Perturbation-theory machine learning for mood disorders: virtual design of dual inhibitors of NET and SERT proteins
2024

Machine Learning for Mood Disorders: Designing Dual Inhibitors

Sample size: 2742 publication 10 minutes Evidence: moderate

Author Information

Author(s): Kleandrova Valeria V., Cordeiro M. Natália D. S., Speck-Planche Alejandro

Primary Institution: University of Porto

Hypothesis

Can a machine learning model effectively predict and design dual-target inhibitors for mood disorders?

Conclusion

The study successfully developed a machine learning model that predicts dual-target inhibitors for mood disorders with promising results.

Supporting Evidence

  • The PTML-MLP model achieved an accuracy of around 80%.
  • Four new drug-like molecules were designed based on the model's predictions.
  • The model can predict activity against multiple experimental conditions.
  • Designed molecules showed potential for dual-target activity against NET and SERT.

Takeaway

Researchers created a computer program that helps design new medicines for mood disorders by targeting two proteins at once.

Methodology

The study used a perturbation-theory machine learning model based on a multilayer perceptron network to predict and design inhibitors.

Potential Biases

Potential biases in the dataset used for training the model could affect the predictions.

Limitations

The model's predictions need experimental validation and may not account for all biological complexities.

Participant Demographics

The study does not specify participant demographics as it focuses on computational modeling.

Statistical Information

P-Value

0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/s13065-024-01376-z

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication