Welcome to m6anet’s documentation!

m6anet is a python tool that leverages Multiple Instance Learning framework to detect m6a modifications from Nanopore Direct RNA Sequencing data.

m6anet requires Python version 3.7 or higher. To install the latest release with PyPI (recommended) run:

pip install m6anet

See our Installation page for details.

To detect m6A modifications from your direct RNA sequencing sample, you can follow the instructions in our Quickstart page. m6Anet is trained on dataset sequenced using the SQK-RNA002 kit and has been validated on dataset from SQK-RNA001 kit. Newer pore version might alter the raw squiggle and affect segmentation and classification results and in such cases m6Anet might need to be retrained.

Contents

• Installation
  • PyPI installation (recommended)
  • Conda installation
  • Installation from our GitHub repository
• Quick Start
  • Dataprep
  • Inference
• Command line arguments
  • m6anet dataprep
  • m6anet inference
  • m6anet train
• Training m6Anet
• Getting Help
• Release Notes
  • Release Note 2.1.0
  • m6anet model trained with RNA004 chemistry (development version)
  • Training and evaluating the RNA004 m6anet
  • Acknowledgments
  • Release Note 2.0.0
  • API Changes
  • Faster and Better Inference Implementation
  • Rounding of Dataprep Output
  • Arabidopsis Trained m6Anet
• Citing m6Anet

Citing m6Anet

If you use m6Anet in your research, please cite Christopher Hendra, et al.,Detection of m6A from direct RNA sequencing using a Multiple Instance Learning framework. *Nat Methods* (2022)

Contacts

m6anet is developed and maintained by Christopher Hendra and Jonathan Göke from the Genome Institute of Singapore, A*STAR. If you want to contribute, please leave an issue in our repo

Thank you!