Predicting Efficacy of Drugs for Amyotrophic Lateral Sclerosis Using Recurrent Neural Networks and LSTM

Amyotrophic Lateral Sclerosis (ALS) is a progressive neurodegenerative disorder marked by the degeneration of motor neurons, which results in severe motor dysfunction. Despite considerable research efforts, effective treatments for ALS remain elusive, underscoring the critical need to expedite drug discovery processes. This study investigates the application of Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) models to predict the efficacy of potential ALS therapeutics. Utilizing molecular structure data, represented through canonical SMILES, the proposed model forecasts EC50 values, a key indicator of drug potency. These advanced models discern complex patterns within the molecular data, thereby enhancing the accuracy of drug efficacy predictions. The results demonstrate that the proposed approach significantly outperforms traditional methods, offering a promising strategy for accelerating the identification of ALS therapeutics. This research highlights the potential of RNN and LSTM models to not only improve the precision and efficiency of drug discovery but also to advance the development of effective ALS treatments.