We are hiring for a junior data scientist position in Garching, near Munich, to strenghen our interdisciplinary team which specializes in the development of state-of-the-art deep learning and analytics pipelines for high-throughput protein analyses.

The successfull candidate should have a background in computer science, bioinformatics, statistics, physics, biology, biotechnlogy or related fields and demonstrated expertise in analysis of multidimensional data using classical data science frameworks (R, Python, Julia, etc.). The candidate will contribute to the creation of deep learning-based protein analysis software to aid with the understanding, diagnosis, and treatment of diseases by analyzing vast amount of biological data.

We look forward to receiving your comprehensive application as a single PDF file including your earliest starting date (to Dr. Martin Frejno): career@msaid.de

We are happy to announce that our novel publication in Rapid Communications in Mass Spectrometry has been accepted. The paper titled “INFERYS Rescoring: boosting peptide identifications and scoring confidence of database search results” can be accessed here.


Database search engines for bottom-up proteomics largely ignore peptide fragment ion intensities during the automated scoring of tandem mass spectra against protein databases. Recent advances in deep learning allow the accurate prediction of peptide fragment ion intensities. Using these predictions to calculate additional intensity-based scores help to overcome this drawback.

Here, we describe a processing workflow termed INFERYS™ Rescoring for the intensity-based rescoring of Sequest HT search engine results in Thermo Scientific™ Proteome Discoverer™ 2.5 software. The workflow is based on the deep learning platform INFERYS capable of predicting fragment ion intensities, which runs on personal computers without the need for GPUs. This workflow calculates intensity-based scores comparing PSMs from Sequest HT and predicted spectra. Resulting scores are combined with classical search engine scores for input to the FDR estimation tool Percolator.

We demonstrate the merits of this approach by analyzing a classical HeLa standard sample and exemplify how this workflow leads to a better separation of target and decoy identifications, in turn resulting in increased PSM, peptide and protein identification numbers. On an immunopeptidome dataset, this workflow leads to a 50% increase in identified peptides, emphasizing the advantage of intensity-based scores when analyzing low-intensity spectra or analytes with very similar physicochemical properties that require vast search spaces.

Overall, the end-to-end integration of INFERYS Rescoring enables simple and easy access to a powerful enhancement to classical database search engines, promising a deeper, more confident, and more comprehensive analysis of proteomic data from any organism by unlocking the intensity dimension of tandem mass spectra for identification and more confident scoring.


Zolg, DP, Gessulat, S, Paschke, C, et al. INFERYS Rescoring: boosting peptide identifications and scoring confidence of database search results. Rapid Commun Mass Spectrom. 2021;e9128. Accepted Author Manuscript. https://doi.org/10.1002/rcm.9128

MSAID, a pioneer in transforming proteomics with deep learning, announces an exclusive license agreement with Thermo Fisher Scientific, the world leader in serving science, to develop and commercialize deep learning tools for proteomics.

“Accurately measuring the proteome is a crucial step in the understanding, diagnosis, and treatment of diseases”, said Prof. Bernhard Kuster, a leading expert in proteomics and co-founder of MSAID GmbH. “Harnessing artificial intelligence will enable us to dig deeper into proteomic data and will unlock its true potential.”

Characteristics like chromatographic retention time or fragment ion intensities in tandem mass spectra are crucial for the confident identification of peptides from experimental data. Based on vast amounts of data, artificial intelligence can learn and subsequently predict these characteristics, extrapolating beyond the initial training data. Improving on the published deep learning model Prosit [1], MSAID developed INFERYS, an artificial intelligence, which will be made available to laboratories around the world through the collaboration with Thermo Fisher Scientific.

INFERYS will enable users to predict spectral libraries of entire proteomes with the click of a button. In addition, it powers INFERYS Rescoring, which automatically calibrates INFERYS to user data and then calculates intensity-based similarity scores for peptide-spectrum-matches, thereby improving the confidence in search results.

“INFERYS is fully compatible with CPUs and end-user hardware and does not require expensive GPUs to run. This marks the beginning of a new era in proteomics where artificial intelligence is at every researcher’s fingertips,” said Martin Frejno, co-founder and CEO of MSAID GmbH. “INFERYS will dramatically increase the confidence in results of proteomics experiments and help with the analysis of particularly challenging samples commonly encountered, for example, in Immunopeptidomics experiments.”

MSAID and Thermo Fischer Scientific will present the results of their collaboration at the American Society for Mass Spectrometry (ASMS) Reboot Program, from June 1-12, 2020. Also see Thermo Fisher’s press release on our collaboration.

[1] Prosit: proteome-wide prediction of peptide tandem mass spectra by deep learning; Gessulat S, Schmidt T et al., Nature Methods 2019.


MSAID GmbH [ɛm ɛs eɪd] transforms the way scientists analyze proteomics data. MSAID is a privately-held informatics spin-off from the Technical University of Munich, Germany. The company was founded by an interdisciplinary team of scientists with the vision to provide better computational solutions to the field of proteomics. All founders have an exceptionally strong track record and long-standing expertise in the acquisition, analysis, and interpretation of proteomic data. Our ambition is to replace current algorithms for proteomics with powerful, AI-based solutions, thereby paving the way for a smarter, deeper, and more reliable way of interrogating proteomic data. For more details, please visit www.msaid.de