Data mining of nanomaterials: Prediction of hemolytic activity

• Grant number: 25/05793-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: June 01, 2025
• End date: November 30, 2025
• Field of knowledge: Interdisciplinary Subjects
• Principal Investigator: Diego Stéfani Teodoro Martinez
• Grantee: Anna Karen de Oliveira Pinto
• Host Institution: Centro Nacional de Pesquisa em Energia e Materiais (CNPEM). Ministério da Ciência, Tecnologia e Inovação (Brasil). Campinas , SP, Brazil

Abstract

Nanomaterials have multiple functionalities due to their unique physicochemical properties. These properties are directly associated with biological effects, nanobiointeractions, and toxicity. Data mining and machine learning (ML) techniques are excellent tools for visualizing information and predicting the toxicity of nanomaterials. However, a robust predictive model and database that encompass all the parameters of the properties relevant to nanotoxicity are still lacking. In this project, we seek to create a specialized dataset that allows the development of a model to predict the hemolytic activity of nanomaterials through data mining and ML techniques. Toxicity tests of nanomaterials on red blood cells (hemolytic effect) will be systematically studied. To this end, we will curate published articles to identify parameters relevant to hemolysis; creating a structured dataset containing information on nanomaterial properties and exposure conditions relevant to toxicity in red blood cells. Next, predictive models will be designed to classify nanomaterials as hemolytic or non-hemolytic and predict the percentage of hemolysis. With this project, we aim to contribute to the application of the Safe by Design concept in nanotechnology using computational tools and applied computer science.