Related Experiment Video
Updated: May 8, 2026

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
Published on: June 20, 2025
An Ensemble Method for Predicting and Designing of Druggable Proteins
Shipra Jain1, Srijanee Gupta1, Gajendra P S Raghava1
1Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India.
This study developed a predictive model to identify druggable proteins, achieving high accuracy in distinguishing therapeutic proteins. The findings aid in discovering new drug candidates and streamline protein-based drug development.
Area of Science:
- Biochemistry and Bioinformatics
- Drug Discovery and Development
Background:
- Proteins and peptides exhibit diverse therapeutic properties, including anticancer and antimicrobial effects.
- Despite therapeutic potential, most discovered proteins fail clinical trials, with few gaining US FDA approval due to challenges in identifying druggable candidates.
Purpose of the Study:
- To systematically investigate the properties of FDA-approved proteins.
- To develop predictive models for identifying druggable proteins.
- To enhance the success rate of protein-based drug discovery.
Main Methods:
- Utilized a dataset of 356 FDA-approved proteins and an equal number of negative controls.
- Employed machine learning models, including Random Forest with SVC-L1 feature selection.
- Incorporated MERCI-based motif analysis to identify exclusive patterns in druggable proteins.
Main Results:
- A Random Forest model achieved an AUC of 0.80 and MCC of 0.61 on validation data.
- An ensemble model combining machine learning and exclusive motifs reached an AUC of 0.92 and MCC of 0.83.
- Identified exclusive motifs characteristic of druggable proteins.
Conclusions:
- Developed "ThPPred", a web server and standalone package for predicting and designing druggable proteins.
- The proposed methods and tools aim to assist the scientific community in protein-based drug discovery.
- Facilitates identification of promising protein candidates for therapeutic development.
Related Concept Videos
Protein-protein Interfaces
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Structure-Activity Relationships and Drug Design
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence its...
Drug Discovery: Overview
Protein-Drug Binding: Determination Methods
Indirect methods involve isolating the bound drug from its free form in biological samples such as blood, serum, or plasma. These techniques aim to measure the percentage of drugs bound to proteins. Equilibrium dialysis is a commonly used method where the free drug concentration at equilibrium is measured by separating the bound...
Conserved Binding Sites
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally analyses the...
