TY - GEN
T1 - Application of Artificial Intelligence to Predict the Degradation of Potential mRNA Vaccines Developed to Treat SARS-CoV-2
AU - Giridhar, Ankitha
AU - Sampathila, Niranjana
N1 - Funding Information:
Acknowledgements. The authors would like to thank the Department of Biomedical Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education for the support in enabling this study.
Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2022
Y1 - 2022
N2 - The Covid19 pandemic has impacted the entire world negatively, and scientists, healthcare professionals and engineers are all on the search for viable solutions. During the search for a vaccine for the virus, scientifically known as SARS-CoV-2, it was identified as an mRNA virus, which is why mRNA vaccines could be potential solutions. However, mRNA vaccines easily degrade, and the objective of this study was to predict the degradation rates of various potential mRNA strands to potentially select an ideal sequence for a vaccine. This paper details an approach that uses a Neural Network model with the LSTM (Long Short Term Memory) and GRU (Gated Recurrent Unit) architectures to predict the degradation of each sequence in the given data, which comprised of sequences of mRNA. The performance of the model was evaluated using the MCRMSE (Mean Columnwise Root Mean Squared Error) as the scoring metric.
AB - The Covid19 pandemic has impacted the entire world negatively, and scientists, healthcare professionals and engineers are all on the search for viable solutions. During the search for a vaccine for the virus, scientifically known as SARS-CoV-2, it was identified as an mRNA virus, which is why mRNA vaccines could be potential solutions. However, mRNA vaccines easily degrade, and the objective of this study was to predict the degradation rates of various potential mRNA strands to potentially select an ideal sequence for a vaccine. This paper details an approach that uses a Neural Network model with the LSTM (Long Short Term Memory) and GRU (Gated Recurrent Unit) architectures to predict the degradation of each sequence in the given data, which comprised of sequences of mRNA. The performance of the model was evaluated using the MCRMSE (Mean Columnwise Root Mean Squared Error) as the scoring metric.
UR - http://www.scopus.com/inward/record.url?scp=85116914930&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85116914930&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-82469-3_8
DO - 10.1007/978-3-030-82469-3_8
M3 - Conference contribution
AN - SCOPUS:85116914930
SN - 9783030824686
T3 - Lecture Notes in Networks and Systems
SP - 85
EP - 94
BT - Machine Learning and Big Data Analytics - Proceedings of International Conference on Machine Learning and Big Data Analytics, ICMLBDA 2021
A2 - Misra, Rajiv
A2 - Shyamasundar, Rudrapatna K.
A2 - Chaturvedi, Amrita
A2 - Omer, Rana
PB - Springer Science and Business Media Deutschland GmbH
T2 - International Conference on Machine Learning and Big Data Analytics, ICMLBDA 2021
Y2 - 29 March 2021 through 30 March 2021
ER -
