Artificial intelligence-driven research for drug discovery: tackling Chagas disease

Chagas disease is an infectious disease caused by the protozoan parasite Trypanosoma cruzi.1 This disease affects over 6-8 million people worldwide, killing over 12,000 patients annually.2 The treatment is limited to only one drug, benznidazole, which is only ineffective at the chronic phase of the disease and present limitations regarding its toxicity. Thus, there is an urgent need to develop new, safer, and effective drugs against the Chagas disease. Here, we developed binary and continuous QSAR models using random forest and deep neural networks for predicting trypanocidal activity and cytotoxicity of new molecules.3 As a result, we have obtained statistically predictive QSAR models, with accuracy ranging between 0.86–0.88 (binary models) and values ranging between 0.70–0.88 (continuous models). Then, we applied the best models for virtual screening of ChemBridge database. Future directions include experimental validation of prioritized virtual hits using in vitro assays.