Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Rethinking Genomic Modeling Through Optical Character Recognition

About

Recent genomic foundation models largely adopt large language model architectures that treat DNA as a one-dimensional token sequence. However, exhaustive sequential reading is structurally misaligned with sparse and discontinuous genomic semantics, leading to wasted computation on low-information background and preventing understanding-driven compression for long contexts. Here, we present OpticalDNA, a vision-based framework that reframes genomic modeling as Optical Character Recognition (OCR)-style document understanding. OpticalDNA renders DNA into structured visual layouts and trains an OCR-capable vision--language model with a \emph{visual DNA encoder} and a \emph{document decoder}, where the encoder produces compact, reconstructible visual tokens for high-fidelity compression. Building on this representation, OpticalDNA defines prompt-conditioned objectives over core genomic primitives-reading, region grounding, subsequence retrieval, and masked span completion-thereby learning layout-aware DNA representations that retain fine-grained genomic information under a reduced effective token budget. Across diverse genomic benchmarks, OpticalDNA consistently outperforms recent baselines; on sequences up to 450k bases, it achieves the best overall performance with nearly $20\times$ fewer effective tokens, and surpasses models with up to $985\times$ more activated parameters while tuning only 256k \emph{trainable} parameters.

Hongxin Xiang, Pengsen Ma, Yunkang Cao, Di Yu, Haowen Chen, Xinyu Yang, Xiangxiang Zeng• 2026

Related benchmarks

TaskDatasetResultRank
Subspecies GeneralizationRice japonica subspecies In-Domain
Accuracy59
3
Subspecies GeneralizationRice aus subspecies Near-OOD
Accuracy55.6
3
Subspecies GeneralizationRice rufipogon subspecies Mid-OOD
Accuracy63.9
3
Subspecies GeneralizationRice barthii subspecies Far-OOD
Accuracy60.8
3
Subspecies GeneralizationRice glaberrima subspecies Far-OOD
Accuracy59.9
3
Whole-genome Phenotype PredictionRice whole-genome phenotype dataset
TGW (g)2.952
3
Showing 6 of 6 rows

Other info

Follow for update