Towards a foundation model for raw nanopore signal through discrete tokenization
This paper introduces Brieno, a self-supervised model for raw nanopore signals that improves read classification and methylation detection without reference genomes.
Author
Aalto UniversityORCID 0009-0008-6160-3637Unclaimed ORCID profile · follow to get notified of new preprints
4 papers
Recent·Most cited
This paper introduces Brieno, a self-supervised model for raw nanopore signals that improves read classification and methylation detection without reference genomes.
Guangzhao Cheng, Lassi Härtsiä, Minna‐Liisa Änkö, Lu Cheng
segSHAPE improves RNA secondary structure prediction from Nanopore DRS data by enhancing signal alignment and modification rate estimation, achieving higher accuracy than existing methods.
Guangzhao Cheng, Aki Vehtari, Lu Cheng
This paper introduces SegPore, a method for improving raw signal segmentation in Nanopore direct RNA sequencing, leading to better RNA modification detection.
Guangzhao Cheng, Tien Le, Ran Zhou, Lu Cheng
The paper introduces SCAPE-APA, an improved version of SCAPE for estimating alternative polyadenylation events from scRNA-seq data, with optimizations for speed and reliability.