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

Related Concept Videos

Diffusion

Diffusion

Diffusion is the passive movement of substances down their concentration gradients—requiring no expenditure of cellular energy. Substances, such as molecules or ions, diffuse from an area of high concentration to an area of low concentration in the cytosol or across membranes. Eventually, the concentration will even out, with the substance moving randomly but causing no net change in concentration. Such a state is called dynamic equilibrium, which is essential for maintaining overall...

You might also read

Related Articles

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

Sort by

Same author

BindingSite-AugmentedDTA: enabling a next-generation pipeline for interpretable prediction models in drug repurposing.

Briefings in bioinformatics·2023

Same author

AttentionSiteDTI: an interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification.

Briefings in bioinformatics·2022

Same author

UnbiasedDTI: Mitigating Real-World Bias of Drug-Target Interaction Prediction by Using Deep Ensemble-Balanced Learning.

Molecules (Basel, Switzerland)·2022

Same author

Quantifying the Effects of Social Distancing on the Spread of COVID-19.

International journal of environmental research and public health·2021

Same author

Quantum Contagion: A Quantum-Like Approach for the Analysis of Social Contagion Dynamics with Heterogeneous Adoption Thresholds.

Entropy (Basel, Switzerland)·2021

Search research articles

Related Experiment Video

Updated: Sep 16, 2025

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Published on: June 20, 2025

BoKDiff: best-of-K diffusion alignment for target-specific 3D molecule generation.

Ali Khodabandeh Yalabadi¹, Mehdi Yazdani-Jahromi², Ozlem Ozmen Garibay¹

¹Department of Industrial Engineering and Management Systems, University of Central Florida, Orlando, FL 32816, United States.

Bioinformatics Advances

|July 7, 2025

Summary

This summary is machine-generated.

BoKDiff enhances ligand generation for structure-based drug design by integrating Best-of-K alignment and Best-of-N sampling. This novel approach improves molecule quality and generation rates, advancing therapeutic development.

More Related Videos

Analyzing and Building Nucleic Acid Structures with 3DNA

Analyzing and Building Nucleic Acid Structures with 3DNA

Published on: April 26, 2013

A Simple, Robust, and High Throughput Single Molecule Flow Stretching Assay Implementation for Studying Transport of Molecules Along DNA

A Simple, Robust, and High Throughput Single Molecule Flow Stretching Assay Implementation for Studying Transport of Molecules Along DNA

Published on: October 1, 2017

Related Experiment Videos

Last Updated: Sep 16, 2025

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Published on: June 20, 2025

Analyzing and Building Nucleic Acid Structures with 3DNA

Analyzing and Building Nucleic Acid Structures with 3DNA

Published on: April 26, 2013

A Simple, Robust, and High Throughput Single Molecule Flow Stretching Assay Implementation for Studying Transport of Molecules Along DNA

A Simple, Robust, and High Throughput Single Molecule Flow Stretching Assay Implementation for Studying Transport of Molecules Along DNA

Published on: October 1, 2017

Area of Science:

Computational chemistry and cheminformatics
Artificial intelligence in drug discovery
Molecular modeling and simulation

Background:

Structure-based drug design (SBDD) relies on target protein 3D structures for drug development.
Generative models show potential but face challenges with limited data and alignment issues.
Existing methods struggle with effective protein-ligand complex generation.

Purpose of the Study:

To introduce BoKDiff, a novel framework for enhanced ligand generation in SBDD.
To address limitations in data scarcity and alignment accuracy in current generative models.
To improve the quality and diversity of generated drug candidates.

Main Methods:

BoKDiff framework combines multi-objective optimization with Best-of-K alignment.
Ligand center of mass is repositioned to match docking pose for accurate sub-component extraction.
Best-of-N (BoN) sampling strategy is employed for optimal candidate selection without fine-tuning.
DecompDiff model is utilized as the base for ligand generation.

Main Results:

BoKDiff achieves high scores for drug-likeness (QED > 0.6) and synthetic accessibility (SA > 0.75).
The Best-of-N sampling strategy demonstrates over 35% success rate in candidate selection.
BoKDiff outperforms previous models on the CrossDocked2020 dataset with an average docking score of -8.58.
Achieved a 26% valid molecule generation rate, significantly improving upon existing methods.

Conclusions:

BoKDiff represents a significant advancement in structure-based drug design ligand generation.
The integration of Best-of-K alignment and BoN sampling offers a powerful new strategy.
This approach holds potential for practical, high-quality drug candidate design and development.