Ensemble-Learning and Feature Selection Techniques for Enhanced Antisense Oligonucleotide Efficacy Prediction in Exon Skipping

Abstract

Antisense oligonucleotide (ASO)-mediated exon skipping has become a valuable tool for investigating gene function and developing gene therapy. Machine-learning-based computational methods, such as eSkip-Finder, have been developed to predict the efficacy of ASOs via exon skipping. However, these methods are computationally demanding, and the accuracy of predictions remains suboptimal. In this study, we propose a new approach to reduce the computational burden and improve the prediction performance by using feature selection within machine-learning algorithms and ensemble-learning techniques. We evaluated our approach using a dataset of experimentally validated exon-skipping events, dividing it into training and testing sets. Our results demonstrate that using a three-way-voting approach with random forest, gradient boosting, and XGBoost can significantly reduce the computation time to under ten seconds while improving prediction performance, as measured by R² for both 2'-O-methyl nucleotides (2OMe) and phosphorodiamidate morpholino oligomers (PMOs). Additionally, the feature importance ranking derived from our approach is in good agreement with previously published results. Our findings suggest that our approach has the potential to enhance the accuracy and efficiency of predicting ASO efficacy via exon skipping. It could also facilitate the development of novel therapeutic strategies. This study could contribute to the ongoing efforts to improve ASO design and optimize gene therapy approaches.

Keywords: RNA; antisense oligonucleotides; ensemble learning; exon skipping; genetic disease; machine learning; n-of-1 therapy; personalized medicine; splice switching; splicing.

Figure 1

Predictive performance of three-way voting for PMO (left) and 2OMe (right) ASOs. When the three-way-voting approach was applied to the test data, we observed improved predictive performance for both PMO and 2OMe AOs compared to previous studies.

Figure 2

Feature importance as determined by the three-way-voting method. The feature importance scores for PMO and 2OMe are displayed on the top and bottom sides of the figure, respectively. Higher scores indicate greater importance of the feature for predicting exon-skipping efficacy. #; number.

Figure 3

Feature correlations. The feature correlations (absolute values) for PMO and 2OMe are displayed on the top and bottom sides of the figure, respectively. #; number.

Figure 4

Top k features. R² as a function of top k features when top k features were used for 10-fold cross validation on the training dataset (top for PMO and bottom for 2OMe).