Cloud-Accelerated Personalized Cancer Treatment Prediction Using Adaptive Quantum-Inspired Evolutionary Algorithm and Graph Neural Networks
Abstract
Personalized cancer treatment prediction is a critical challenge in precision oncology, requiring the integration of high-dimensional genomic and clinical data to predict patientspecific treatment outcomes. This white paper presents a novel cloud-accelerated framework for predicting chemotherapy response in breast cancer patients using the Cancer Genome Atlas (TCGA-BRCA) dataset. We propose an adaptive Quantum-Inspired Evolutionary Algorithm (QIEA) for feature selection that dynamically adjusts to patient subgroups, coupled with a Graph Neural Network (GNN) for classification. By leveraging Amazon Web Services (AWS) SageMaker for distributed computing and AWS Lambda for real-time inference, our framework achieves an approximate 7× speedup compared to local execution while maintaining high predictive accuracy. This approach not only accelerates computation but also enables interpretable, real-time predictions, paving the way for scalable and personalized cancer care in clinical settings.
Read the paper
Related studies
- In silico toxicology protocols
- QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
- Quantum Informed Machine-Learning Potentials for Molecular Dynamics Simulations of CO2's Chemisorption and Diffusion in Mg-MOF-74
- In-silico strategies in nano-drug design: Bridging nanomaterials and pharmacological applications
- mRNA codon optimization with quantum computers
- The computational power of the human brain
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.