Predicting antitubercular activity in the mouse model
What is it about?
This is a follow up to our earlier work in which we collated a large set of compounds tested for antitubercular activity in the mouse. We have now added a further 60 molecules from 2014-2015. which were used as a test set for various machine learning models. In addition we have assessed these compounds using mouse liver microsomes and in vitro MTB activity models.
Why is it important?
This work is important because testing compounds in vivo is expensive so any efforts to prioritize them would increase our efficiency. We show that using in vitro models may help in predicting in vivo efficacy. We also provide a novel clustering visualization of all the mouse in vivo TB data to date.
The following have contributed to this page: Dr Sean Ekins