A validated and interpretable predictive model of cruzain inhibitors

Chagas disease affects 8-11 million people worldwide, most of them living in Latin America. Moreover, migratory phenomenon have spread the infection beyond endemic areas. Efforts for the development of new pharmacological therapies are paramount, as the pharmacological profile of the two marketed drugs currently available, nifurtimox and benznidazole, needs to be improved. Cruzain, a parasitic cysteine protease, is one of the most attractive biological targets due to its roles in parasite survival and immune evasion. In this work, we generated Quantitative Structure-Activity Relationship linear models for the prediction of pIC50 values of cruzain inhibitors. The statistical parameters for internal and external validation indicate high predictability with a cross-validated correlation coefficient of [Formula] and an external correlation coefficient of [Formula]. The applicability domain is quantitatively defined, according to QSAR good practices, using the leverage method. A qualitative interpretation of the model is provided based on protein-ligand interactions obtained from docking studies and structural information codified in the molecular descriptors relevant to the QSAR model. The model described in this work will be valuable for the discovery of novel cruzain inhibitors. Author summaryChagas disease is a major health problem in Latin America. The disease involves a long-lasting silent phase that usually culminates in serious or fatal heart damage. Despite its prevalence, there are only two antichagas approved drugs available. Despite these drugs have been in the market for more than 50 years, significant undesirable side effects and modest effectiveness in the chronic phase are prevalent. The need of new drugs to treat this disease is evident. Cruzain is a vital protein for the survival of Trypanosoma cruzi, the parasite causative of Chagas disease. Inhibition of this species-specific protein has been associated with improvements in pharmacological effects in animal models. Thus, blocking the activity of cruzain is an attractive approach for the development of antichagas agents. In this work, we present a validated mathematical model capable of predicting the cruzain inhibition value of a molecule from its chemical structure. This model can contribute to the identification of potential pharmacological alternatives against Chagas disease.