PuSH - Publication Server of Helmholtz Zentrum München

Hingerl, J.C.* ; Karollus, A.* ; Gagneur, J.

Flashzoi: An enhanced Borzoi for accelerated genomic analysis.

Bioinformatics 41:btaf467 (2025)
Publ. Version/Full Text Research data DOI PMC
Open Access Gold
Creative Commons Lizenzvertrag
MOTIVATION: Accurately predicting how DNA sequence drives gene regulation and how genetic variants alter gene expression is a central challenge in genomics. Borzoi, which models over ten thousand genomic assays including RNA-seq coverage from over half a megabase of sequence context alone promises to become an important foundation model in regulatory genomics, both for massively annotating variants and for further model development. However, the currently used relative positional encodings limit Borzoi's computational efficiency. RESULTS: We present Flashzoi, an enhanced Borzoi model that leverages rotary positional encodings and FlashAttention-2. This achieves over 3-fold faster training and inference and up to 2.4-fold reduced memory usage, while maintaining or improving accuracy in modeling various genomic assays including RNA-seq coverage, predicting variant effects, and enhancer-promoter linking. Flashzoi's improved efficiency facilitates large-scale genomic analyses and opens avenues for exploring more complex regulatory mechanisms and modeling. AVAILABILITY: The Flashzoi model architecture is part of the MIT-licensed borzoi-pytorch package, can be found at https://github.com/johahi/borzoi-pytorch and installed via pip. Model weights for all four Flashzoi and Borzoi replicates are available at https://huggingface.co/johahi under the MIT license. The code has been archived at https://zenodo.org/records/15669913. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Impact Factor
Scopus SNIP
Altmetric
0.000
0.000
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Journal article
Document type Scientific Article
Language english
Publication Year 2025
HGF-reported in Year 2025
e-ISSN 1367-4811
Journal Bioinformatics
Quellenangaben Volume: 41, Issue: 9, Pages: , Article Number: btaf467 Supplement: ,
Publisher Oxford University Press
Publishing Place Oxford
Reviewing status Peer reviewed
POF-Topic(s) 30205 - Bioengineering and Digital Health
Research field(s) Enabling and Novel Technologies
PSP Element(s) G-503800-001
Grants DFG
Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)
European Research Council (ERC)
Scopus ID 105017086967
PubMed ID 40905959
Erfassungsdatum 2025-11-13