Multitask learning-driven identification of novel antitrypanosomal compounds

• Published in: Future medicinal chemistry 2023-08, Vol.15 (16), p.1449-1467
• Main Authors: Lemos, Jade Milhomem, Brito da Silva, Meryck Felipe, dos Santos Carvalho, Alexandra Maria, Vicente Gil, Henric Pietro, Fiaia Costa, Vinícius Alexandre, Andrade, Carolina Horta, Braga, Rodolpho Campos, Grellier, Philippe, Muratov, Eugene N, Charneau, Sébastien, Moreira-Filho, José Teófilo, Dourado Bastos, Izabela Marques, Neves, Bruno Junior
• Format: Article
• Language: English
• Subjects: Chemical Sciences; Computer Science; deep learning; Life Sciences; low-data regimes; model explainability; neglected tropical diseases; QSAR; trypanosomatids; virtual screening
• ISSN: 1756-8919; 1756-8927
• DOI: 10.4155/fmc-2023-0074

Chagas disease and human African trypanosomiasis cause substantial death and morbidity, particularly in low- and middle-income countries, making the need for novel drugs urgent. Therefore, an explainable multitask pipeline to profile the activity of compounds against three trypanosomes ( and ) were created. These models successfully discovered four new experimental hits ( , , and ). Among them, showed promising results, with IC values ranging 0.01–0.072 μM and selectivity indices >10,000. These results demonstrate that the multitask protocol offers predictivity and interpretability in the virtual screening of new antitrypanosomal compounds and has the potential to improve hit rates in Chagas and human African trypanosomiasis projects. Improved approaches to antitrypanosomal drug discovery are needed to boost hit rates. To address this issue, multitask models were created to profile the activity of compounds against three trypanosomes. These models facilitated the discovery of four new antitrypanosomal hits.