We developed an innovative machine learning approach to predict TFPMs. By using the ProtBERT model for predicting TFs, we employed simplified K-mer features and a support vector machine to accomplish the task of predicting TFPMs. When we tested the method on an independent dataset, it outperformed all existing methods. Applying this approach to a complete dataset of human transcription factors revealed that many proteins from certain families show a strong preference for binding to methylated DNA. Current research in the field has delved into the mechanisms behind these binding preferences, and experimental validation has confirmed the binding principles for some of these proteins.
-
Notifications
You must be signed in to change notification settings - Fork 0
LiZaiyuan0619/RKmer-SVM4TFPM
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
A Simplified K-mer and SVM Method for Predicting TFPMs.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published