Work

LLM-guided prediction of riboswitch–ligand binding affinity under data-limited conditions

Year: 2026

Type: article

Abstract: Riboswitches are RNA regulatory elements that sense small molecules and regulate gene expression through ligand-induced conformational changes in an aptamer domain. They enable synthetic biology applications such as biosensing and gene circuit design. Accurate prediction of riboswitch–ligand binding affinity, quantified by the dissociation constant (K d ), is essential for rational riboswitch engineering. We present a neuro-symbolic framework in which LLM-derived embeddings encode riboswitch sequences, secondary structures, and ligand representations into a unified representation that captures riboswitch–ligand interaction context, while domain-informed rules encode explicit biochemical priors. Despite limited labeled data, this framework achieves strong predictive performance and improved data efficiency. It predicts min–max log-scaled pK d values and supports binary classification of binding strength, particularly by mitigating systematic overestimation of affinity. More broadly, the results suggest that LLM-based neuro-symbolic representations provide an effective route for modeling riboswitch–ligand interactions under data-limited conditions.

Source: New Biotechnology

DOI: 10.1016/j.nbt.2026.08.008

Authors: Sunggi An, Sofia Mun, Yousung Jung, Hyun Uk Kim

Institutions: Korea Advanced Institute of Science and Technology, Seoul National University, Institute of Engineering Research

Language: English

Topic: RNA and protein synthesis mechanisms

Subfield: Molecular Biology

Field: Biochemistry, Genetics and Molecular Biology

Domain: Life Sciences

Open Access status: gold

Estimated APC paid: $3,670

Funders: National Research Foundation, National Research Foundation of Korea