MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541123019 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'machine learning framework for predicting nanoparticle-drug interactions.'
Inventor(s) include Somasundaram S. K.; Shashwat Bhatnagar; Vaishnavi Awasthi; and Aman Singh.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a system for predicting nanoparticle-drug interactions. The system includes a data preprocessing module configured to process experimental data including physicochemical properties of nanoparticles and pharmaceutical compounds, where properties include particle size, zeta potential, exposure concentration, exposure time, polymer type, and source. The system includes a machine learning module having multiple algorithms including a logistic regression classifier with L2 regularization configured to identify significant features, an XGBoost classifier configured to model non-linear relationships using ensemble learning, and a GraphSAGE neural network configured to represent interactions as a graph network and capture dependencies through node embeddings. The system includes an evaluation module configured to assess performance using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve metrics. The system architecture (FIG. 1) demonstrates modular integration of DatasetLoader, FeatureEngineer, StatisticalAnalyzer, PCAReducer, and XGBoostClassifier components for toxicity prediction."
Disclaimer: Curated by HT Syndication.
