See all
Research Projects

Development of (deep) machine learning computational proteomics tools and algorithms and its application to MaxQuant


Jürgen Cox
MPI, 1st Supervisor

Eduard Sabidó
CRG, 2nd Supervisor


Improve existing and build new learning models for the prediction of MS-based proteomics related peptide and protein properties. These will be integrated into the MaxQuant software to improve the identification and quantification of peptides and proteins. Prediction targets include fragmentation spectra, collision cross-section, retention time, and many more. The aim is to integrate these improvements into the DDA, DIA, and top-down modules of MaxQuant.


Algorithm development in the C# based MaxQuant environment making use of the machine and deep learning libraries such as TensorFlow and Microsoft CNTK. Team-based programming in the Cox lab continuous integration environment.

Required Skills

Excellent programming skills
Good command of English
Background knowledge in biology or mass spectrometry is a plus

Expected Results

A version of the MaxQuant software with highly enhanced identification and quantification capabilities. It will be platform-independent and highly parallelized.

Planned Secondments

Host: CRG (E. Sabido), Duration: 2 Months; When: Year 1; Goal: Experience in wet lab proteomics.

Host: THERMO (B. Delanghe), Duration: 2 Months; When: Year 2; Goal: Algorithm development.

Host: DDS (P. Garcia), Duration: 1 Month; When: Year 3; Goal: Visualization strategies.

Enrolment in doctoral programs

Ph.D. from the Faculty of Medicine at TUM.


1. Tiwary, S., Levy, R., Gutenbrunner, P., Salinas Soto, F., Palaniappan, K. K., Deming, L., Berndl, M., Brant, A., Cimermancic, P., and Cox, J. (2019) High quality MS/MS spectrum prediction for data-dependent and data-independent acquisition data analysis. Nat. Methods, doi:10.1038/s41592-019-0427-6.
Prianichnikov, N., Koch, H., Koch, S., Lubeck, M., Heilig, R., Brehmer, S., Fischer, R. and Cox, J. (2020) MaxQuant software for ion mobility enhanced shotgun proteomics. Mol. Cell. Proteomics 19, 1058-69, doi:10.1074/mcp.TIR119.001720

2. Sinitcyn, P., Rudolph, J.D. and Cox, J. (2018). Computational Methods for Understanding Mass Spectrometry–Based Shotgun Proteomics Data. Annual Review of Biomedical Data Science 1, 207-234.

3. Yu, S.H., Kyriakidou, P. and Cox, J. (2020) Isobaric matching between runs and novel PSM-level normalization in MaxQuant strongly improve reporter ion-based quantification. J. Proteome Res. 19, 3945-54, doi:10.1021/acs.jproteome.0c00209.

4. Yu, S.H., Ferretti, D., Schessner, J.P., Rudolph, J.D., Borner, G.H.H and Cox, J. (2020) Expanding the Perseus Software for Omics Data Analysis With Custom Plugins. Curr. Protoc. Bioinformatics 71, e105, doi:10.1002/cpbi.105.

5. Rudolph, J.D. and Cox, J. (2019) A network module for the Perseus software for computational proteomics facilitates proteome interaction graph analysis. J. Proteome Res. 18, 2052–2064, doi: 10.1021/acs.jproteome.8b00927.

6. Sinitcyn, P., Tiwary, S., Rudolph, J.D., Gutenbrunner, P., Wichmann, C., Yilmaz, S., Hamzeiy, H. and Cox, J. (2018). MaxQuant goes Linux. Nature Methods 15, 401.