Drug repositioning for the treatment of Chagas disease. Application of machine learning methods for the discovery of new drugs

ALBERCA LN; RUIZ D; MORALES JF; SBARAGLINI ML; CARRILLO C; TALEVI A

San Diego

Congreso; International Conference & Exhibition; 2018

Chagas disease is an infectious disease caused by the kinetoplastid Trypanosoma cruzi , affecting more than 6 millons people in Latin America. Despite the increasing knowledge on the biology of the parasite, there are still noeffective and safe drugs. The enzyme N-myristoyl transferase (NMT) has been validated as a druggable molecular target for the search of new drug against T. cruzi. In this work we have developed computational models capable of identifying NMT inhibitors. These models were applied in a virtual screening campaign and the 3 best candidates were acquired for in vitro assays. All theassayed drugs showed a strong trypanocidal activity against T. cruzi epimastigotes.From a database of 279 compounds previously tested against trypanosomatid NMT, we have generated computationalmodels capable of identifying drugs with trypanocidal activity. The ensemble models have shown a improvement in thepredictive capability of the individual models. We have applied the best model combination in the Virtual Screening ofSweetlead and DrugBank databases, finding 90 approved drugs as potential trypanocidal drugs. We have found that Danazol,Dicyclomine and Quinestrol have trypanocidal activity against T. cruzi epimastigotes, while only Quinestrol showed inhibitoryactivity against the clinically relevant T. cruzi trypomastigotes.The results demonstrate the value of in silico aided drug repurposing, since three active compounds were found with a minimal time- and resource-investment.Computer ? guided drug repositioning could efficiently provide solutions for neglected tropical diseases, such as Chagas disease.