Spatial Transcriptomics and Adaptive Multi-Modal Ensemble Encoding: Early Metastasis Profiling and Targeting
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Lung cancer remains the leading cause of cancer-related mortality, primarily due to its high metastatic potential and the difficulty of early metastasis detection.Current clinical approaches rely on low-sensitivity assessments and can also cause complications.To address these challenges, this project introduces a computational framework that predicts metastatic potential directly from the primary tumor site, thereby eliminating the need for secondary site biopsies and enabling earlier intervention.This framework leverages spatial transcriptomics, a cutting-edge technology that maps tumor tissue, capturing cellular interactions that are missed by traditional methods.By analyzing the spatial and molecular features of primary tumors, this system identifies high-risk tumor regions and key metastatic drivers, integrating neural networks, autoencoders, and unsupervised clustering.Insilico validation aligned the received outputs with known signatures from open datasets.Building on these findings, a deep learning-guided lipid nanoparticle optimization pipeline was developed to design drug carriers for siRNA, aiming to silence the inhibition of genetic pathways.Further supervised analysis and validation revealed the heightened properties of the enhanced carriers.This study bridges AI-driven metastasis prediction and treatment with precision nanomedicine for metastatic cancer at its earliest stages by shifting from late-stage intervention to proactive, gene-targeted suppression.
Fields of Study & Subjects
Single-cell and spatial transcriptomics
Gene expression and cancer classification
AI in cancer detection
Publication details
- Journal / source
- International journal of high school research
- Volume
- 8
- Issue
- 5
- Pages
- 1–10
- Publication date
- 31 March 2026
- Language
- EN