Immunological Responses and Drug-Ligand Interactions in Predicting Binding Affinity of the Drug for ADHD Treatment Using Big Data-Driven Modified Extreme Gradient Boosting Model

Abstract

Attention Deficit Hyperactivity Disorder (ADHD) affects both adults and children. It is a neuro-developmental illness that requires drug treatment to assess the degree of immune reactions and drug-ligand interactions with human body cells to treat ADHD in both adult and child populations. We suggest Modified Extreme Gradient Boosting (M-XGBoost) to determine the degree of drug ligand interactions with human body cells and immunological reactions to treat the ADHD brain condition. M-XGBoost, a powerful and popular gradient-boosting technique, has the capacity to estimate binding affinities. We start by compiling an extensive dataset of pharmacological molecules and how they interact with cells in the human body. To ensure consistency and dependability, this dataset undergoes thorough preparation, which includes procedures for data cleaning and normalization. M-XGBoost is used to produce binding affinity scores, which are used to predict immunological responses. These ratings work as a quantifiable indicator of how a therapeutic molecule interacts with its intended target cells, offering insightful information about the potential effectiveness of various substances for the treatment of ADHD. The selected medication candidates' immunological reactions can be predicted using the suggested M-XGBoost machine learning model. Using this prediction model, we could find medications that interact with the target cells and result in a positive immunological reaction in the patient’s body.