Skip to content

Latest commit

 

History

296 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

4th Year Research Project and Dissertation

Code

Dissertation

The SARS-CoV-2 pandemic saw a high death toll which was reduced as drugs such as Remdesivir were introduced as treatments. This process was slow and few drugs were found capable of reducing the mortality of the virus. A solution to this issue is presented: finding existing, workable treatments using batch active learning. This combines greedy methodologies with clusters and uncertainty analysis, accumulating in a final algorithm RoDGer. Algorithms were compared with each other, with RoDGer producing a learning rate of $17.70\pm{}0.26$ compared to a learning rate of $16.32\pm{}0.36$ for random sampling. This was undertaken in a framework providing consistency between different algorithms, as well as providing a means of fitting parameters to different algorithms.

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages