SCONE: A Practical, Constraint-Aware Plug-in for Latent Encoding in Learned DNA Storage

TL;DR

SCONE introduces a novel, integrated DNA encoding plug-in that directly compresses neural latent representations into DNA sequences while ensuring biochemical constraints are met, improving efficiency and simplicity.

Contribution

It presents a constraint-aware, single-step quaternary coding method that unifies latent compression and DNA encoding, enhancing DNA storage pipelines.

Findings

Achieves near-perfect constraint satisfaction in DNA sequences.

Maintains high compression efficiency with minimal computational overhead.

Provides a latent-agnostic interface for DNA-compatible neural codecs.

Abstract

DNA storage has matured from concept to practical stage, yet its integration with neural compression pipelines remains inefficient. Early DNA encoders applied redundancy-heavy constraint layers atop raw binary data - workable but primitive. Recent neural codecs compress data into learned latent representations with rich statistical structure, yet still convert these latents to DNA via naive binary-to-quaternary transcoding, discarding the entropy model's optimization. This mismatch undermines compression efficiency and complicates the encoding stack. A plug-in module that collapses latent compression and DNA encoding into a single step. SCONE performs quaternary arithmetic coding directly on the latent space in DNA bases. Its Constraint-Aware Adaptive Coding module dynamically steers the entropy encoder's learned probability distribution to enforce biochemical constraints - Guanine-Cytosine (GC) balance and homopolymer suppression - deterministically during encoding, eliminating post-hoc correction. The design preserves full reversibility and exploits the hyperprior model's learned priors without modification. Experiments show SCONE achieves near-perfect constraint satisfaction with negligible computational overhead (<2% latency), establishing a latent-agnostic interface for end-to-end DNA-compatible learned codecs.