Grinfeld, J. et al. (2018). Classification and Personalized Prognosis in Myeloproliferative Neoplasms. N. Engl. J. Med. 379, 1416–1430.
-
M. Gerstung, E. Papaemmanuil, I. Martincorena, et al. (2017). Precision oncology for acute myeloid leukemia using a knowledge bank approach. Nat Genet, 49:332-340.
-
E. Papaemmanuil, M. Gerstung, L. Bullinger, et al. (2016). Genomic Classification and Prognosis in Acute Myeloid Leukemia. N Engl J Med, 374:2209-21.