Related Experiment Video
Updated: Feb 8, 2026

Drug Repurposing Hypothesis Generation Using the "RE:fine Drugs" System
Published on: December 11, 2016
ConvAHKG: Action-based hybrid knowledge graph with a dual-channel convolutional approach for drug repurposing
Marzieh Khodadadi AghGhaleh1,2, Rooholah Abedian3, Reza Zarghami2
1Laboratory of Bioinformatics and Drug Design (LBD), Institute of Biochemistry and Biophysics, University of Tehran, Tehran, Iran.
ConvAHKG, a novel knowledge graph approach, enhances drug repurposing by predicting drug-disease associations. It identifies potential new treatments for diseases like non-small cell lung cancer, improving drug discovery efficiency.
Area of Science:
- Computational biology and bioinformatics
- Drug discovery and development
- Artificial intelligence in medicine
Background:
- Drug repurposing accelerates the identification of new therapeutic applications for existing drugs, reducing development time and costs.
- Predicting drug-disease associations is crucial for effective drug repurposing but faces challenges due to data complexity and class imbalance.
Purpose of the Study:
- To propose ConvAHKG, an action-based hybrid knowledge graph approach, for improved prediction of drug-disease associations.
- To leverage biological relationships and integrate drug/disease features for a comprehensive drug repurposing framework.
- To address class imbalance in drug-disease datasets and enhance predictive performance.
Main Methods:
- Utilized Word2Vec embeddings to capture semantic similarities among biological entities (drugs, proteins, diseases).
- Introduced a novel dual-channel 1D convolutional neural network (IDC_Conv1D) for classifying drug-disease pairs.
- Implemented a weighted binary cross-entropy loss function to mitigate class imbalance issues.
Main Results:
- ConvAHKG achieved superior performance compared to state-of-the-art models, with an Area Under the Curve (AUC) of 0.9836 and an Area Under the Precision-Recall Curve (AUPRC) of 0.9686.
- The framework successfully identified promising therapeutic candidates for non-small cell lung cancer (NSCLC), including Trastuzumab.
- Molecular docking analyses supported the potential of a predicted compound as a novel NSCLC treatment option.
Conclusions:
- ConvAHKG offers a robust and effective approach for drug repurposing and predicting drug-disease associations.
- The method demonstrates significant potential for identifying novel therapeutic strategies, particularly for complex diseases like NSCLC.
- The study provides a validated computational framework and open-source resources for advancing drug discovery efforts.
More Related Videos
07:35A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
Published on: October 13, 2023
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
Related Concept Videos
Antihypertensive Drugs: Action of Calcium Channel Blockers
Principles of Drug Action
Drugs can be agonists or antagonists. Like the endogenous ligands, agonists always bind and activate the target to produce a cellular response. Agonist binding induces a conformational change which in turn...
Antihypertensive Drugs: Action of Diuretics
Convolution Properties II
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
Targets for Drug Action: Overview
Receptors are either membrane-spanning or intracellular proteins, which upon binding a ligand, get activated and transmit the signal downstream to elicit a response. Drugs bind receptors, either mimicking the action of endogenous ligands or blocking the receptor activity to bring about a modified response. Nearly 35% of approved drugs target the G...
Neurochemical Transmission: Sites of Drug Action