Related Experiment Video
Updated: Sep 12, 2025
10:58
Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules
Published on: July 25, 2013
17.2K
De Novo Design of Multiple Microplastic-Binding Peptides with a Protein Language Model-Guided Generative Adversarial
Siyuan Wang1, Michael T Bergman2, Carol K Hall2
1College of Engineering, Cornell University, Ithaca, New York 14853, United States.
Journal of Chemical Information and Modeling
|August 6, 2025
Summary
Researchers developed an AI framework to design novel peptides that bind to multiple types of microplastics. This breakthrough offers a promising eco-friendly solution for detecting and capturing diverse plastic pollutants.
Area of Science:
- Environmental Science
- Biotechnology
- Materials Science
Background:
- Microplastics are pervasive pollutants with significant ecological and health risks.
- Current mitigation strategies are insufficient, and eco-friendly solutions are needed.
- Plastic-binding peptides offer a potential method for microplastic detection and capture.
Purpose of the Study:
- To develop a generalizable AI-driven framework for de novo design of plastic-binding peptides.
- To create peptides with high affinity for multiple types of plastics, addressing real-world pollution complexity.
- To engineer peptides capable of binding to polyethylene, polypropylene, and poly(ethylene terephthalate).
Main Methods:
- Integration of a pretrained protein language model (PLM) with a generative adversarial network (GAN).
- Fine-tuning the PLM on biophysical modeling data (PepBD algorithm) for accurate peptide-plastic adsorption predictions.
- Utilizing a modular split-training strategy for the GAN to ensure stability, diversity, and optimization of multi-plastic binding.
Main Results:
- Designed peptides demonstrate high affinity for multiple plastics, including polyethylene, polypropylene, and poly(ethylene terephthalate).
- Molecular dynamics simulations confirm strong multi-plastic binding, with significantly improved adsorption free energies compared to previous methods.
- One designed peptide exhibits exceptionally high affinity for both polyethylene and polypropylene.
Conclusions:
- The AI-driven framework is effective for designing high-affinity, multi-plastic-binding peptides.
- This approach holds significant potential for developing innovative solutions to microplastic pollution.
- The methodology can be applied to broader peptide engineering applications beyond microplastics.
