Publications by authors named "Abrar Yaqoob"
Transforming Cancer Classification: The Role of Advanced Gene Selection.
Diagnostics (Basel)
November 2024
Accurate classification in cancer research is vital for devising effective treatment strategies. Precise cancer classification depends significantly on selecting the most informative genes from high-dimensional datasets, a task made complex by the extensive data involved. This study introduces the Two-stage MI-PSA Gene Selection algorithm, a novel approach designed to enhance cancer classification accuracy through robust gene selection methods.
View Article and Find Full Text PDFArticle Synopsis
- Breast cancer remains a major global health concern, with early detection complicated by the complex and high-dimensional nature of gene expression data.
- This study introduces a hybrid deep learning model utilizing Harris Hawk Optimization and Whale Optimization algorithms to enhance the selection of genetic features and improve detection accuracy using RNA-Seq data from breast cancer patients.
- Results showed the new model achieved a remarkable 99.0% classification accuracy, outperforming traditional optimization methods, indicating its potential for early detection and personalized treatment in breast cancer care.*
Article Synopsis
- - The study tackles the difficulty of identifying relevant biomarkers from complex cancer data, noting that traditional feature selection methods often fall short in accuracy and efficiency.
- - A new approach combining Random Drift Optimization (RDO) with XGBoost is proposed to improve cancer classification, resulting in better classification accuracy and biological insights into cancer progression.
- - Experimental results showed that the RDO-XGBoost framework outperformed popular classifiers across multiple cancer datasets, achieving high accuracy rates of over 95% in most cases, highlighting its effectiveness and potential for cancer data analysis.
Gene expression datasets offer a wide range of information about various biological processes. However, it is difficult to find the important genes among the high-dimensional biological data due to the existence of redundant and unimportant ones. Numerous Feature Selection (FS) techniques have been created to get beyond this obstacle.
View Article and Find Full Text PDF