Skip to main content
Keyvisual ICB
Tex vector -

Computational Biomedicine

Menden Lab


The mission of our research group is to develop biostatistical and machine learning frameworks applied to biomedical data, to retrieve insights in the aetiology of complex diseases and identify novel intervention strategies. For this, we explore deep molecular characterised biomedical datasets, environmental factors, and tailor our models depending on disease specific knowledge gained through collaborations, literature and data driven analyses, thus empowering the next generation of drug target identification, drug repositioning and precision medicine.

Computational Cancer Pharmacogenomics 

We have strong expertise is in computational method development for cancer pharmacogenomics including the analysis of monotherapy and drug combination high-throughput screens, and lately, CRISPR lethality and drug resistance screens, which is highlighted by our recent ERC Starting Grant. The Menden Lab customises machine learning and biostatistical methods to predict drug sensitivity and synergy, as well as derived genetic biomarkers of these responses. Our work focuses on clinical translatability and interaction with the microenvironment, and thus enables patient stratification based on deep molecular profiles, which is the key pillar of precision.

Translational Computational Pharmacogenomics

The foundation of our endeavour is our strong expertise in Computational Cancer Pharmacogenomics (ERC StG), which we envision to generalise to the Translational Computational Pharmacogenomics. In particular, we expand our research focus totuberculosis drug resistance (, UNITE4TB), inflammatory skin diseases(IGSSE), neurodegenerative diseases (MUDS) and diabetes (DZD). Common across all projects, we are experts in analysing deep molecular characterisations of patients and disease models to stratify samples into drug responders or phenotypes, which ultimately enables precision medicine. In essence, our research vision is to establish a Translational Computational Pharmacogenomics programme in cancer and beyond, in order to accelerate the delivery of urgently needed targeted therapies. 




Research Group/Lab: Scientists at …

Michael Menden

Dr. Michael Menden

Junior Group Leader

Ginte Kutkaite

PhD candidate

Alexander Joschua Ohnmacht

PhD candidate

Ana Galhoz

PhD candidate

Christina Hillig

PhD candidate

Phong Nguyen

PhD candidate

Ines Assum

PhD candidate

Dr. Diyuan Lu


Martin Meinel

PhD candidate

Daniel Garger

Phd candidate

Göksu Avar

PhD candidate

Nikita Makarov

PhD candidate

Clara Meijs

PhD Candidate

Join our team!

For all positions, candidates should email their CV and a letter of interest to, including names of (ideally 3) references. The letter of interest has to be tailored to our group, mentioning projects or articles of our group that you find interesting, and explaining how you would fit on our group. Please also provide a pointer to a code repository if possible. Non-specific applications without this expression of interest or sent to a different address will not be considered.

- We have open positions for postdoctoral fellows, PhD students, or staff scientists, and welcome spontaneous applications or qualified candidates.

- In additions, we have opportunities for student assistants (HiWi), bachelor thesis, master thesis, and internships. In general, these are for a period of six months or longer, although shorter internships of 3 months are possible, in particular for local students. Besides the general information above, please include information on the lectures you have attended.


Open Internship position, Bachelor or Master thesis:

Modern machine learning techniques are revolutionising medical diagnosis, sometimes already performing better than human experts. We are interested in a wide range of topics related to drug response prediction, disease subtypes, drug discovery and development, clinical trial simulations, etc. We are looking for highly motivated and qualified students to join us in this journey.

The successful applicant (m/f/d) should have a background in computer science or a related discipline (e.g., machine learning, statistics, bioinformatics, etc.) and have strong programming (python or R) skills. Experience with some of the following is a plus but not required: tensorflow, pytorch, deep neural networks, RNASeq data analysis, time series predictions, etc. 

We are always looking for students for internship, bachelor’s or master’s thesis in the following topics.

  1. Machine learning for cancer subtyping 
  2. Machine learning for clinical trial simulations

Research Group: Publications

See all

2015 Nature

Stransky N*, Ghandi M*, Lehár J*, Amzallag A*, Menden MP*, Iorio F*, et al.

Pharmacogenomic agreement between two cancer cell line data sets

Large cancer cell line collections broadly capture the genomic diversity of human cancers and provide valuable insight into anti-cancer drug response. Here we show substantial agreement and biological consilience between drug sensitivity measurements and their associated genomic predictors from two publicly available large-scale pharmacogenomics resources: The Cancer Cell Line Encyclopedia and the Genomics of Drug Sensitivity in Cancer databases.

