Implementation of a Hybrid Deep Learning System for Anti- Drug Response Prediction Using Genetic Sequencing Data

DOI

https://www.doi.org/10.59256/indjcst.20260501076

Published In

Volume 5, Issue 1 (2026)

Published Online

January-April 2026

Pages

641-648

Article Type

Original Article

Check for updates

Predicting anti-drug response (ADR) plays a crucial role in advancing personalized medicine, as patients often react differently to the same treatment due to genetic differences. Traditional methods are unable to accurately capture the complex relationship between drug compounds and genetic data, leading to ineffective treatments and harmful side effects. To address this issue, this paper presents the design and implementation of a deep learning-based system for predicting anti-drug response using genetic sequencing data. The proposed system uses a hybrid deep learning approach that combines Graph Convolutional Networks (GCNs) to extract structural features from drug molecules and 1D Convolutional Neural Networks (1D-CNNs) to analyze high-dimensional genomic sequences. These models are integrated into a single framework that learns complex interactions between drug properties and patient-specific genetic profiles. The system is designed with a user-friendly interface that allows efficient input of genomic and drug data, and provides prediction outputs indicating drug sensitivity or resistance. The implementation includes data preprocessing, feature extraction, model training, and prediction modules, ensuring accurate and efficient performance. Experimental results show that the proposed system improves prediction accuracy compared to traditional single-model approaches. This tool can assist healthcare rofessionals in selecting effective treatments, reducing negative drug reactions, and supporting data-driven medical decision-making. In general, the advanced framework highlights the potential of deep learning techniques in transforming drug response prediction and contributes to the advancement of precision medicine.