QSAR Modelling for Drug Discovery: Predicting the Activity of LRRK2 inhibitors for Parkinson's Disease using Cheminformatics Approaches

SEBASTIÁN-PÉREZ, VÍCTOR; MARTÍNEZ, MARÍA JIMENA; GIL, CARMEN; CAMPILLO, NURIA E.; MARTINEZ, ANA; PONZONI, IGNACIO

Toledo

Conferencia; PACBB 2018: 12th International Conference on Practical Applications of Computational Biology & Bioinformatics (PACBB 2018); 2018

Parkinson´s disease is one of the most common neurodegenerativedisorders in elder people and the leucine-rich repeat kinase 2 (LRRK2) is apromising target for its pharmacological treatment. In this paper, QSAR modelsfor identification of potential inhibitors of LRRK2 protein are designed by usingan in house chemical library and several machine learning methods. The appliedmethodology works in two steps: first, several alternative subsets of moleculardescriptors relevant for characterizing LRRK2 inhibitors are identified by afeature selection software tool; secondly, QSAR models are inferred by usingthese subsets and three different methods for supervised learning. Theperformance of all these QSAR models are assessed by traditional metrics andthe best models are analyzed in statistical and physicochemical terms.