DRUG EFFICACY SCORE PREDICTION USING SIGNATURE BASED APPROACHES FOR AMYOTROPHIC LATERAL SCLEROSIS DISORDER: A REVIEW

Abstract

Amyotrophic Lateral sclerosis is one of the inflammatory demyelinating diseases that affects the central nervous system. Demyelination occurs due to the attack of the immune system in the myelin layer of nerves. Because of the complexity of disorder in the nervous system, the pharmacological processes are unknown, which results in incorrect biomarker identification, uncertain targets, and unknown models. Gene signatures are employed as the primary method for treating complicated disorders. Signature based drug discovery strategy plays a vital role in predicting drug efficacy scores to reveal unknown pharmacological processes based on chemical perturbations and gene perturbations. Machine learning models with high computational and processing technologies are currently being adopted to predict drug efficacy scores by interconnecting OMICS data. This paper explores and reviews different computational models available for signature-based drug discovery and machine learning models for predicting drug efficacy scores. The results of the existing research are studied and reported.