抽象的

Identification of RNA-binding sites on the proteins using simultaneous network model.

P Siva Kumar*

Those amino acids residues that interact directly using RNA make up the RNA-binding region of proteins. Addressing diverse post-transcriptional controls requires identifying RNA-binding domains on enzymes. The use of experimental techniques to discover RNA-binding locations has several drawbacks, including expensive constraints and lower productivity. Computationally models provide an appealing alternative. Notwithstanding these claims of accomplishment implemented by different researching groups, unbiased studies show that existing computational approaches have rather poor reliability. As a result, there seems to be a pressing need to improve computationally approaches. We used a deep learning approach called Convolutional Neural Network (CNN) to discover RNA-bindings locations on enzymes in this research. The CNN has 97.2 percent accuracies with 0.98 Area under the Curves (AUC) in five-fold cross-validation. Deeply learning outperforms other state of the art machine learning approaches such as supports vector machines and Randomized Forests, according to assessments.