Deep learning analysis of intracranial EEG for recognizing drug effects and mechanisms of action

TL;DR

This paper introduces a convolutional neural network model that analyzes intracranial EEG data to predict drug-target interactions and elucidate drug mechanisms of action, enhancing drug discovery and understanding of neural effects.

Contribution

The study presents a novel CNN-based approach for EEG-mediated DTI prediction that explains complex drug actions and identifies similarities in mechanisms of psychotropic drugs.

Findings

Effective CNN model for EEG-based DTI prediction

Ability to classify drugs by mechanism of action

Insights into neural effects of psychotropic drugs

Abstract

Drug-target interaction (DTI) prediction has become a foundational task in drug repositioning, polypharmacology, drug discovery, as well as drug resistance and side-effect prediction. DTI identification using machine learning is gaining popularity in these research areas. Through the years, numerous deep learning methods have been proposed for DTI prediction. Nevertheless, prediction accuracy and efficiency remain key challenges. Pharmaco-electroencephalogram (pharmaco-EEG) is considered valuable in the development of central nervous system-active drugs. Quantitative EEG analysis demonstrates high reliability in studying the effects of drugs on the brain. Earlier preclinical pharmaco-EEG studies showed that different types of drugs can be classified according to their mechanism of action on neural activity. Here, we propose a convolutional neural network for EEG-mediated DTI prediction. This new approach can explain the mechanisms underlying complicated drug actions, as it allows the identification of similarities in the mechanisms of action and effects of psychotropic drugs.