TY  - CONF
AU  - Piroozeh, Zohreh
AU  - Akerman, Ildem
AU  - Kesselheim, Stefan
AU  - Kalinina, Olga
AU  - Bazarova, Alina
TI  - Interpretable prediction of DNA replication origins in S. cerevisiae using attention-based motif discovery
M1  - FZJ-2026-00952
PY  - 2025
AB  - In a living cell, DNA replication begins at multiple genomic sites, called replicationorigins. Identifying these origins and their underlying base sequence compositionis crucial for understanding replication process. Existing machine learningmethods for origin prediction often require labor-intensive feature engineering orlack interpretability. Here, we employ DNABERT to predict yeast replication originsand uncover sequence motifs by combining attention maps with MEME, aclassical bioinformatics tool. Our approach eliminates manual feature extractionand identifies biologically relevant motifs across datasets of varying complexity.This work advances interpretable machine learning in genomics, offering a potentiallygeneralizable framework for origin prediction and motif discovery.
T2  - ICLR 2025
CY  - 24 Apr 2025 - 28 Apr 2025, Singapore (Singapore)
Y2  - 24 Apr 2025 - 28 Apr 2025
M2  - Singapore, Singapore
LB  - PUB:(DE-HGF)24
DO  - DOI:10.34734/FZJ-2026-00952
UR  - https://juser.fz-juelich.de/record/1052350
ER  -