Machine learning algorithms in big data analyses identify determinants of insulin gene transcription
Wilson K. M. Wong, Vinod Thorat, Mugdha V. Joglekar, Charlotte X. Dong, Hugo Lee, Yi Vee Chew, Adwait Bhave, Wayne J. Hawthorne, Feyza Engin, Aniruddha Pant, Louise T. Dalgaard, Sharda Bapat, Anandwardhan A. Hardikar
The paper compares 10 machine learning workflows to identify genes associated with insulin transcript presence in human pancreatic single-cell transcriptomes, finding Random Forest to be highly predictive.
bioRxiv · Mar 27, 2021 · PreprintGenetics