Welcome to modCnet’s documentation!

modCnet is a deep learning framework designed to harness the power of Oxford Nanopore direct RNA sequencing for precise identification of N4-acetylcytidine (ac4C) and 5-methylcytosine (m5C) sites, a crucial aspect in RNA modification studies. By effectively distinguishing ac4C and m5C from unmodified cytidine, modCnet enables accurate estimation of modification rates at each ac4C site. Through rigorous validation on independent in vitro datasets and a human cell line, modCnet showcases its robustness, versatility, and immense potential in advancing the understanding and exploration of ac4C modifications in mRNA.

To use modCnet, you can follow the instructions below:

Contents

• Installation
• Data preprocessing
  • Basecalling
  • Multi-fast5 to single-fast5
  • Resquiggling
  • Feature extraction
• Usage
  • Source code
  • Data processing
  • Training from scratch
  • Prediction
• Run examples
  • Train ac4C model using IVT datasets
  • Train m5C model using IVT datasets
  • Predict ac4C sites in human cell line
• Data postprocessing
  • Transcriptome location to genome location
  • Read-level predictions to site-level predictions
  • Futher analysis
• Getting Help
• Citing modCnet

Citing modCnet

If you use modCnet in your research, please cite **********************************

Contacts

modCnet is developed and maintained by You Wu and Xiang Yu from Shanghai Jiao Tong University. If you want to contribute or have any questions, please leave an issue in our repository.

Thank you!