Campolina: A Deep Neural Framework for Accurate Segmentation of Nanopore Signals
Preprint
Abstract
Nanopore sequencing enables real-time, long-read analysis by processing raw signals as they are produced. A key step, segmentation of signals into events, is typically handled algorithmically, struggling in noisy regions. We present Campolina, a first deep-learning frame-work for accurate segmentation of raw nanopore signals. Campolina uses a convolutional model to identify event boundaries and significantly outperforms the traditional Scrappie algorithm on R9.4.1 and R10.4.1 datasets. We introduce a comprehensive evaluation pipeline and show that Campolina aligns better with reference-guided ground-truth segmentation. We show that integrating Campolina segmentation into real-time frameworks, Sigmoni and RawHash2, improves their performance while maintaining time efficiency.Keywords
All Related Versions
- Published version: Genome Biology, 27 (1).
Funding Information
- Singapore Ministry of Health’s National Medical Research Council (NMRC/OFIRG/MOH-000649-00)
This publication has 18 references indexed in Scilit:
- RawHash2: mapping raw nanopore signals using hash-based seeding and adaptive quantizationBioinformatics, 2024
- Sigmoni: classification of nanopore signal with a compressed pangenome indexBioinformatics, 2024
- RawHash: enabling fast and accurate real-time analysis of raw nanopore signals for large genomesBioinformatics, 2023
- Nanopore sequencing technology, bioinformatics and applicationsNature Biotechnology, 2021
- Targeted nanopore sequencing by real-time mapping of raw electrical signal with UNCALLEDNature Biotechnology, 2020
- Readfish enables targeted nanopore sequencing of gigabase-sized genomesNature Biotechnology, 2020
- Nanopore sequencing and assembly of a human genome with ultra-long readsNature Biotechnology, 2018
- Real-time selective sequencing using nanopore technologyNature Methods, 2016
- Three decades of nanopore sequencingNature Biotechnology, 2016
- Deep learningNature, 2015