Here, our main method developments based on structural information for target assessment are summarized.
Target deconvolution is a vital initial step in preclinical drug development to determine research focus and strategy. In this respect, computational target prediction is used to identify the most probable targets of an orphan ligand or the most similar targets to a protein under investigation. Applications range from the fundamental analysis of the mode-of-action over polypharmacology or adverse effect predictions to drug repositioning.
3D pharmacophore modeling is a powerful tool to encode a ligand’s physicochemical properties in space (pharmacophore features), which are supposed to be important for ligand-target binding. Such a model can be used for virtual screening for novel ligands matching the pharmacophore features. Depending on the available data for a target under investigation, 3D pharmacophores can be generated from either a set of known ligands (ligand-based), ligand-macromolecule complexes (structure/interaction-based), or macromolecules (apo structures) without binding ligands (target-based).
Besides target-independent approaches, we focus our structure-based developments on kinases, one of the major classes of therapeutic targets. This includes fragment-based approaches, kinase binding site comparison, and others.
Machine learning - and especially deep learning - models require large datasets for training. As such datasets, especially those containing protein-ligand-complex information - are more rare in the drug design landscape, we assess the use of in silico structural docking data for machine learning. To this end, we perform template docking using the OpenEye software on a large kinase activity dataset (kinodata) following the complex generation pipeline developed in kinoml.
Finding the optimal docking pipeline to identify novel ligands for a target of interest is challenging. Our project aims to develop a data-driven pipeline to find new hits for energy-coupling factor (ECF) transporters through the optimization of various structure-based virtual screening workflows.