Performance Analysis of Quantum Annealing with CNN Model For Analyzing and Predicting Abnormalities in DNA Sequence of Pleuro Pulmonary Blastoma

Abstract

Abstract One of the scary diseases is cancer which affects the human body and causes death. For four to five decades, the healthcare and medical industries were not efficient in diagnosing and treating cancer diseases at the earlier stage. It was tough to identify the patient affected by cancer from the symptoms and root causes. Some of the earlier research works have provided medical image-based cancer diagnosis, but the accuracy is poor. Earlier medical industrieshave found that identifying genetic disorders helps estimate the risk level of the diseases and is the first phenotype method. Most diseases are identified and cured by diagnosing the patient's DNA/RNA, which gives high accuracy. So, the medical industries have focused on identifying cancer diseases by diagnosing the DNA/RNA sequences. This paper aims to identify the pathogenic variants related to the risk level of PPB cancer in DICER1. This paper uses the Quantum Annealing (QA) method to analyze the DNA data efficiently since it needs more computational time, space, and an automatic tuning model.It is proved that the potential of the QA method in terms of various reduced complexities when compared with the Convolution Neural Network for DNA sequence analysis. In addition, quantum computers' raw power is utilized through Hamiltonian optimization algorithms that work based on codon optimization. It also discusses the issues faced in implementing them in real-time applications. It helps in the faster and more efficient processing of DNA sequences. The proposed BQM model is simulated and tested using python and Qiskit 0.16.4 libraries with an open-source dataset. The QA and CNN models' simulation results are verified and evaluated using different data with different number states of the sequences. The results are also compared with the other state-of-the-art method for evaluating the performance of the QA model. From the computational and estimated output, it is found that the proposed QA model outperforms others.