Deep Multitask Learning-Driven Discovery of New Compounds Targeting Leishmania infantum
2024

Discovering New Compounds to Fight Leishmania infantum

Sample size: 1300000 publication 10 minutes Evidence: moderate

Author Information

Author(s): Santos Eder Soares de Almeida, Lemos Jade Milhomem, dos Santos Carvalho Alexandra Maria, Mendonça de Melo Felipe da Silva, Pereira Eufrasia de Sousa, Moreira-Filho José Teófilo, Braga Rodolpho de Campos, Muratov Eugene N., Grellier Philippe, Charneau Sébastien, Bastos Izabela Marques Dourado, Neves Bruno Junior

Primary Institution: Universidade Federal de Goiás

Hypothesis

Can multitask learning models effectively predict the antileishmanial activity of compounds against Leishmania species?

Conclusion

The study successfully identified three promising compounds with significant antileishmanial activity against L. infantum.

Supporting Evidence

  • Nine compounds showed significant in vitro antileishmanial activity against L. infantum.
  • Three compounds exhibited notable potencies with IC50 values ranging from 1.05 to 15.6 μM.
  • The study highlights the effectiveness of multitask learning models in virtual screening.

Takeaway

Researchers used computer models to find new medicines that can help treat a serious disease caused by tiny parasites. They found some strong candidates that could be tested further.

Methodology

The study developed multitask learning models to predict antileishmanial activity and screened 1.3 million compounds from the ChemBridge database.

Potential Biases

Potential biases may arise from the reliance on existing datasets and the inherent limitations of computational models.

Limitations

The predictive performance of the models may be limited by the availability of data for certain Leishmania species.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1021/acsomega.4c07994

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication