TB Topo I machine learning
What is it about?
This work collates a large library of over 600 molecules tested vs TB Topo I and uses them to build various machine learning models. These modes were compared vs docking for identifying new inhibitors.
Why is it important?
While we can generate statistically meaningful machine learning models after 5 fold cross validation etc, these models were not successful in identifying new compounds for in vitro testing. Docking in a homology model seemed to do much better. A more recently derived apo structure for TB top I was used to dock some of out in vitro actives to rationalize them. We also compared the homology model vs the apo structure.
The following have contributed to this page: Dr Sean Ekins