Related Experiment Video
Updated: Aug 1, 2026
Polymalic Acid-based Nano Biopolymers for Targeting of Multiple Tumor Markers: An Opportunity for Personalized Medicine?
Published on: June 13, 2014
Hybrid deep learning technique for COX-2 inhibition bioactivity detection against breast cancer disease
Sahebrao B Pawar1, N K Deshmukh1, Sharad B Jadhav1
1School of Computational Sciences, Swami Ramanand Teerth, Marathvada University, Nanded, India.
Abstract:
This study addresses detecting COX-2 inhibition in breast cancer, targeting its role in tumor growth. The primary goal is to develop an efficient technique for precise COX-2 inhibition bioactivity detection, with implications for identifying anti-cancer compounds and advancing breast cancer therapies. The proposed methodology uses the UNet architecture for feature extraction, enhancing accuracy. A modified chicken swarm optimization (MCSO) algorithm addresses data dimensionality, optimizing features. An improved Laguerre neural network (ILNN) classifies COX-2 inhibition bioactivity. Validation is performed using the ChEMBL database. The research evaluates the accuracy, precision, recall, F-measure, Matthews' correlation coefficient (MCC), and Dice coefficient of the proposed method. These metrics are compared against those of contemporary methods to assess the efficiency and effectiveness of the developed technique. The study underscores the hybrid deep learning method's significance in accurately detecting COX-2 inhibition bioactivity against breast cancer. Results highlight its potential as a valuable tool in breast cancer drug discovery.
Insights
This study introduces a hybrid deep learning method for detecting cyclooxygenase-2 (COX-2) inhibition in breast cancer. The technique accurately identifies potential anti-cancer compounds, aiding breast cancer drug discovery.
Area of Science:
- Biomedical Engineering
- Computational Biology
- Oncology
Background:
- Cyclooxygenase-2 (COX-2) plays a role in breast cancer tumor growth.
- Accurate detection of COX-2 inhibition is crucial for developing targeted therapies.
- Existing methods may lack efficiency in identifying bioactive compounds.
Purpose of the Study:
- To develop an efficient and precise technique for detecting COX-2 inhibition bioactivity.
- To identify potential anti-cancer compounds for breast cancer treatment.
- To advance breast cancer therapies through improved drug discovery tools.
Main Methods:
- Utilized the UNet architecture for enhanced feature extraction.
- Employed a modified chicken swarm optimization (MCSO) algorithm for feature optimization and dimensionality reduction.
- Implemented an improved Laguerre neural network (ILNN) for classifying COX-2 inhibition bioactivity.
- Validated the method using the ChEMBL database.
Main Results:
- The proposed hybrid deep learning method demonstrated high accuracy in detecting COX-2 inhibition bioactivity.
- Performance was evaluated using metrics including accuracy, precision, recall, F-measure, MCC, and Dice coefficient.
- Comparative analysis showed the method's effectiveness against contemporary techniques.
Conclusions:
- The hybrid deep learning approach offers a significant advancement in accurately detecting COX-2 inhibition bioactivity.
- This method shows strong potential as a valuable tool in breast cancer drug discovery.
- The findings support the development of novel anti-cancer compounds targeting COX-2.
