Artem Shadskiy

The paper benchmarks gene annotation methods, showing fine-tuned DNA language models outperform existing tools and generalize across species and annotate non-coding transcripts.

This paper adapts a modernized BERT-style model to genomic sequence modeling, achieving strong efficiency and performance, and releases it as an open baseline.

This study compares dynamic and static loop extrusion models in chromatin folding, showing they produce distinct results and highlighting the importance of extruder behavior and noise in simulations.

This paper introduces an S1 nuclease-based Hi-C method for chromatin conformation capture, offering improved chromatin fragmentation and library preparation compared to DNase I Hi-C.