Tranquillyzer: A Neural Network Framework for Long-read Annotation and Demultiplexing
Genomics, Proteomics & Bioinformatics · 30.06.2026
DOI: 10.1093/gpbjnl/qzag055 ↗Kurz gefasst
Fachartikel in der Zeitschrift Genomics, Proteomics & Bioinformatics, online erschienen am 30.06.2026. Verfasst von Ayush Semwal und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Epigenetics, Van Andel Research Institute, Grand Rapids, MI 49503, USA. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Long-read single-cell RNA sequencing enables full-length transcript profiling but remains limited by challenges in interpreting structurally complex sequencing reads. High error rates, heterogeneous library designs, and frequent molecular artifacts disrupt barcode and UMI detection, while existing pipelines rely on positional heuristics that fail when structural elements are shifted, truncated, rearranged, or concatenated. Here, we introduce Tranquillyzer, a deep learning framework for global, context-aware structural inference of long-read molecules. Tranquillyzer performs base-resolution annotation of sequencing reads by modeling their full architectural context, enabling accurate identification of adapters, barcodes, UMIs, and transcript segments even under substantial sequencing noise and structural variability. Across simulated benchmarks, Tranquillyzer achieved > 99.7% structural filtering accuracy, > 91% demultiplexing efficiency, and > 99.9% demultiplexing accuracy, substantially exceeding existing methods. Tranquillyzer supports standard long-read single-cell protocols and can be rapidly trained to interpret custom library architectures. Its scalable processing and read-level visualization enable systematic detection of complex molecular artifacts, including multi-fragment chimeras. By enabling reliable structural parsing of long-read libraries, Tranquillyzer provides a generalizable framework for structural interpretation of single-cell and bulk long-read sequencing data. Tranquillyzer is freely available at: https://github.com/huishenlab/Tranquillyzer.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Epigenetics, Van Andel Research Institute, Grand Rapids, MI 49503, USA.
- Department of Cell Biology, Van Andel Research Institute, Grand Rapids, MI 49503, USA.
ORCID-Profile: Ayush Semwal, Jacob Morrison, Ian Beddows, Theron Palmer, Mary F Majewski, H Josh Jang, Benjamin K Johnson, Hui Shen
Zitieren
APA
Semwal, A., Morrison, J., Beddows, I., Palmer, T., Majewski, M. F., Josh Jang, H., Johnson, B. K., & Shen, H. (2026). Tranquillyzer: A Neural Network Framework for Long-read Annotation and Demultiplexing. Genomics, Proteomics & Bioinformatics. https://doi.org/10.1093/gpbjnl/qzag055
Vancouver
Semwal A, Morrison J, Beddows I, Palmer T, Majewski MF, Josh Jang H, et al. Tranquillyzer: A Neural Network Framework for Long-read Annotation and Demultiplexing. Genomics, Proteomics & Bioinformatics. 2026. doi:10.1093/gpbjnl/qzag055
BibTeX
@article{Semwal2026,
author = {Semwal, Ayush and Morrison, Jacob and Beddows, Ian and Palmer, Theron and Majewski, Mary F and Josh Jang, H and Johnson, Benjamin K and Shen, Hui},
title = {Tranquillyzer: A Neural Network Framework for Long-read Annotation and Demultiplexing},
journal = {Genomics, Proteomics & Bioinformatics},
year = {2026},
doi = {10.1093/gpbjnl/qzag055}
}
EUVIMED