Alignment-Aware Genomic Coordinate Encoding for Long-Range DNA Modeling
Xu Yang, Chenchen Qin, Fang Wang, Bing He, Yu Zhao, Jiayang Wu, Yanlin Zhang, Jianhua Yao
This paper introduces USM-AA, an alignment-aware genomic foundation model that improves long-range DNA modeling by incorporating reference genome coordinates and reverse-complement masked learning.
bioRxiv · Oct 12, 2026 · PreprintGenomics