PhD Thesis

Déjà Vu - Réjà Vu 

On knowledge-based approaches linking 

ligand and target information 

to bioactivity

Over the last decades several disciplines relevant to medicinal chemistry and preclinical drug discovery have made gigantic leaps; this includes chemistry, biology and measurement of bioactivity. Better techniques have led to massive amounts of data. Moreover, sources of chemical and bioactivity data have become available in the public domain. Hence there is a need for new techniques combining and mining these data sources. This thesis focuses on computational methods combining data from these disciplines and demonstrates that the sum of these methods leads to better quality predictions than models using the individual data sources. One of the techniques central in this thesis is proteochemometric modeling, a machine learning approach linking chemical descriptors and protein descriptors to a biologically relevant output variable. This output variable describes the activity of molecules on biological macromolecules and hence proteochemometric models can make relevant predictions for both unseen molecules and unseen macromolecules (e.g. novel viral mutants). Secondly we present a novel technique that is able to combine information from multiple crystal structures in such a way that shared and unique pharmacophoric features can be isolated and visualised. Approaches presented here have been validated prospectively and have been shown to be widely applicable.

 Description  Notes    Publication
 Title Page    
 Chapter 1    
 Chapter 2   Proteochemometric Modeling as a Tool to Design Selective Compounds and for Extrapolating to Novel Targets 
 Chapter 3   Benchmarking of protein descriptor sets in proteochemometric modeling (part 1)

Benchmarking of protein descriptor sets in proteochemometric modeling (part 2) 
 Chapter 4   Identifying Novel Adenosine Receptor Ligands by Simultaneous Proteochemometric Modeling of Rat and Human Bioactivity Data 
 Chapter 5   Which Compound to Select in Lead Optimization? Prospectively Validated Proteochemometric Models Guide Preclinical Development 
 Chapter 6   Significantly Improved HIV Inhibitor Efficacy Prediction Employing Proteochemometric Models Generated From Antivirogram Data
 Chapter 7   Mining protein dynamics from sets of crystal structures using "consensus structures"
 Chapter 8     
Summary in English     
Summary in Dutch     
Summary in Laymen's Terms     
Publications_Afterword_Curriculum Vitae_Appendix     

Please find the supporting information pdf files below.