iVaccine-Deep: Prediction of COVID-19 mRNA vaccine degradation using deep learning

• Main Authors: Muneer, A., Fati, S.M., Arifin Akbar, N., Agustriawan, D., Tri Wahyudi, S.
• Format: Article
• Published: King Saud bin Abdulaziz University 2021
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85118347688&doi=10.1016%2fj.jksuci.2021.10.001&partnerID=40&md5=0243279bdb663ba6a6956b940b7e6741; http://eprints.utp.edu.my/29392/

Messenger RNA (mRNA) has emerged as a critical global technology that requires global joint efforts from different entities to develop a COVID-19 vaccine. However, the chemical properties of RNA pose a challenge in utilizing mRNA as a vaccine candidate. For instance, the molecules are prone to degradation, which has a negative impact on the distribution of mRNA among patients. In addition, little is known of the degradation properties of individual RNA bases in a molecule. Therefore, this study aims to investigate whether a hybrid deep learning can predict RNA degradation from RNA sequences. Two deep hybrid neural network models were proposed, namely GCNGRU and GCNCNN. The first model is based on graph convolutional neural networks (GCNs) and gated recurrent unit (GRU). The second model is based on GCN and convolutional neural networks (CNNs). Both models were computed over the structural graph of the mRNA molecule. The experimental results showed that GCNGRU hybrid model outperform GCNCNN model by a large margin during the test time. Validation of proposed hybrid models is performed by well-known evaluation measures. Among different deep neural networks, GCNGRU based model achieved best scores on both public and private MCRMSE test scores with 0.22614 and 0.34152, respectively. Finally, GCNGRU pre-trained model has achieved the highest AuC score of 0.938. Such proven outperformance of GCNs indicates that modeling RNA molecules using graphs is critical in understanding molecule degradation mechanisms, which helps in minimizing the aforementioned issues. To show the importance of the proposed GCNGRU hybrid model, in silico experiments has been contacted. The in-silico results showed that our model pays local attention when predicting a given position's reactivity and exhibits interesting behavior on neighboring bases in the sequence. © 2021 King Saud University