I am currently working on a research paper focused on gene classification using data obtained from Next Generation Sequencing (NGS). I am particularly interested in understanding which machine learning algorithms are most effective for this purpose and how to preprocess NGS data for optimal results. Additionally, any advice on feature selection and model validation specific to genomics would be highly appreciated. If you have experience in this area or can point me to relevant studies, I'd be grateful for your insights.
I am not an expert in this field, but I am very interested and have researched to find an answer. I received some assistance from tlooto.com for this response. Could you please review the response below to see if it is correct?
To classify genes using NGS data with machine learning, start with quality control to filter out low-quality reads and normalize the data using TPM or RPKM [1][8]. Apply dimensionality reduction techniques such as PCA or t-SNE to handle high-dimensional data [1][6]. For feature selection, prioritize biologically relevant genes and use statistical tests like ANOVA, as well as regularization techniques like LASSO [5][9]. Effective algorithms include Random Forest, SVM, neural networks, and XGBoost [3][7]. Validate models using k-fold cross-validation and metrics like accuracy and F1-score [4][10]. Optimize performance through hyperparameter tuning and consider ensemble methods [4][7]. Ensure results are biologically interpretable by examining feature importance and model coefficients [2][6].
Reference
[1] Pezoulas, V., Hazapis, O., Lagopati, N., Exarchos, T., Goules, A., Tzioufas, A., Fotiadis, D., Stratis, I., Yannacopoulos, A., & Gorgoulis, V. (2021). Machine Learning Approaches on High Throughput NGS Data to Unveil Mechanisms of Function in Biology and Disease. Cancer Genomics & Proteomics, 18, 605 - 626.
[2] Mazlan, A. U., Sahabudin, N. A., Remli, M. A. b., Ismail, N. N., Mohamad, M. S., Nies, H. W., & Warif, N. B. A. (2021). A Review on Recent Progress in Machine Learning and Deep Learning Methods for Cancer Classification on Gene Expression Data. Processes.
[3] Le, D. (2020). Machine learning-based approaches for disease gene prediction.. Briefings in functional genomics.
[4] Akter, S., Xu, D., Nagel, S., Bromfield, J., Pelch, K. E., Wilshire, G., & Joshi, T. (2019). Machine Learning Classifiers for Endometriosis Using Transcriptomics and Methylomics Data. Frontiers in Genetics, 10.
[5] Das, P., Roychowdhury, A., Das, S., Roychoudhury, S., & Tripathy, S. (2020). sigFeature: Novel Significant Feature Selection Method for Classification of Gene Expression Data Using Support Vector Machine and t Statistic. Frontiers in Genetics, 11.
[6] Reggiani, F., Rashed, Z. E., Petito, M., Pfeffer, M., Morabito, A., Tanda, E., Spagnolo, F., Croce, M., Pfeffer, U., & Amaro, A. (2024). Machine Learning Methods for Gene Selection in Uveal Melanoma. International Journal of Molecular Sciences, 25.
[7] Shang, X., & Chisholm, L. (2014). Classification of Australian Native Forest Species Using Hyperspectral Remote Sensing and Machine-Learning Classification Algorithms. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7, 2481-2489.
[8] Glaab, E., Bacardit, J., Garibaldi, J., & Krasnogor, N. (2012). Using Rule-Based Machine Learning for Candidate Disease Gene Prioritization and Sample Classification of Cancer Gene Expression Data. PLoS ONE, 7.
[9] Alharbi, F., & Vakanski, A. (2023). Machine Learning Methods for Cancer Classification Using Gene Expression Data: A Review. Bioengineering, 10.
[10] Petinrin, O. O., Saeed, F., Salim, N., Toseef, M., Liu, Z., & Muyide, I. O. (2023). Dimension Reduction and Classifier-Based Feature Selection for Oversampled Gene Expression Data and Cancer Classification. Processes.
