OCR: OmniNet-Fusion: A Hybrid Attention-Based CNN-RNN Model for Multi-Omics Integration in Precision Cancer Drug Response Prediction DOI

Syed Mohammed Azmal,

Sajja Tulasi Krishna

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 16, 2025

Abstract The increasing complexity of cancer treatment necessitates advanced computational models for accurate drug response prediction. OmniNet-Fusion (OCR) is a hybrid deep learning model designed to integrate multi-omics data—genomics, transcriptomics, proteomics, and metabolomics—enhancing precision medicine. leverages Convolutional Neural Network (CNN) analyze spatial omics data Recurrent (RNN) process sequential data, with an attention mechanism highlighting crucial features across layers. To optimize predictive accuracy, feature selection techniques such as Lasso regression mutual information filtering are utilized, while Principal Component Analysis (PCA) reduces dimensionality, ensuring efficiency. undergoes evaluation using key performance metrics, including precision, recall, F1-score, AUC-ROC, demonstrating superior over existing methods. By integrating fusion learning, OCR enhances biological interpretability facilitates personalized treatment. This approach not only improves prediction but also provides deeper insights into mechanisms, supporting oncology advancing AI-driven therapy.

Language: Английский

OCR: OmniNet-Fusion: A Hybrid Attention-Based CNN-RNN Model for Multi-Omics Integration in Precision Cancer Drug Response Prediction DOI

Syed Mohammed Azmal,

Sajja Tulasi Krishna

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 16, 2025

Abstract The increasing complexity of cancer treatment necessitates advanced computational models for accurate drug response prediction. OmniNet-Fusion (OCR) is a hybrid deep learning model designed to integrate multi-omics data—genomics, transcriptomics, proteomics, and metabolomics—enhancing precision medicine. leverages Convolutional Neural Network (CNN) analyze spatial omics data Recurrent (RNN) process sequential data, with an attention mechanism highlighting crucial features across layers. To optimize predictive accuracy, feature selection techniques such as Lasso regression mutual information filtering are utilized, while Principal Component Analysis (PCA) reduces dimensionality, ensuring efficiency. undergoes evaluation using key performance metrics, including precision, recall, F1-score, AUC-ROC, demonstrating superior over existing methods. By integrating fusion learning, OCR enhances biological interpretability facilitates personalized treatment. This approach not only improves prediction but also provides deeper insights into mechanisms, supporting oncology advancing AI-driven therapy.

Language: Английский

Citations

0