DeepSAP: an integrated generative and predictive deep-learning framework for controllable design of self-assembling peptides.
- 1MOE Key Laboratory of Laser Life Science & Institute of Laser Life Science, College of Biophotonics, School of Optoelectronic Science and Engineering, South China Normal University, Guangzhou 510631, China.
- 2Guangdong Provincial Key Laboratory of Laser Life Science, Guangzhou Key Laboratory of Spectral Analysis and Functional Probes, College of Biophotonics, School of Optoelectronic Science and Engineering, South China Normal University, Guangzhou 510631, China.
Abstract
Motivation
Self-assembling peptides (SAPs), particularly short sequences whose amino acid composition dictates their spontaneous organization, are emerging as versatile building blocks in biomedicine and bio-optoelectronic materials. As the thermodynamic and kinetic behaviours of peptide self-assembly are affected by intrinsic factors, such as amino acid sequence, length, and hydrophobicity, the controllable design of SAPs with tailored properties is essential to achieve specific structures and functions for various application scenarios. However, existing computational approaches, which primarily focus on prediction or heuristic screening, lack conditional generative capability of SAPs.Results
We present DeepSAP, an end-to-end framework integrating conditional peptide generation with predictive screening for property-guided design of SAPs. By pretraining on large-scale peptide datasets and fine-tuning on limited SAP-specific data, the generative SAPGEN model transfers general sequence knowledge to the SAPs domain, enabling the conditional generation of SAPs in low-data regimes. Subsequently, we constructed a lightweight predictive model, SAPBRF, to further screen the generated peptides. Comparative analyses demonstrated that SAPGEN enabled reliable and precise control of the physicochemical properties of the generated sequence, outperformed baseline generative models in terms of efficiency and quality across multiple design tasks. The SAPBRF predictor achieved efficient and accurate screening with high predictive performance. Finally, the complete DeepSAP framework demonstrated strong generalization under unseen physicochemical regimes, where peptides generated and screened by the pipeline consistently exhibited stable self-assembly behaviour, as further verified by molecular dynamics simulations. Our findings indicate that DeepSAP enables the conditional generation of SAPs with desired properties, holding the potential for tailored design of functional biomaterials.Availability and implementation
Source code for the DeepSAP model training and evaluation is available at: https://github.com/Paul-hihihopes/Deep_SAP_Design and at DOI: 10.5281/zenodo.21522690.
Related
- Integrating Predictive and Generative Capabilities by Latent Space Design via the DKL-VAE Model
- GenGLem as a generative framework for capturing chemical cliffs in energetic materials
- A predictive transferability index for crystal plasticity framework selection: Variational derivation, analytical bounds, and FFT-based plausibility assessment
- Interfacial Mechanisms of Reactive Dye Adsorption on a Waste-Cotton Derived PVA/TiO2/Cellulose Biofilm: A Molecular Dynamics and Physics-Informed Predictive Framework
- Water-soluble and self-assembling DAN & NDI based peptide aromatic oligomers
BibTeX
@article{song2026deepsap,
title = {{DeepSAP: an integrated generative and predictive deep-learning framework for controllable design of self-assembling peptides.}},
author = {Yuanming Song and Yuhan Wu and Yuqiu Jiang and Li He and Shoubo Zhao and Xiaoyuan Deng},
journal = {Bioinformatics (Oxford, England)},
year = {2026},
month = oct,
doi = {10.1093/bioinformatics/btag744},
url = {https://europepmc.org/article/MED/42841737},
note = {CC BY},
}
RIS
TY - JOUR
TI - DeepSAP: an integrated generative and predictive deep-learning framework for controllable design of self-assembling peptides.
AU - Yuanming Song
AU - Yuhan Wu
AU - Yuqiu Jiang
AU - Li He
AU - Shoubo Zhao
AU - Xiaoyuan Deng
PY - 2026
DA - 2026/10/01
JO - Bioinformatics (Oxford, England)
DO - 10.1093/bioinformatics/btag744
UR - https://europepmc.org/article/MED/42841737
AB - Motivation Self-assembling peptides (SAPs), particularly short sequences whose amino acid composition dictates their spontaneous organization, are emerging as versatile building blocks in biomedicine and bio-optoelectronic materials. As the thermodynamic and kinetic behaviours of peptide self-assembly are affected by intrinsic factors, such as amino acid sequence, length, and hydrophobicity, the controllable design of SAPs with tailored properties is essential to achieve specific structures and functions for various application scenarios. However, existing computational approaches, which primarily focus on prediction or heuristic screening, lack conditional generative capability of SAPs.Results We present DeepSAP, an end-to-end framework integrating conditional peptide generation with predictive screening for property-guided design of SAPs. By pretraining on large-scale peptide datasets and fine-tuning on limited SAP-specific data, the generative SAPGEN model transfers general sequence knowledge to the SAPs domain, enabling the conditional generation of SAPs in low-data regimes. Subsequently, we constructed a lightweight predictive model, SAPBRF, to further screen the generated peptides. Comparative analyses demonstrated that SAPGEN enabled reliable and precise control of the physicochemical properties of the generated sequence, outperformed baseline generative models in terms of efficiency and quality across multiple design tasks. The SAPBRF predictor achieved efficient and accurate screening with high predictive performance. Finally, the complete DeepSAP framework demonstrated strong generalization under unseen physicochemical regimes, where peptides generated and screened by the pipeline consistently exhibited stable self-assembly behaviour, as further verified by molecular dynamics simulations. Our findings indicate that DeepSAP enables the conditional generation of SAPs with desired properties, holding the potential for tailored design of functional biomaterials.Availability and implementation Source code for the DeepSAP model training and evaluation is available at: https://github.com/Paul-hihihopes/Deep_SAP_Design and at DOI: 10.5281/zenodo.21522690.
SN - 1367-4803
SN - 1367-4811
ER -