Table 2.
Overview of the features and the models used in the methods reviewed by this article. Feature level describes the type of input features used by the software. All methods modeled on the raw electrical current are classified into the signal intensity, and otherwise, it is labeled as the base call error.
| Feature level | Model/Method | URL | |
|---|---|---|---|
| DENA | Signal intensity | Deep Learning | https://github.com/weir12/DENA |
| m6Anet | https://github.com/GoekeLab/m6anet | ||
| nanoDoc | https://github.com/uedaLabR/nanoDoc | ||
| MINES | Machine Learning | https://github.com/YeoLab/MINES.git | |
| nano-ID | https://github.com/birdumbrella/nano-ID | ||
| nanom6A | https://github.com/gaoyubang/nanom6A | ||
| NanoRMS | https://github.com/novoalab/nanoRMS | ||
| Penguin | https://github.com/Janga-Lab/Penguin | ||
| EpiNano-SVM | https://github.com/novoalab/EpiNano | ||
| Nanocompore | Bayesian Modelling | https://github.com/tleonardi/nanocompore | |
| xPore | https://github.com/GoekeLab/xpore | ||
| Yanocomp | http://www.github.com/bartongroup/yanocomp | ||
| DiffErr | Base call error | Differential Tests | https://github.com/bartongroup/differr_nanopore_DRS |
| DRUMMER | https://github.com/DepledgeLab/DRUMMER | ||
| ELIGOS | https://gitlab.com/piroonj/eligos2 | ||
| EpiNano-Error | https://github.com/novoalab/EpiNano |