Effective training of nanopore callers for epigenetic marks with limited labelled data
Open Biology · 2024
DOI: 10.1098/rsob.230449 ↗Kurz gefasst
Fachartikel in der Zeitschrift Open Biology, 2024. Verfasst von Brian Yao und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering & Computer Sciences, University of California , Berkeley, CA 94720, USA. Hauptthemen laut MEDLINE: Epigenesis, Genetic, 5-Methylcytosine, DNA Methylation, Neural Networks, Computer. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Research Council.
Abstract (Originalsprache)
Nanopore sequencing platforms combined with supervised machine learning (ML) have been effective at detecting base modifications in DNA such as 5-methylcytosine (5mC) and N6-methyladenine (6mA). These ML-based nanopore callers have typically been trained on data that span all modifications on all possible DNA k -mer backgrounds—a complete training dataset. However, as nanopore technology is pushed to more and more epigenetic modifications, such complete training data will not be feasible to obtain. Nanopore calling has historically been performed with hidden Markov models (HMMs) that cannot make successful calls for k -mer contexts not seen during training because of their independent emission distributions. However, deep neural networks (DNNs), which share parameters across contexts, are increasingly being used as callers, often outperforming their HMM cousins. It stands to reason that a DNN approach should be able to better generalize to unseen k -mer contexts. Indeed, herein we demonstrate that a common DNN approach (DeepSignal) outperforms a common HMM approach (Nanopolish) in the incomplete data setting. Furthermore, we propose a novel hybrid HMM–DNN approach, amortized-HMM, that outperforms both the pure HMM and DNN approaches on 5mC calling when the training data are incomplete. This type of approach is expected to be useful for calling other base modifications such as 5-hydroxymethylcytosine and for the simultaneous calling of different modifications, settings in which complete training data are not likely to be available.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Electrical Engineering & Computer Sciences, University of California , Berkeley, CA 94720, USA.
- Department of Chemical Physics, Tel Aviv University , Tel Aviv-Yafo, Israel.
- Edmond J. Safra Center for Bioinformatics, Tel Aviv University , Tel Aviv-Yafo, Israel.
- Center for Computational Biology, University of California , Berkeley, CA 94720, USA.
ORCID-Profile: Jennifer Listgarten
Förderung
- European Research Council
Zitieren
APA
Yao, B., Hsu, C., Goldner, G., Michaeli, Y., Ebenstein, Y., & Listgarten, J. (2024). Effective training of nanopore callers for epigenetic marks with limited labelled data. Open Biology. https://doi.org/10.1098/rsob.230449
Vancouver
Yao B, Hsu C, Goldner G, Michaeli Y, Ebenstein Y, Listgarten J. Effective training of nanopore callers for epigenetic marks with limited labelled data. Open Biology. 2024. doi:10.1098/rsob.230449
BibTeX
@article{Yao2024,
author = {Yao, Brian and Hsu, Chloe and Goldner, Gal and Michaeli, Yael and Ebenstein, Yuval and Listgarten, Jennifer},
title = {Effective training of nanopore callers for epigenetic marks with limited labelled data},
journal = {Open Biology},
year = {2024},
doi = {10.1098/rsob.230449}
}
EUVIMED