An Extensive Report on Cellular Automata Based Artificial Immune System for Strengthening Automated Protein Prediction
This work addresses the problem of improving accuracy and adaptability in protein prediction for bioinformatics, though it appears incremental as it builds on existing methods with hybrid variations.
The paper tackled automated protein prediction by developing an Artificial Immune System based on Cellular Automata (AIS-MACA) to classify protein sequences into ten classes and predict secondary structures, achieving overall accuracies between 80% and 89.8% on benchmark datasets.
Artificial Immune System (AIS-MACA) a novel computational intelligence technique is can be used for strengthening the automated protein prediction system with more adaptability and incorporating more parallelism to the system. Most of the existing approaches are sequential which will classify the input into four major classes and these are designed for similar sequences. AIS-MACA is designed to identify ten classes from the sequences that share twilight zone similarity and identity with the training sequences with mixed and hybrid variations. This method also predicts three states (helix, strand, and coil) for the secondary structure. Our comprehensive design considers 10 feature selection methods and 4 classifiers to develop MACA (Multiple Attractor Cellular Automata) based classifiers that are build for each of the ten classes. We have tested the proposed classifier with twilight-zone and 1-high-similarity benchmark datasets with over three dozens of modern competing predictors shows that AIS-MACA provides the best overall accuracy that ranges between 80% and 89.8% depending on the dataset.