In Silico Drug Discovery And Design

The heart of our computer-aided drug discovery technologies and services is guiding and accelerating the design of selective compounds. The emphasis and uniqueness of our approach is predicting binding profiles across a wide range of potential off-targets and taking these into account when designing novel and improved compounds. Inspired design strategies are realized by proprietary tools, grounded in computational chemistry and cutting edge artificial intelligence techniques.

With our proven track record in tweaking the selectivity of kinase inhibitors, we offer customized hit identification and lead optimization support against kinases as well as a variety of other target classes. Furthermore, we provide in-depth data science and machine learning skills to extract insights from complex biological and chemical data.

Our core technologies for computer-aided drug design

The ‘KinSpectrum’ technology contains prediction models for the entire kinome including cancer related resistance mutations. The technology is trained using a unique panel of biological bioactivity data combined with publicly available profiling data for kinases. Based on this large and diverse data source, we developed a powerful technology for hit identification and the identification of off-targets across the entire kinome. Similar prediction models can be also derived for other target classes.

‘Molecular Mojo’ is our de novo design pipeline for lead optimization that generates synthetically accessible compounds with improved activity and selectivity. The body of ‘Mojo’ comprises the identification of selectivity determining features in protein structures and the in silico design of project specific compound libraries with respect to retro-synthetic rules, whereas the soul is a multi-objective compound selection scheme where we employ our proprietary scoring technologies. In a nutshell, the soul consists of selectivity scoring via molecular grids and activity optimization using machine learning models of quantum mechanical calculations and ‘Matched Molecular Pair’ analysis to design the optimal compounds.

If you are interested in learning more about our technologies and services, please do not hesitate to get in touch.


  1. Volkamer, A., Eid, S., Turk, S., Jaeger, S., Rippmann, F., Fulle, S.
    The Pocketome of Human Kinases: Prioritizing the ATP binding sites of (yet) untapped protein kinases for drug discovery. J. Chem. Inf. Model. 2015, 55, 538–549.
  2. Volkamer, A., Eid, S., Turk, S., Rippmann, F., Fulle, S.
    Identification and visualization of kinase-specific subpockets. J. Chem. Inf. Model. 2016, 56, 335-346.
  3. Merget, B., Turk, S., Eid, S., Rippmann, F., Fulle, S.
    Profiling prediction of kinase inhibitors: toward the virtual assay. J. Med. Chem. 2017, 60, 474−485.
  4. Eid, S., Turk, S., Volkamer, A., Rippmann, F., Fulle, S.
    KinMap: a web-based tool for interactive navigation through human kinome data. BMC Bioinformatics, 2017, 18:16.
  5. Fulle, S., Merget, B.
    In silico Design selektiver Kinase-Inhibitoren rückt in greifbare Nähe. 2016, 11, 40-43.
  6. Fulle, S., Merget, B., Turk. S
    Towards in silico design of selective kinase inhibitors. Int. Ed. 2017, 11, 40-43.
  7. Sorgenfrei, F.A., Fulle, S., Merget, B.
    Kinome-wide profiling prediction of small molecules. ChemMedChem, accepted.

Our Team Members

Dr. Simone Fulle

Head of Bioinformatics

Works with the team on software development and research projects

Previous work
  • 20132016: Group leader of the team “Selective Kinase Inhibitors” at BioMed X
  • 2011–2013: Postdoctoral Researcher in Computer-aided Drug Design at InhibOx Ltd., Oxford
  • 2010–2011: Postdoctoral Researcher at the Heinrich Heine University, Düsseldorf
  • 2010: PhD in Structural Bioinformatics at the Goethe University, Frankfurt/Main

Dr. Benjamin Merget

Principal Scientist, Computational Chemistry & Data Science

Responsible for computational chemistry and data-mining tasks, such as molecular modeling, compound optimization, and off-targets prediction

Previous work
  • 20152016: Postdoctoral Researcher at BioMed X
  • 20112015: PhD in Computational Medicinal Chemistry at the University of Würzburg

Dr. Samo Turk

Principal Scientist, Cheminformatics & De Novo Design

Responsible for curating and mining ligand data as well as for compound optimization suggestions

Previous work
  • 2013–2016: Postdoctoral Researcher at BioMed X
  • 2011–2013: Postdoctoral Researcher in Computer-aided Drug Design, Cheminformatics and Medicinal Chemistry at the University of Ljubljana
  • 2011: PhD in Medicinal Chemistry at the University of Ljubljana