0
Systematic Review ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 1 ? Systematic review or meta-analysis. Synthesizes findings across many studies. Strongest evidence. Environmental Sources Remediation Sign in to save

Integrating Genomic and Proteomic Data Using Machine Learning for Plastic Biodegradation: A Systematic Review

NIPES Journal of Science and Technology Research 2025
Olamma Iheanetu, Akinyemi Priscilla

Summary

This systematic review summarizes how machine learning and genomic data are being used to identify microbes and enzymes that can break down plastic waste. The research is significant for microplastic concerns because discovering more effective biological degradation pathways could provide a natural solution for reducing the microplastic pollution that accumulates in our environment and bodies.

Study Type Review

Plastic waste remains a major environmental concern, and although microbial and enzymatic degradation offer eco-friendly solutions, their effectiveness is limited by microbial diversity and polymer complexity. This systematic review examined 15 studies (2021–2025) using machine learning models; such as Random Forest, SVM, XGBoost, and protein language models—applied to genomic and/or proteomic data to predict plastic biodegradation. Major plastics included PET, PE, PU, and PLA. Studies integrating multi-omics data consistently outperformed single-omics approaches, with up to 25% gains in prediction accuracy. Validation methods ranged from in vitro assays to in silico docking and field trials. While challenges remain in translating predictions into real-world applications, ML-guided multi-omics integration holds strong potential for accelerating the discovery of effective biological solutions to plastic pollution.

Share this paper