Hybrid CNN-LSTM and modified wild horse herd Model-based prediction of genome sequences for genetic disorders

Abstract

Structural genomic rearrangements are a major source of genetic disorders. The main objective of the proposed work is the detection of changes or mutations that occur in a single gene of the Deoxyribonucleic acid (DNA) sequence in the human genome. More specifically, autosomal dominant inheritance from either parent causes Monogenetic or Single-gene disorders. The proposed work of prediction of monogenetic disorders uses two different approaches. The first approach is the clustering method that uses the Microsoft sequence clustering algorithm and Needleman–Wunsch algorithm for sequence alignment. The second one is the formulation of the hybrid Convolution Neural Network (CNN) and Long short-term memory (LSTM) architecture for accurate genetic disorder prediction. The modified wild horse herd optimization (MWHHO) technique is used to enhance the weight function of the hybrid CNN-LSTM architecture. The MWHHO algorithm is formed by integrating the operations of horse herd optimization and the wild horse algorithm. Experimental findings employing the NCBI dataset demonstrate that the proposed approach has a high-performance accuracy when compared to the previous technique in the prediction of monogenetic disorders such as Marfan syndrome, Prader-Willi syndrome, and Angelman syndromes. The proposed CNN-LSTM-based MWHHO algorithm is compared to several baseline techniques in terms of AUC and error rate, including COBRA, Deep Learning, Ensemble methodology, WHISTLE, Network-based classification, LVQ-CGA, and DNN. When evaluated with the F-Score, the proposed model obtains a value of 94.83%, 90.69%, and 91.53% for the NCBI SARS-COV-2, ENCPP, and UBE3A datasets respectively. In summary, the proposed model offers improved accuracies of 98.25%, 97.89%, and 96.53% for the SARC-CoV-2, ENCPP, and UBE3A datasets.