Working group: “Statistics for translational oncology”

To deal with the ever increasing amount of biological data and related statistical questions, the working group ”Statistics for translational oncology” was established at the division of Biostatistics in 2006. We are working on the development, usage, and validation of statistical methods for clinical, pathological, imaging and molecular data. Beginning with new approaches in dealing with conventional low-dimensional data in retrospective analyses and prospective clinical trials, one main focus is the exploitation of high-dimensional molecular data to improve the understanding of carcinogenesis and prediction of disease outcome and prognosis. One topic in this context is the evaluation of function and interaction of genes during carcinogenesis. Further focus is given to the search for biomarkers associated with prognosis and disease outcome and for predictive genetic and genomic factors, i.e., the identification of biologically defined patient subgroups who benefit from specific treatment or who are susceptible to serious adverse events due to their genomic profile. Another research topic is the development and validation of statistical methods for classification, prognosis and prediction using high-dimensional data. We also cooperate with clinical units at the University hospitals Heidelberg and Ulm on research on prediction models with low and high-dimensional data structure. Furthermore, in a collaborative effort we developed a software tool that allows visual integrative analysis of comprehensive genomics data sets (L. Bullinger/A. Unwin/A. Benner, “SEURAT”, a project funded by the German José Carreras Foundation). Recently, the focus of our work has moved towards the development of statistical prediction models capable of integrating high-dimensional data from several molecular data sources (such as gene expression, methylation, and copy number variation data) while accounting for biological interrelations between these data. This research is done in close collaboration with the working group “Bayesian statistics for integrative genomics”.


Natalia Becker, Axel Benner (Team leader), Dominic EdelmannThomas Hielscher, Julia Krzykalla, Christina KunzMaral Saadati, Martin Sill

(Former members Martina Fischer, Christiane Heiß, Stephan Lücke, Wiebke Werft, Manuela Zucknick)


  • May 2011: Wiebke Werft (PhD, Medical Faculty, University Heidelberg)
  • July 2011: Christina Wunder (PhD, Medical Faculty, University Heidelberg)
  • August 2011: Lisa Bast (BSc Biomathematics, Koblenz University of Applied Sciences)
  • September 2011: Lars Ismail (MSc Statistics and OR, University of Edinburgh, UK)
  • November 2011: Natalia Becker (PhD, Medical Faculty, University Heidelberg)
  • November 2011: Martin Sill (PhD, Medical Faculty, University Heidelberg)
  • February 2013: Bianca Stenz (MSc Mathematics, Koblenz University of Applied Sciences)
  • November 2013: Stephan Lücke (MSc Medical Biometry/Biostatistics, University Heidelberg)

Research Support

  • 07/2009 - 06/2021 (BMBF)
    "IMPACT: Verbesserung der Langzeitprognose und der Lebensqualität von Patienten mit kolorektalem Karzinom”
  • 06/2015 - 05/2016 DKS)
    "Neuropath 2.0 - Increasing diagnostic accuracy in prediatric neurooncology”
  • 01/2010 - 12/2015 (DFG, KFO 227)
    Clinical Research Unit " Colorectal cancer: from primary tumor progression towards metastases"
  • 10/2011 - 09/2016 (Helmholtz-Gemeinschaft)
    Virtual Institute: "Understanding and overcoming resistance to apoptosis and therapy in leukemia"
  • 07/2012 - 07/2015 (DKFZ/BHC Alliance Joint Project)
    “Statistical methods for early detection of predictive biomarkers based on integrative analysis of omics data for cancer cell lines”
  • 01/2013 - 02/2016 (Else Kröner-Fresenius-Stiftung)
    “Integrated genome, methylome and transcriptome analyses of CLL”
  • 06/2013 - 02/2016 (DKH)
    "Risiko-adaptierte Prostatakarzinom (PCA) - Früherkennung durch eine „Basis“-PSA Bestimmung bei jungen Männern" (Prostatakrebsfrüherkennungs-Interventionsstudie, PROBASE)

Clinical Cooperations

  • Medical Oncology (Prof. Jäger) National Center for Tumor Diseases (NCT) Heidelberg
  • Department of Hematology, Oncology, and Rheumatology at Heidelberg University Hospital
  • Multiple Myeloma Section (University of Heidelberg and NCT) and GMMG (German Multiple Myeloma study group)
  • Research Group of Prof. Stilgenbauer, University Hospital of Ulm
  • German-Austrian Acute Myeloid Leukemia Study Group (AMLSG)

Software (R packages)

  • c060
    Additional functions for glmnet models
  • glmperm
    Inference in Generalized Linear Models
  • mfp
    Multivariable Fractional Polynomials
  • penalizedSVM
    Feature Selection SVM using penalty functions
  • s4vd
    Biclustering via sparse singular value decomposition incorporating stability selection
  • s4vdpca                                                                                                                                                                                                                                                                                                                                                                     Sparse principal component analysis using stability selection

Selected Publications

  • Becker N, Toedt G, Lichter P, Benner A. Elastic SCAD as a novel penalization method for SVM classification tasks in high-dimensional data. BMC Bioinformatics 2011; 12:138.
  • Benner A, Zucknick M, Hielscher T, Ittrich C, Mansmann U. High-dimensional Cox models: the choice of penalty as part of the model building process. Biom J. 2010; 52:50-69.
  • Binder H, Benner A, Bullinger L, Schumacher M. Tailoring sparse multivariable regression techniques for prognostic single-nucleotide polymorphism signatures. Stat Med 2013; 32: 1778-1791.
  • Gribov A, Sill M, Lück S, Rücker F, Döhner K, Bullinger L, Benner A, Unwin A. SEURAT: Visual analytics for the integrated analysis of microarray data. BMC Med Genomics. 2010; 3: 21.
  • Hielscher T, Zucknick M, Werft W, Benner A. On the prognostic value of survival models with application to gene expression signatures. Stat Med. 2010; 29: 818-829.
  • Saadati M, Benner A. Statistical challenges of high-dimensional methylation data. Stat Med 2014; 33: 5347-5357.
  • Sill M, Saadati M, Benner A. Applying stability selection to consistently estimate sparse principal components in high-dimensional molecular data. Bioinformatics 2015; 31: 2683-2690.
  • Werft W, Benner A, Kopp-Schneider A. On the identification of predictive biomarkers: Detecting treatment-by-gene interaction in high-dimensional data. Comp Stat and Data Analysis 2012; 56: 1275-1286.

to top