DNA Methylation Prediction Using Reduced Features Obtained via Gappy Pair Kernel and Partial Least Square

Shah, Sayyar Ali; Rahman, Altaf Ur; Jabeen, Sadia; Khan, Ahmad Neyaz; Khan, Fiaz Gul; ElAffendi, Mohammed

doi:10.1109/access.2022.3174260

Cited by 1 publication

(2 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It identifies the principal components, which are the directions of maximum variance, and represents the data in terms of these components. PCA has been extensively applied in genomics for tasks such as visualizing high-dimensional gene expression data, identifying patterns and sources of variation, and reducing dimensionality as a pre-processing step for downstream analyses [12].…”

Section: Machine Learning Techniques For Feature Reductionmentioning

confidence: 99%

“…SVMs handle nonlinear decision boundaries via the kernel trick, result in sparse solutions for computational efficiency, and have been extensively used in genomics for tasks like gene expression analysis, protein structure prediction, and disease risk prediction due to their ability to handle high-dimensional data, robustness to noise, and capturing complex non-linear relationships. They are particularly well-suited for classification tasks, including binary classification problems prevalent in genomics [12] [13].…”

Section: Predictive Modeling and Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Techniques and Hybrid Feature Selection Methods for Efficient Prediction of Cancer

2024

IJSREM

View full text Add to dashboard Cite

The high-dimensional genomic data presents significant challenges, and traditional analytical methods often struggle to capture the complex, non-linear relationships within these datasets. This study elaborates into the application of machine learning methods for dimensionality reduction and predictive modeling of binary phenotypes using gene expression data. Various dimensionality reduction techniques are explored, including t-distributed stochastic neighbor embedding (t-SNE), Non-negative matrix factorization (NMF), Principal component analysis (PCA), and manifold learning methods. Additionally, various algorithms such as logistic regression, random forests, support vector machines (SVMs)cand naive Bayes models are evaluated for predicting phenotypes. The study employs rigorous cross-validation, permutation testing, and evaluation metrics like the Matthews Correlation Coefficient (MCC) to assess model performance. The study rigorously assesses current genomics strategies, pinpointing their drawbacks and suggesting areas for future investigation, while delving into the potential of machine learning to overcome these hurdles and offer valuable insights in genomics. Keywords- Gene Expression , Dimensionality Reduction, Biomarkers, Cancer Prediction, Epigenetics, Machine Learning, Feature extraction.

show abstract

Section: Machine Learning Techniques For Feature Reductionmentioning

confidence: 99%

Section: Predictive Modeling and Evaluationmentioning

confidence: 99%