Gene Expression Analysis Using Machine Learning : A Multi-Dataset Approach

The expression levels of a fraction of the genes directly control the regulatory or functional activities inside the cell. Individual gene activity is recorded in gene expression, which helps reveal underlying cellular dynamics. High-throughput investigations require grouping genes based on their temporal expression patterns, often achieved using unsupervised machine learning methods. The majority of clustering methods, however, either need to account for the temporal structure of the data or suffer from gene expression that needs to be longer in duration. The hierarchical framework can resolve these problems we suggest in this research, a revolutionary learning-based system for grouping known as Random Forest (RF), Naïve Bayes (NB) and C4.5. The anticipated model first transforms the data to provide richer data representations. For the created images, a deep network classifier is then used. Compared to frequently employed algorithms, the proposed classifiers' assessment show that this new paradigm is useful for prediction and classification. Keywords- Gene Expression, Prediction, Classification, Accuracy, Data Representation