Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Oct 3, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Similarity-Based Virtual Screen Using Enhanced Siamese Deep Learning Methods.

Mohammed Khaldoon Altalib^1,2, Naomie Salim¹

¹School of Computing, Universiti Teknologi Malaysia, Johor Bahru 81310, Malaysia.

|February 21, 2022

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Hybrid-Enhanced Siamese Similarity Models in Ligand-Based Virtual Screen.

Biomolecules·2022

Same author

Machine Learning-Based Performance Comparison to Diagnose Anterior Cruciate Ligament Tears.

Journal of healthcare engineering·2022

Same author

Similarity-Based Virtual Screen Using Enhanced Siamese Multi-Layer Perceptron.

Molecules (Basel, Switzerland)·2021

Same journal

Impact of an Artificial Albumin Corona on Surface Charge-Driven Nano-Bio Interactions and Cytotoxicity of Silver Nanoparticles.

ACS omega·2026

Same journal

Structural and Functional Disruption of Thiopurine S‑Methyltransferase by the A80P Variant: A Simulation and Genotyping Study.

ACS omega·2026

Same journal

CRISPR/Cas12a2-Mediated Ultrasensitive Assay for Rapid Detection of H1N1 Influenza Virus RNA.

ACS omega·2026

Same journal

Photocatalytic Treatment of Real Sugar Industry Wastewater Using Lignocellulosic Biomass-Derived Hydrochar/g-CN.

ACS omega·2026

Same journal

Electrochemical Dopamine Biosensor Based on Plant-Derived Peroxidase Immobilized on Titanate Nanowires.

ACS omega·2026

Same journal

Revealing the Effects of Process Parameters on Structural, Thermal, Mechanical, Biodegradation, and Biocompatibility Properties on the Electrospinning of Poly(vinyl alcohol)/Microbial Inulin Nanofibers.

ACS omega·2026

See all related articles

This study enhances virtual screening for drug discovery by improving molecular similarity searches, particularly for structurally diverse compounds. Novel deep learning approaches, including enhanced Siamese networks, significantly outperform existing methods in identifying potential drug candidates.

Area of Science:

Computational chemistry
Drug discovery
Artificial intelligence in pharmacology

Background:

Traditional drug production is lengthy and costly.
Virtual screening accelerates compound evaluation but struggles with structurally heterogeneous molecules.
Existing ligand-based virtual screening (LBVS) methods are insufficient for diverse chemical structures.

Purpose of the Study:

To enhance the performance of similarity searching in ligand-based virtual screening (LBVS), especially for structurally heterogeneous molecules.
To develop an improved deep learning model for more accurate molecular similarity measurements.
To boost the efficiency and effectiveness of virtual screening in drug discovery.

Main Methods:

An enhanced Siamese network architecture incorporating two similarity distance layers and a fusion layer.

More Related Videos

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

Related Experiment Videos

Last Updated: Oct 3, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

Integration of deep learning models: Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network-1D (CNN1D), and Convolutional Neural Network-2D (CNN2D).

Experiments conducted on real-world datasets to validate the proposed methods.

Main Results:

The proposed enhanced Siamese network architecture significantly improved similarity measurements between molecules.
Deep learning models demonstrated superior performance in handling structurally heterogeneous molecular data.
The enhanced methods outperformed existing techniques in virtual screening tasks, particularly in retrieval recall.

Conclusions:

The developed deep learning-based approach offers a powerful solution for identifying potential drug candidates from large, diverse chemical libraries.
The enhanced Siamese network architecture effectively addresses the limitations of traditional methods in handling molecular heterogeneity.
This work advances computational drug discovery by providing more accurate and efficient virtual screening tools.