SiaRNA: a siamese neural network with bidirectional cross-attention for pairwise siRNA-mRNA efficacy prediction

Small interfering RNA (siRNA) therapeutics have extraordinary potential for targeted gene silencing. They mediate post-transcriptional gene regulation by binding to complementary messenger RNA (mRNA) sequences and degrading them, thereby preventing the production of unwanted proteins. Recent machine learning and deep learning frameworks for predicting siRNA efficacy have only achieved moderate success as these models solely rely either on handcrafted features or on sequential relations and therefore cannot capture the full complexity of siRNA-mRNA interactions.

In the above context, we propose SiaRNA, which uses a Siamese Neural Network for feature-derived representations and a bidirectional cross-attention mechanism for sequence-level relationships. It uniquely identifies mRNAs and their corresponding siRNAs as paired entities, allowing unified and context-aware modeling. Unlike previous models, which discard 2-nucleotide (2-nt) overhangs at the 3' end while using 21-nt efficacy labels, SiaRNA both trains and tests on 21-nt sequences to ensure biologically consistent predictions.

Our model sets a new performance benchmark, outperforming previous state-of-the-art models. SiaRNA is trained on the HUVK dataset, achieving an accuracy of 0.881, and its generalization is confirmed by testing on the independent Simone dataset.

The results prove SiaRNA's potential as a reliable and biologically accurate framework to guide siRNA design and improve therapeutic outcomes. On performing a case study using Patisiran siRNA and its target transthyretin (TTR) mRNA, an efficacy value of 0.7134 was observed indicating that our model can successfully identify therapeutically effective targets.