CTDN (Convolutional Temporal Based Deep- Neural Network): An Improvised Stacked Hybrid Computational Approach for
Davinder Paul Singh1, Baijnath Kaushik1
1School of Computer Science and Engineering, Shri Mata Vaishno Devi University, Katra 182320, Jammu and Kashmir, India.
Abstract:
The characterization of drug - metabolizing enzymes is a significant problem for customized therapy. It is important to choose the right drugs for cancer victims, and the ability to forecast how those drugs will react is usually based on the available information, genetic sequence, and structural properties. To the finest of our knowledge, this is the first study to evaluate optimization algorithms for selection of features and pharmacogenetics categorization using classification methods based on a successful evolutionary algorithm using datasets from the Cancer Cell Line Encyclopaedia (CCLE) and Genomics of Drug Sensitivity in Cancer (GDSC). The study proposes the uses of Firefly and Grey Wolf Optimization techniques for feature extraction, while comparing the traditional Machine Learning (ML), ensemble ML and Stacking Algorithm with the proposed Convolutional Temporal Deep Neural Network or CTDN. With the potential to increase efficiency from the suggested intelligible classifier model for a suggestive chemotherapeutic drugs response prediction, our study is important in particular for selecting an acceptable feature selection method. The comparison analysis demonstrates that the proposed model not only surpasses the prior state-of-the-art methods, but also uses Grey Wolf and Fire Fly Optimization to lessen multicollinearity and overfitting.
Insights
This study introduces novel optimization algorithms for feature selection in pharmacogenetics, improving cancer drug response prediction. The proposed methods enhance accuracy and reduce model complexity for personalized cancer therapy.
Area of Science:
- Bioinformatics
- Computational Biology
- Pharmacogenomics
Background:
- Accurate prediction of chemotherapeutic drug response is crucial for personalized cancer therapy.
- Characterizing drug-metabolizing enzymes and genetic variations aids in forecasting drug efficacy.
- Existing methods for feature selection and pharmacogenetic categorization require optimization.
Purpose of the Study:
- To evaluate optimization algorithms for feature selection in pharmacogenetics.
- To compare traditional and advanced machine learning models for predicting cancer drug response.
- To introduce a novel Convolutional Temporal Deep Neural Network (CTDN) model.
Main Methods:
- Utilized datasets from the Cancer Cell Line Encyclopaedia (CCLE) and Genomics of Drug Sensitivity in Cancer (GDSC).
- Employed Firefly and Grey Wolf Optimization techniques for feature extraction.
- Compared traditional Machine Learning (ML), ensemble ML, Stacking Algorithm, and the proposed CTDN model.
Main Results:
- The proposed CTDN model, enhanced by Firefly and Grey Wolf Optimization, outperformed existing state-of-the-art methods.
- Optimization algorithms effectively reduced multicollinearity and overfitting in the models.
- The study demonstrated improved efficiency in predicting chemotherapeutic drug response.
Conclusions:
- Novel optimization algorithms significantly enhance feature selection for pharmacogenetic categorization.
- The CTDN model offers a promising approach for accurate and efficient prediction of cancer drug response.
- This research contributes to advancing personalized medicine through improved computational drug response prediction.
More Related Videos
09:53Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
Published on: August 16, 2020
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Related Concept Videos
02:50Combination Therapies and Personalized Medicine
The combination of the drug acetazolamide and sulforaphane is a good example of combination therapy to treat cancer. The cells in the interior of a large tumor often die due to the hypoxic and...
01:21Cancer Survival Analysis
02:53Adaptive Mechanisms in Cancer Cells
Some of the advantages that cancer cells have on normal cells include - enhanced ability to divide without terminally differentiating, induce new blood vessel formation,...