Work

High Data Quality Enhances Microplastic Toxicity Prediction

Year: 2026

Type: preprint

Abstract: Unlike chemicals, microplastics (MPs) lack standardized identifiers, limiting the applicability of traditional predictive ecotoxicology methods such as quantitative structure-activity relationship (QSAR) models. This study aimed to predict MP toxicity using MP properties, MP concentration, organismal traits, endpoints, and experimental design, and to evaluate how data pre-processing, dataset size, and quality influence model performance. We applied the Boosted Regression Tree (BRT) machine learning algorithm to four datasets derived from the Toxicity of Microplastics Explorer database (ToMEx 2.0): (i) imputed missing values, (ii) complete-case (missing values removed), (iii) high-quality data, and (iv) low-quality data. The high-quality dataset yielded the best final predictions for both random cross-validation (AUC = 0.93) and blocked cross-validation by particle identifier (AUC = 0.87). Explainable artificial intelligence (xAI) analyses showed that predictive performance was primarily determined by endpoints and concentration, with MP properties contributing despite limited reporting. Our findings demonstrate the feasibility of machine learning to predict and identify key drivers of MP toxicity, highlighting that high-quality data improves predictive performance while reducing data mining and computational costs. Standardized experiments, detailed MP characterization, and high reporting standards would better support risk assessment frameworks and inform the design of safer materials.

DOI: 10.32942/x2c96d

Authors: Ana Antonio Vital, Scott Coffin, Andrea Bonisoli-Alquati, Maaike Vercauteren, Luan de Souza Leite, Maximilian Pichler, Magdalena Mair

Institutions: University of Bayreuth, State of California, California State Polytechnic University, Ghent University, Universidade Estadual de Campinas (UNICAMP), University of Regensburg

Language: English

Topic: Microplastics and Plastic Pollution

Subfield: Pollution

Field: Environmental Science

Domain: Physical Sciences

Open Access status: green

Funders: Deutsche Forschungsgemeinschaft, Fundação de Amparo à Pesquisa do Estado de São Paulo

Awards: G3961440842, Fate and impacts of microplastics and pesticides in aquatic and terrestrial matrices in agricultural contexts, SFB 1357: MIKROPLASTIK – Gesetzmäßigkeiten der Bildung, des Transports, des physikalischchemischen Verhaltens sowie der biologischen Effekte: Von Modell zu komplexen Systemen als Grundlage neuer Lösungsansätze

OpenAlex ID: W7140102910

Cites: 51

Cited by:

Related to: 10