How Could Perform a Predictive Model Created Using the Heterogeneous Chemical Space of Compounds against Trypanosoma cruzi?

Author(s)

Baldim, Joao L. ; Rosa, Welton ; Silva, Thais A. C. ; Ferreira, Daiane D. ; Tempone, Andre Gustavo ; de Paula, Daniela Aparecida C. ; Soares, Marisi G. ; Lago, Joao Henrique G.

• Document type: Journal article
• Source: Journal of the Brazilian Chemical Society; v. 36, n. 8, p. 13-pg., 2025-01-01.

Abstract

The limited treatment options for Chagas disease (CD), coupled with the side effects of approved drugs, highlight the urgent need to identify novel therapeutic candidates for this neglected disease. To address this challenge, we developed a strategy to assess whether existing data on this topic could support a comprehensive approach for predicting the antitrypanosomal properties of natural and synthetic compounds against Trypanosoma cruzi. The chemical space constructed in this study comprised various classes of compounds, which were subjected to machine learning-based screening to evaluate the robustness of different methodologies for handling heterogeneous data. The optimized models accurately predicted the antitrypanosomal activity of multiple compounds in the external test set, achieving correlation coefficient of the training set (R2) = 0.995, robustness (Q2) = 0.935, root mean squared error (RMSE) = 0.366, percentage split (P2) = 980, and correlation with predictions on the external test set (P2(testset)) = 0.888. Additionally, twentyfive compounds were tested in vitro against T. cruzi trypomastigotes, and the model successfully predicted their logarithm of half maximal inhibitory concentration (pIC50) values. This study proposes an approach for developing in house methodologies to identify promising candidates for biological assays by leveraging machine learning within a heterogeneous chemical space. (AU)

• FAPESP's process: 21/02789-7 - Search for bioactive metabolites with antiparasitic action in plant species from Atlantic Forest and Cerrado regions - a chemical, phenotypical, and metabolomic approach
• Grantee: João Henrique Ghilardi Lago
• Support Opportunities: BIOTA-FAPESP Program - Regular Research Grants
• FAPESP's process: 18/10279-6 - Selection and Optimization of New Drug Candidates for Leishmaniasis and Chagas Disease
• Grantee: André Gustavo Tempone Cardoso
• Support Opportunities: Regular Research Grants
• FAPESP's process: 18/07885-1 - Biomolecules from plant species of remnant areas of the Atlantic Forest and Cerrado to treat neglected tropical diseases - chemical and pharmacological aspects
• Grantee: João Henrique Ghilardi Lago
• Support Opportunities: BIOTA-FAPESP Program - Regular Research Grants
• FAPESP's process: 23/12447-1 - Searching for specialized metabolites from Brazilian floristic biodiversity as drug candidates for neglected tropical diseases
• Grantee: João Henrique Ghilardi Lago
• Support Opportunities: BIOTA-FAPESP Program - Regular Research Grants
• FAPESP's process: 16/19269-8 - Metabolic induction guided by genomic-mining strategies in Burkholderia thailandensis for the biosynthesis of antibiotic-like natural products
• Grantee: Joao Luiz Baldim Zanin
• Support Opportunities: Scholarships in Brazil - Post-Doctoral