Back close

A Deep Learning Approach for Prediction of Binding Affinity for Anti Malerial Drugs and Their Target Proteins

Publication Type : Conference Paper

Publisher : IEEE

Source : 2024 3rd International Conference for Innovation in Technology (INOCON)

Url : https://doi.org/10.1109/inocon60754.2024.10512173

Campus : Bengaluru

School : School of Engineering

Year : 2024

Abstract : Malaria, a severe illness caused by a specific parasite and transmitted through mosquito bites, poses a significant threat to life. Considerable research has been conducted in diagnosing this disease. Various drugs have been developed to combat it, notably chloroquine derivatives and artemisinin. However, chloroquine's effectiveness against the malaria parasite has been limited due to the parasite's development of resistance to the drug. Although the exact method by which chloroquine eliminates the parasite remains unclear, this research conducts a thorough investigation into the mechanism of action of chloroquine. It aims to understand how substances akin to chloroquine attach themselves to its target proteins. Furthermore, the effectiveness of chloroquine derivatives is demonstrated in this study through the binding energy exhibited by the drug towards specific proteins by introducing a novel approach for determining the drug's binding energy, using convolutional neural networks. The model ended up by giving a mean squared error of 1.23 with an R2 score of 0.65. The model has been validated with the quercetin derivatives and their target protein called pfLDH (lactate dehydrogenase proteins). The paper highlights that there are patterns in the sequences of drugs and target which can helps in leading out to the prediction of binding affinities without the use of any docking study.

Cite this Research Publication : Shaik Reeha, Masabattula Teja Nikhil, Amrita Thakur, A Deep Learning Approach for Prediction of Binding Affinity for Anti Malerial Drugs and Their Target Proteins, 2024 3rd International Conference for Innovation in Technology (INOCON), IEEE, 2024, https://doi.org/10.1109/inocon60754.2024.10512173

Admissions Apply Now