KinMethyl: robust methylation detection in prokaryotic SMRT sequencing via kinetic signal modeling and deep feature integration

TL;DR

KinMethyl improves detection of DNA methylation in bacteria using deep learning and kinetic signals from SMRT sequencing.

Contribution

KinMethyl introduces a novel deep learning framework that integrates sequence and kinetic signals for robust methylation detection in prokaryotes.

Findings

KinMethyl outperforms existing tools in methylation detection across bacterial species and modification types.

The method improves AUC by up to 0.20 for 5mC classification with statistical significance.

Performance improvements are consistent across species and sequencing platforms like RSII and Sequel.

Abstract

Accurate detection of 5-methylcytosine (5mC) from PacBio single-molecule real-time (SMRT) sequencing remains challenging in prokaryotes due to weak kinetic signals and motif diversity.

Here, we present KinMethyl, a generalizable deep learning framework that integrates sequence and kinetic signals to improve methylation detection across diverse bacterial genomes. Central to our approach is a regression model trained on whole-genome amplified samples to estimate the expected kinetics signals of unmethylated sequences. These predicted signals are incorporated into a downstream classifier to enhance the performance under low signal-to-noise conditions. KinMethyl outperforms existing tools such as kineticstools and ccsmeth across multiple bacterial species, methylation motifs, and modification types not only 5mC but also N6-methyladenine (6 mA) and N4-methylcytosine (4mC). In 5mC classification, KinMethyl improved the AUC by up to 0.20 compared to the existing method (0.6165 to 0.8190) with statistical significance (DeLong’s test, P < 1e-10). The improvements were consistently observed in cross-species evaluations as well as different sequencing platforms including RSII and Sequel. This work highlights the utility of kinetic signal modeling and feature integration for robust and motif-independent methylation analysis in prokaryotic epigenomics.

The source code is available at https://github.com/ZhangBio/KinMethyl.

Figures