What is UNIVIE’s main focus?
The main focus of our work comprise the molecular basis of the interaction of ligands with transmembrane transport proteins and prediction of toxicity. For this we combine methods from ligand- and structure-based design with data science and machine learning.
How has participating in TransQST impacted your company?
We were able to collaborate with excellent groups, yielding exciting projects and publications. It especially pushed our work on systems biology approaches such as establishing compound-pathway fingerprints and their use for toxicity prediction and generation of hypotheses for mechanism of action for i.e., hepatotoxic compounds.
What challenges has UNIVIE faced across the project? What are your main achievements in TransQST?
For us it is always a challenge to understand the needs of our collaboration partners so that we can develop the respective computational tools to support and analyze their experiments. Together with EBI we developed and implemented Drig4Path, which integrates openly available data to gain insights of drugs` systemic effects. This resulted in two publications, as well as two openly available data science workflows.
Which TransQST outcome/s would you highlight? Why?
We would highlight all the very useful computational tools that were created in the scope of the project. These tools are very helpful in deciphering and quantifying toxic mechanisms and since they are mainly already published and openly accessible, they will support other projects beyond TransQST as well.
What do you believe is the main contribution of TransQST in the field?
In addition to the developed tools it is the immense data curation, integration, and annotation effort which has been put into e.g. withdrawn and black box warning drug data or histopathology data.