Abstract

Single-molecule chromatin fiber sequencing is based on the single-nucleotide resolution identification of DNA N6-methyladenine (m6A) along individual sequencing reads. We present fibertools, a semi-supervised convolutional neural network that permits the fast and accurate identification of both endogenous and exogenous m6A-marked bases using single-molecule long-read sequencing. Fibertools enables highly accurate (>90% precision and recall) m6A identification along multi-kilobase DNA molecules with a ~1,000-fold improvement in speed and the capacity to generalize to new sequencing chemistries.

Competing Interest Statement

The authors have declared no competing interest.

Footnotes

* Added subsections headings, included new references, and extended the discussion.

* https://github.com/fiberseq/fibertools-rs

Details

Title
Fibertools: fast and accurate DNA-m6A calling using single-molecule long-read sequencing
Author
Jha, Anupama; Bohaczuk, Stephanie C; Mao, Yizi; Ranchalis, Jane; Mallory, Benjamin J; Min, Alan T; Hamm, Morgan O; Swanson, Elliott; Finkbeiner, Connor; Li, Tony; Whittington, Dale; William Stafford Noble; Stergachis, Andrew B; Vollger, Mitchell R
University/institution
Cold Spring Harbor Laboratory Press
Section
New Results
Publication year
2023
Publication date
Jul 6, 2023
Publisher
Cold Spring Harbor Laboratory Press
ISSN
2692-8205
Source type
Working Paper
Language of publication
English
ProQuest document ID
2833815575
Copyright
© 2023. This article is published under http://creativecommons.org/licenses/by/4.0/ (“the License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.