2016 Cell

Iorio F*, Knijnenburg TA*, Vis DJ*, Bignell GR*, Menden MP*, Schubert M, Aben N, Gonçalves E, Barthorpe S, Lightfoot H, Greninger P, van Dyk E, Chang H, de Silva H, Heyn HA, Deng X, Egan RK, Liu O, Mironenko T, Mitropoulos X, Richardson L, Wang J, Zhang T, Moran S, Saylos S, Soleimani M, Tamborero D, Lopez-Bigas N, Ross-Macdonald P, Esteller M, Gray N, Haber DA, Stratton MR, Benes CH, Wessels LFA, Saez-Rodriguez J, McDermott U#, Garnett MJ#.

A landscape of pharmacogenomic interactions in cancer

2018 Nature Communications

Menden MP*, Casale FP*, Stephan J, Bignell GR, Iorio F, McDermott U, Garnett MJ, Saez-Rodriguez J#, Stegle O#

The germline genetic component of drug sensitivity in cancer cell lines

Patients with seemingly the same tumour can respond very differently to treatment. There are strong, well-established effects of somatic mutations on drug efficacy, but there is at-most anecdotal evidence of a germline component to drug response. Here, we report a systematic survey of how inherited germline variants affect drug susceptibility in cancer cell lines. We develop a joint analysis approach that leverages both germline and somatic variants, before applying it to screening data from 993 cell lines and 265 drugs. Surprisingly, we find that the germline contribution to variation in drug susceptibility can be as large or larger than effects due to somatic mutations. Several of the associations identified have a direct relationship to the drug target. Finally, using 17-AAG response as an example, we show how germline effects in combination with transcriptomic data can be leveraged for improved patient stratification and to identify new markers for drug sensitivity.

2019 Nature Communications

Menden MP*, Wang D*, Guan Y*, Mason M*, Szalai B*, Bulusu KC*, Yu T, Kang J, Jeon M, Wolfinger R, Nguyen T, Zaslavskiy M, AstraZeneca-Sanger Drug Combination DREAM Consortium, Jang IS, Ghazoui Z, Ahsen MA, Vogel R, Neto EC, Norman T, Tang EKY, Garnett MJ, Di Veroli G, Fawell S, Stolovitzky G, Guinney J#, Dry JR#, Saez-Rodriguez J#.

A cancer pharmacogenomic screen powering crowed-sourced advancement of drug combination prediction

The effectiveness of most cancer targeted therapies is short-lived. Tumors often develop resistance that might be overcome with drug combinations. However, the number of possible combinations is vast, necessitating data-driven approaches to find optimal patient-specific treatments. Here we report AstraZeneca’s large drug combination dataset, consisting of 11,576 experiments from 910 combinations across 85 molecularly characterized cancer cell lines, and results of a DREAM Challenge to evaluate computational strategies for predicting synergistic drug pairs and biomarkers. 160 teams participated to provide a comprehensive methodological development and benchmarking. Winning methods incorporate prior knowledge of drug-target interactions. Synergy is predicted with an accuracy matching biological replicates for >60% of combinations. However, 20% of drug combinations are poorly predicted by all methods. Genomic rationale for synergy predictions are identified, including ADAM17 inhibitor antagonism when combined with PIK3CB/D inhibition contrasting to synergy when combined with other PI3K-pathway inhibitors in PIK3CA mutant cells.

2019 iScience

Guo T*#, Luna A*, Rajapakse VN*, ChiekKoh C*, Wu Z, Liu W, Sun Y, Gao H, Menden MP, Xu C, Calzone L, Martignetti L, Auwerx C, Buljan M, Banaei-Esfahani A, Ori A, Iskar M, Gillet L, Bi R, Zhang J, Zhang H, Yu C, Zhon Q, Varma S, Schmitt U, Qui P, Zhang Q, Zhu Y, Wild PJ, Garnett MJ, Bork P, Beck M, Liu K, Rodriguez JS, Elloumi F, Reinhold WC, Sander C, Pommier Y#, Aebersold R#

Quantitative proteome landscape of the NCI-60 cancer cell lines

2022 Emerging Infectious Diseases

Johanna Erber, Verena Kappler, Bernhard Haller, Hrvoje Mijočević, Ana Galhoz, Clarissa Prazeres da Costa, Friedemann Gebhardt, Natalia Graf, Dieter Hoffmann, Markus Thaler, Elke Lorenz, Hedwig Roggendorf, Florian Kohlmayer, Andreas Henkel, Michael P. Menden, Jürgen Ruland, Christoph D. Spinner, Ulrike Protzer*, Percy Knolle*, Paul Lingor*#, and on behalf of the SeCoMRI Study Group

Infection Control Measures and Prevalence of SARS-COV-2 IgG among 4,554 University Hospital Employees, Munich Germany


Michael Menden

Dr. Michael Menden

Junior Group Leader

58a / 003