Background/Objectives: Chagas disease is a neglected tropical disease caused by the protozoan parasite Trypanosoma cruzi, which currently affects around 8 million people worldwide. The therapeutic arsenal against T. cruzi is so far limited to only two approved drugs, benznidazole and nifurtimox, that have considerable side effects and limited efficacy in the chronic stage of the disease. Here, we have resorted to supervised phenotypic machine learning models to explore drug repurposing opportunities and identify potential new therapeutic solutions for Chagas disease. Methods: More than 100,000 bioactivity data points were retrieved from ChEMBL and carefully curated according to the data-centric machine learning paradigm. After curation, two datasets comprising 344 compounds tested against T. cruzi Y strain trypomastigotes and 785 compounds tested against Tulahuen strain amastigotes were obtained and used to infer ensemble learning models with excellent average and early enrichment metrics in retrospective screening experiments (AUROC > 0.96 and EF_0.01 > 58). A prospective screening campaign was then performed on DrugBank and the Drug Repurposing Hub databases, submitting eight in silico hits for experimental confirmation. Results: Six of the in silico hits confirmed their predicted trypanocidal effects. Conclusions: We have built portable meta-classifiers capable of identifying small molecules with trypanocidal activity against amastigotes, the clinically most relevant stage of T. cruzi. The predictive ability of this meta-classifier was experimentally validated.

Trypanosoma cruzi , the etiological agent of Chagas disease, has a digenetic life cycle. In its passage from the insect vector to the mammalian host, and vice versa, it must be prepared to cope with abrupt changes in environmental conditions in order to survive. Sensing and signaling pathways that allow the parasite to adapt, have unique characteristics with respect to their hosts and other free-living organisms. Many of the canonical proteins involved in these transduction pathways have not yet been found in the genomes of these parasites, because they present divergences either at the functional, structural and/or protein sequence level. All of this makes these pathways promising targets for therapeutic drugs. The AMP-activated protein kinase (AMPK) is a serine/threonine kinase activated by environmental stresses that results in reduction of ATP and increase of AMP levels. Thus, AMPK is regarded as a fuel gauge, functioning both as a nutrient and an energy sensor, to maintain energy homeostasis and, eventually, to protect cells from death by nutrient starvation. In the present study, we report the characterization of AMPK complexes for the first time in T. cruzi and describe the function of TcAMPK as a novel regulator of nutritional stress in epimastigote forms. We demonstrate that this complex possesses specific AMPK kinase activity in epimastigotes, which is inhibited by Compound C and is modulated by carbon source availability. In addition, TcAMPKα2 subunit has an unprecedented functional substitution (Ser x Thr) at the activation loop and its overexpression in epimastigotes led to higher autophagic activity during prolonged nutritional stress. Moreover, the over-expression of the catalytic subunits resulted in antagonistic phenotypes associated with proliferation. Together, these results point to a role of TcAMPK in autophagy and nutrient sensing, key processes for the survival of trypanosomatids and for its life cycle progression.