High-throughput screening and Bayesian machine learning for copper-dependent inhibitors of Staphylococcus aureus

  • Alex G. Dalecki, Kimberley M. Zorn, Alex M. Clark, Sean Ekins, Whitney T. Narmore, Nichole Tower, Lynn Rasmussen, Robert Bostwick, Olaf Kutsch, Frank Wolschendorf
  • Metallomics, January 2019, Oxford University Press (OUP)
  • DOI: 10.1039/c8mt00342d

Using machine learning for S. Aureus drug discovery

What is it about?

This article describes a large screen for copper dependent inhibitors of S. Aureus. The data were used for modeling chemical properties, Bayesian machine learning using Biovia software and Assay Central. We also performed a prospective screen and identified a couple of anti-helminths that are copper dependent inhibitors.

Why is it important?

The integration of HTS and machine learning with a large dataset.

Perspectives

Dr Sean Ekins
Collaborations in Chemistry

This was a very nice collaboration with the University of Alabama that spanned approx a year. It also highlighted the importance of looking at as many statistics and external tests as possible..

Read Publication

http://dx.doi.org/10.1039/c8mt00342d

The following have contributed to this page: Dr Sean Ekins