Author

Till Muser

ETH ZurichORCID 0000-0002-9856-4554Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Signature Assays, Organisms & Methods

Click to filter · or open tag

Assay:ATAC-seq· 2 Approach:deep learning· 2 Research Focus:differential expression· 2 Research Focus:benchmarking· 1 Research Focus:gene regulatory network inference· 1 Organism:human· 1 Approach:transformer / foundation model· 1 Research Focus:variant effect prediction· 1

Frequent Co-Authors

Aayush GroveriD· 2 shared Ekaterina KrymovaiD· 2 shared Lin ZhangiD· 2 shared Valentina BoevaiD· 2 shared Eliezer M. Van AlleniD· 1 shared Fabian Joachim TheisiD· 1 shared Ignacio L. IbarraiD· 1 shared Josephine YatesiD· 1 shared

Activity by Year

2026-2026 · peak 2/yr

Co-Author Collaboration Network

10 top collaborators · 40 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

2 shared papersGenomics

Aayush GroverORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

GenomicsNucleic Acids ResearchPeer-reviewedMay 5, 2026

UniversalEPI: robust prediction of cell type-specific and differential chromatin interactions from DNA sequence and chromatin accessibility

Aayush Grover, Lin Zhang, Till Muser…·Valentina Boeva

UniversalEPI predicts cell type-specific and differential chromatin interactions using DNA sequence and ATAC-seq data, showing robust performance across cell types and conditions.

DOI 10.1093/nar/gkag485

humanATAC-seq

𝕏 PostBluesky

GenomicsGenome ResearchPeer-reviewedMar 1, 2026

Early feature extraction drives model performance in high-resolution chromatin accessibility prediction: A systematic evaluation of deep learning architectures

Aayush Grover, Till Muser, Liine Kasak…·Valentina Boeva

The paper evaluates deep learning architectures for high-resolution chromatin accessibility prediction, finding that early feature extraction, not downstream architecture, primarily determines performance.

DOI 10.1101/gr.281042.125

ATAC-seqdeep learning

𝕏 PostBluesky