Large-scale AI-guided discovery of antifreeze peptides reveals functional tandem-repeat architectures
- 1Beijing Key Laboratory of Artiffcial Intelligence for Advanced Chemical Engineering Materials, State Key Laboratory of Chemical Engineering and Low-Carbon Techn
Abstract
Despite growing demand for biocompatible materials that regulate ice crystallization in cryopreservation, antifreeze peptide discovery remains constrained by limited candidate sequence diversity and reliance on known protein scaffolds. Here, we establish an AI-guided discovery framework integrating multimodal antifreeze protein prediction, generative sequence expansion and local sequence-pattern analysis. AFPFusionLM combines protein sequence and structure-aware representations, achieving an AUROC of 0.937 and an AUPRC of 0.957 on an independent reference set. Antifreeze-domain-adapted protein sequence generation and multimodel consensus screening of UniProt, glacier metagenomes and generated sequences yielded 87,305 candidate protein records. Large-scale sequence analysis revealed recurring periodic sequence architectures across multiple candidate protein clusters, enabling the identification of short-peptide families with shared repeat features and their natural variants. Experimental evaluation revealed ice recrystallization inhibition activity in multiple peptides from repeat-associated families, with inhibitory effects comparable to or greater than those of reference peptides reported in the literature. Cell-based experiments using a representative peptide-containing formulation also supported its cryoprotective potential under reduced-DMSO conditions. These findings show that large-scale sequence exploration can reveal function-associated peptide sequence architectures, providing a research framework for the systematic discovery and subsequent optimization of antifreeze peptides.
Related
- Deterministic DNA-first discovery reveals recurrent genomic architectures
- Genomic taxonomy reveals distinct evolutionary architectures within the Enterobacter cloacae complex
- Venom composition of the ant Tetraponera rufonigra reveals insights into the evolution of dimeric ant venom peptides
- Autonomous AI-Driven Nanoscale Spatial Mapping Reveals Novel Targets and Ternary Architectures in 5xFAD Alzheimer's Disease Model
- Long-distance RNA–RNA interactions shape dynamic RNA architectures and functional states in plant positive-strand RNA viruses
BibTeX
@misc{li2026largescale,
title = {{Large-scale AI-guided discovery of antifreeze peptides reveals functional tandem-repeat architectures}},
author = {Y. Li and C. Wang and J. Liu and M. Song and L. Zhang and S. Sun and W. Li and J. Qiu and Y. Qin and J. Yao and L. Zhao and H. Yu and X. Wang},
howpublished = {bioRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.03.763275},
url = {https://www.biorxiv.org/content/10.64898/2026.11.03.763275v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Large-scale AI-guided discovery of antifreeze peptides reveals functional tandem-repeat architectures
AU - Y. Li
AU - C. Wang
AU - J. Liu
AU - M. Song
AU - L. Zhang
AU - S. Sun
AU - W. Li
AU - J. Qiu
AU - Y. Qin
AU - J. Yao
AU - L. Zhao
AU - H. Yu
AU - X. Wang
PY - 2026
DA - 2026/11/03
PB - bioRxiv
DO - 10.64898/2026.11.03.763275
UR - https://www.biorxiv.org/content/10.64898/2026.11.03.763275v1
AB - Despite growing demand for biocompatible materials that regulate ice crystallization in cryopreservation, antifreeze peptide discovery remains constrained by limited candidate sequence diversity and reliance on known protein scaffolds. Here, we establish an AI-guided discovery framework integrating multimodal antifreeze protein prediction, generative sequence expansion and local sequence-pattern analysis. AFPFusionLM combines protein sequence and structure-aware representations, achieving an AUROC of 0.937 and an AUPRC of 0.957 on an independent reference set. Antifreeze-domain-adapted protein sequence generation and multimodel consensus screening of UniProt, glacier metagenomes and generated sequences yielded 87,305 candidate protein records. Large-scale sequence analysis revealed recurring periodic sequence architectures across multiple candidate protein clusters, enabling the identification of short-peptide families with shared repeat features and their natural variants. Experimental evaluation revealed ice recrystallization inhibition activity in multiple peptides from repeat-associated families, with inhibitory effects comparable to or greater than those of reference peptides reported in the literature. Cell-based experiments using a representative peptide-containing formulation also supported its cryoprotective potential under reduced-DMSO conditions. These findings show that large-scale sequence exploration can reveal function-associated peptide sequence architectures, providing a research framework for the systematic discovery and subsequent optimization of antifreeze peptides.
ER -