RiboGRAM learns multi-scale non-coding RNA grammar for structural and regulatory inference
- 1Heidelberg University
Abstract
Protein-coding sequences are read through the triplet genetic code, whereas the organization of molecular information within non-coding RNA sequences remains elusive. Here, we identify a non-coding RNA grammar defined by multi-scale motif usage and 5'-to-3' positional gradients, and develop RiboGRAM to learn this organization. Across nine organisms, non-coding RNAs showed scale-dependent divergence from coding sequences, with directional U-rich and AU-rich gradients. Integrating multi-scale sequence encoding with contextual modeling, RiboGRAM organized RNA families, revealing motif-associated and pair-like patterns across layers. Without structural supervision, non-coding RNA pretraining improved base-pair recovery over coding or messenger RNA pretraining, with representations supporting alignment-free diffusion-based 3D modeling of short RNAs. In human RNA-protein binding profiles, RiboGRAM identified position-resolved motif organization across protein targets and cell types, with sequence-preference shifts associated with reduced cross-cell transferability. Together, these results establish a learnable grammar of non-coding RNA sequence organization for structural and regulatory inference.
Related
- A foundation model learns the sequence and functional grammar of fully human heavy-chain-only antibodies
- ChAI-Net learns a regulatory code for chromatin co-accessibility
- Decoding super-enhancer regulatory grammar and pathogenic gain-of-function variants directly from DNA sequence
- A massively parallel synthetic gene atlas for learning compact cis-regulatory grammar across cellular contexts
- Where single-cell foundation models help: a benchmark of annotation, perturbation and regulatory inference against simple baselines
BibTeX
@misc{wang2026ribogram,
title = {{RiboGRAM learns multi-scale non-coding RNA grammar for structural and regulatory inference}},
author = {H. Wang and Z. Chen and H. Huang and S. Li and A. Jäschke and Q. Ye and Y. Zhang},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.12.758266},
url = {https://www.biorxiv.org/content/10.64898/2026.10.12.758266v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - RiboGRAM learns multi-scale non-coding RNA grammar for structural and regulatory inference
AU - H. Wang
AU - Z. Chen
AU - H. Huang
AU - S. Li
AU - A. Jäschke
AU - Q. Ye
AU - Y. Zhang
PY - 2026
DA - 2026/10/12
PB - bioRxiv
DO - 10.64898/2026.10.12.758266
UR - https://www.biorxiv.org/content/10.64898/2026.10.12.758266v1
AB - Protein-coding sequences are read through the triplet genetic code, whereas the organization of molecular information within non-coding RNA sequences remains elusive. Here, we identify a non-coding RNA grammar defined by multi-scale motif usage and 5'-to-3' positional gradients, and develop RiboGRAM to learn this organization. Across nine organisms, non-coding RNAs showed scale-dependent divergence from coding sequences, with directional U-rich and AU-rich gradients. Integrating multi-scale sequence encoding with contextual modeling, RiboGRAM organized RNA families, revealing motif-associated and pair-like patterns across layers. Without structural supervision, non-coding RNA pretraining improved base-pair recovery over coding or messenger RNA pretraining, with representations supporting alignment-free diffusion-based 3D modeling of short RNAs. In human RNA-protein binding profiles, RiboGRAM identified position-resolved motif organization across protein targets and cell types, with sequence-preference shifts associated with reduced cross-cell transferability. Together, these results establish a learnable grammar of non-coding RNA sequence organization for structural and regulatory inference.
ER -