End-to-end simulation of nanopore sequencing signals with feed-forward transformers

Denis Beslic, Martin Kucklick, Susanne Engelmann, Stephan Fuchs, Bernhard Y Renard, Nils Körber · 2025

Read End-to-end simulation of nanopore sequencing signals with feed-forward transformers by Denis Beslic, Martin Kucklick, Susanne Engelmann, Stephan Fuchs, Bernhard Y Renard, Nils Körber (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11729726.txt.

Description

Faking the electrical squiggle of a DNA sequencer helps test analysis tools without burning real samples. Denis Beslic and co-authors present a transformer model for that job in this paper, published in 2024. Older simulators lean on fixed tables for short sequence chunks, which miss how real signals flow and age badly as the chemistry changes.

Their model, seq2squiggle, learns context from chopped real signals and writes new ones in one pass. On two generations of flow cell data it beat rival simulators on signal likeness, base reading accuracy, and variant finding. The code is free on GitHub. The authors aim it at method developers who need truth-like data on demand.

Catalog record

CREATORDenis Beslic, Martin Kucklick, Susanne Engelmann, Stephan Fuchs, Bernhard Y Renard, Nils Körber
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE36 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11729726

Browse the full library · About the Tower of Babel