Being a computer science student, I don't know much about statistical testing. However, recently, a lot of work has reported statistical validation of their result. In machine learning-based prediction of effector proteins, how do you apply statistical tests to validate the result?
Pl consult the article that may be useful
Genome-wide prediction of bacterial effector candidates across six secretion system types using a feature-based statistical framework
https://www.nature.com/articles/s41598-018-33874-1
Please as Prof Roy suggestrd please read the paper. After give us your research question. Then please take a look at this book which will help you with methods:
https://www.amazon.com/Clinical-Prediction-Models-Development-Validation/dp/3030163989/ref=sr_1_fkmr0_1?keywords=e+steyerburg+clinical+prediction&qid=1574386100&s=books&sr=1-1-fkmr0
After that you may want to ask another question. Best, David Booth
- Badges
- Science topic