Predicting transcriptional regulatory interactions with artificial neural networks applied to E. coli multidrug resistance efflux pumps
2008

Predicting E. coli Drug Resistance with Neural Networks

Sample size: 58 publication Evidence: moderate

Author Information

Author(s): Veiga Diogo FT, Vicente Fábio FR, Nicolás Marisa F, Vasconcelos Ana Tereza R

Primary Institution: Laboratório Nacional de Computação Científica

Hypothesis

Can artificial neural networks predict transcriptional regulatory interactions in E. coli related to multidrug resistance?

Conclusion

The study successfully developed neural network predictors that can identify novel regulatory interactions in E. coli's multidrug resistance mechanisms.

Supporting Evidence

  • The neural networks achieved high precision and recall rates in classifying regulatory motifs.
  • New transcription factors were predicted for operons involved in multidrug resistance.
  • Correlations of expression data were used to differentiate between regulatory motifs and random sets.

Takeaway

Scientists used computer programs to help find new ways that bacteria resist drugs, which could help us understand and fight infections better.

Methodology

The study used artificial neural networks trained on gene expression data to predict regulatory interactions in E. coli.

Limitations

The study primarily focused on a limited number of transcription factors and operons, which may not represent the entire regulatory network.

Digital Object Identifier (DOI)

10.1186/1471-2180-8-101

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication