Table 1 Comparison of various existing research in protein sequence analysis
References | Method used | Dataset | Outcome | Future scope |
|---|---|---|---|---|
[15] | Attention-based Neural Network | PDB-14,189 | Improved classification accuracy | Investigate attention mechanisms in larger datasets |
[16] | RNNs | DNA Data Bank of Japan | Improved Classification | Exploration of hybrid models in proteomics research |
[17] | Hybrid CNN-RNN Model | European Nucleotide Archive | Enhanced protein structure prediction | Integration of attention mechanisms in drug design |
[18] | Transformer Networks | The Consensus CDS protein set database | Better classification and performance | Exploration of hybrid models in proteomics research |
[19] | Attention-based Hybrid Model | PDB-2272 | State-of-the-art performance | Application of hybrid models in drug target prediction |
[20] | Random Forest and Decision Tree | SWISS-PROT Dataset | Captured spatial dependencies | Investigation of attention mechanisms in protein engineering |
[21] | CNN and RNN | PROSITE database | Improved classification accuracy | Application of hybrid models in drug target prediction |
[22] | NLP with Machine learning | CASP Dataset | Improved classification accuracy | Development of attention mechanisms for protein-protein interaction prediction |
Proposed Hybrid | Attention method with Improved CNN and BiLSTM | PDB-14,189 Datasets | Improved classification accuracy | Time Complexity can improve. |