Classifying Beta-Secretase 1 Inhibitor Activity for Alzheimer’s Drug Discovery with LightGBM

Classifying Beta-Secretase 1 Inhibitor Activity for Alzheimer’s Drug Discovery with LightGBM

March, 10th 2024 | Teuku Rizky Noviandy, Khairun Nisa, Ghalieb Mutig Idroes, Irsan Hardi, Novi Reandy Sasmita
This study explores the use of LightGBM, a gradient-boosting framework, to classify the inhibitory activity of beta-secretase 1 (BACE1) inhibitors, a key therapeutic target for Alzheimer's disease. The research aims to enhance classification performance by addressing the limitations of traditional statistical models and conventional machine-learning techniques in handling complex molecular datasets. Using a dataset of 7298 compounds from the ChEMBL database, the study calculates molecular descriptors for each compound and employs LightGBM to achieve nuanced analysis of compound activities. The model's efficiency is benchmarked against traditional machine-learning algorithms, showing superior accuracy (84.93%), precision (87.14%), sensitivity (89.93%), specificity (77.63%), and F1-score (88.17%). The study highlights the critical role of molecular descriptors in understanding drug efficacy and the potential of LightGBM in streamlining virtual screening processes. The findings advocate for the adoption of LightGBM in computational drug discovery, offering a promising avenue for advancing Alzheimer's disease therapeutic development by facilitating the identification of potential drug candidates with enhanced precision and reliability.This study explores the use of LightGBM, a gradient-boosting framework, to classify the inhibitory activity of beta-secretase 1 (BACE1) inhibitors, a key therapeutic target for Alzheimer's disease. The research aims to enhance classification performance by addressing the limitations of traditional statistical models and conventional machine-learning techniques in handling complex molecular datasets. Using a dataset of 7298 compounds from the ChEMBL database, the study calculates molecular descriptors for each compound and employs LightGBM to achieve nuanced analysis of compound activities. The model's efficiency is benchmarked against traditional machine-learning algorithms, showing superior accuracy (84.93%), precision (87.14%), sensitivity (89.93%), specificity (77.63%), and F1-score (88.17%). The study highlights the critical role of molecular descriptors in understanding drug efficacy and the potential of LightGBM in streamlining virtual screening processes. The findings advocate for the adoption of LightGBM in computational drug discovery, offering a promising avenue for advancing Alzheimer's disease therapeutic development by facilitating the identification of potential drug candidates with enhanced precision and reliability.
Reach us at info@study.space