AttSiOff: a self-attention-based approach on siRNA design with inhibition and off-target effect prediction

Abstract

Small interfering RNA (siRNA) is often used for function study and expression regulation of specific genes, as well as the development of small molecule drugs. Selecting siRNAs with high inhibition and low off-target effects from massive candidates is always a great challenge. Increasing experimentally-validated samples can prompt the development of machine-learning-based algorithms, including Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Graph Neural Network (GNN). However, these methods still suffer from limited accuracy and poor generalization in designing potent and specific siRNAs.In this study, we propose a novel approach for siRNA inhibition and off-target effect prediction, named AttSiOff. It combines a self-attention-based siRNA inhibition predictor with an mRNA searching package and an off-target filter. The predictor gives the inhibition score via analyzing the embedding of siRNA and local mRNA sequences, generated from the pre-trained RNA-FM model, as well as other meaningful prior-knowledge-based features. Self-attention mechanism can detect potentially decisive features, which may determine the inhibition of siRNA. It captures global and local dependencies more efficiently than normal convolutions. The tenfold cross-validation results indicate that our model outperforms all existing methods, achieving PCC of 0.81, SPCC of 0.84, and AUC of 0.886. It also reaches better performance of generalization and robustness on cross-dataset validation. In addition, the mRNA searching package could find all mature mRNAs for a given gene name from the GENOMES database, and the off-target filter can calculate the amount of unwanted off-target binding sites, which affects the specificity of siRNA. Experiments on five mature siRNA drugs, as well as a new target gene (AGT), show that AttSioff has excellent convenience and operability in practical applications.Graphical