About NanoBaseLib

Publication

BibTeX

@inproceedings{cheng2024nanobaselib,
  title     = {NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore Sequencing},
  author    = {Cheng, Guangzhao and Fu, Chengbo and Cheng, Lu},
  booktitle = {Advances in Neural Information Processing Systems},
  editor    = {A. Globerson and L. Mackey and D. Belgrave and A. Fan and U. Paquet and J. Tomczak and C. Zhang},
  volume    = {37},
  pages     = {76319--76331},
  year      = {2024},
  publisher = {Curran Associates, Inc.},
  doi       = {10.52202/079017-2430},
  url       = {https://nanobaselib.github.io}
}

Developer & maintainer

Questions and contributions: open an issue on GitHub.

Update log

• 7 Oct 2026Release of the redesigned website. New responsive layout with dark mode, filterable dataset tables and a benchmarks overview page.
• Dec 2024NanoBaseLib presented at NeurIPS 2024, Datasets and Benchmarks Track.
• 16 Aug 2024New pages: Nanopore signal processing and raw data download. Added dataset statistics, tool overview and baseline introductions.
• 12 Jun 2024Release of the initial dataset and benchmarks, NanoBaseLib v1.0.
• 30 Apr 2024Launch of the website.

Licenses

The processed dataset is released under the Creative Commons Attribution 4.0 license. The software is released under the Apache License 2.0. Raw data remain under the terms of their original repositories, cited on the raw data page.

Limitations

• Modified bases change the current but are labelled as the canonical nucleotide, so base calling ground truth is an approximation with an inherent accuracy ceiling.
• All datasets use R9.4 / R9.4.1 chemistry; performance on R10 chemistry still needs to be assessed. NanoBaseLib will be updated as new public data appear, and the current release is designated v1.0.
• The paper's benchmarks use a subset of the 16 datasets; the remaining datasets support broader evaluations.