NEMO: Improved and accurate models for identification of 6mA using Nanopore sequencing
Kulkarni, O. V.; Zaveri, L.; Singh, N. K.; Mathew, R. J.; Ara, S.; Garde, S.; Reddy, M.; Tallapaka, K. B.; Sowpati, D. T.
Show abstract
DNA methylation plays a key role in epigenetic regulation across lifeforms. Nanopore sequencing enables direct detection of base modifications. While multiple tools are currently available for studying 5-methylcytosine (5mC), there is a paucity of models that can detect 6-methyladenine (6mA) from raw nanopore data. Leveraging the motif-driven nature of bacterial methylation systems, we generated 6mA identification models that vastly surpass the accuracy of the current best model. Our work enables the study of 6mA at a single-base resolution in new as well as existing nanopore datasets.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- DeepMicro: deep representation learning for disease prediction based on microbiome data 94%
- Correspondence analysis for dimension reduction, batch integration, and visualization of single-cell RNA-seq data 93%
- Real-Time Selective Sequencing with RUBRIC: Read Until with Basecall and Reference-Informed Criteria 93%
Similar papers in this journal
- Comparing methylation levels assayed in GC-rich regions with current and emerging methods 94%
- MicroPIPE: An end-to-end solution for high-quality complete bacterial genome construction 92%
- XCVATR: Detection and Characterization of Variant Impact on the Embeddings of Single -Cell and Bulk RNA-Sequencing Samples 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.