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

Molecular Models

Molecular Models

Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.

Newman Projections

Newman Projections

Different notations are used to represent the three-dimensional structure of molecules on two-dimensional surfaces. One of the most commonly used representations is the dash-wedge formula. The dashed wedges, solid wedges, and the plane lines indicate the groups situated behind the plane, coming out of the plane, and in the plane, respectively.
The organic molecules rotate across the single bonds leading to numerous temporary three-dimensional structures of varying energy known as...

You might also read

Related Articles

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

Sort by

Same author

Stromal Regulation of Tumor Perineural Invasion: A Multicellular and Neuro-Ecological Perspective.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

Facilitating structure-based drug discovery with an artificial intelligence-driven virtual screening platform.

Nature protocols·2026

Same author

EpiMII: Structure-Aware Graph Neural Networks for MHC-II Epitope Generation.

Research (Washington, D.C.)·2026

Same author

Overcoming Resistance in the Androgen Receptor: Rational and Strategic Design of Advanced Antagonists.

Accounts of chemical research·2026

Same author

Targeting the intrinsically disordered AR-NTD through a machine learning-based enhanced sampling workflow.

Nature communications·2026

Same author

BioTD: An Online Database of Biotoxins.

Journal of chemical information and modeling·2026

Same journal

tmGNN-XAI: An Explainable Graph Neural Network Tool for Predicting Electronic Properties of Transition Metal Complexes from SMILES.

Journal of chemical information and modeling·2026

Same journal

QSAR in the Browser: An Interactive Cheminformatics Web Application.

Journal of chemical information and modeling·2026

Same journal

FoldDoF: Utilizing the Primary Degrees of Freedom of Protein Backbone for Geometric Modeling and Generation.

Journal of chemical information and modeling·2026

Same journal

Derisking Affinity Optimization for Macrocycles and Cyclic Peptides: High-Precision Free Energy Simulations across Five Diverse Targets.

Journal of chemical information and modeling·2026

Same journal

An End-User Audit of Reproducibility, Data Leakage, and Overfitting of the Top-Ranked ADMET Prediction Models in TDC Leaderboards.

Journal of chemical information and modeling·2026

Same journal

PFASGroups: An Open-Source Framework for Automated Identification, Structural Classification, and Prioritization of Per- and Polyfluoroalkyl Substances.

Journal of chemical information and modeling·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 5, 2025

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

Durian: A Comprehensive Benchmark for Structure-Based 3D Molecular Generation.

Dou Nie¹, Huifeng Zhao¹, Odin Zhang¹

¹Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, 310058 Zhejiang, China.

Journal of Chemical Information and Modeling

|December 16, 2024

Summary

This summary is machine-generated.

Durian, a new framework, evaluates structure-based 3D molecular generation models using diverse metrics. It reveals limitations in balancing novelty and practicality for drug discovery, emphasizing multiobjective optimization.

More Related Videos

A Protocol for Computer-Based Protein Structure and Function Prediction

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Published on: July 25, 2013

Related Experiment Videos

Last Updated: Jun 5, 2025

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

A Protocol for Computer-Based Protein Structure and Function Prediction

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Published on: July 25, 2013

Area of Science:

Computational Chemistry
Drug Discovery
Artificial Intelligence in Chemistry

Background:

Deep neural networks are used for 3D molecular generation, leveraging target structural information.
Current evaluation methods for these models are limited by data biases and single metrics.
Comparing generative models is challenging due to inconsistent assessment criteria.

Purpose of the Study:

To introduce Durian, a comprehensive evaluation framework for structure-based 3D molecular generation.
To assess six leading 3D molecular generation methods using a multi-metric approach.
To guide the selection and optimization of generative models for drug design.

Main Methods:

Developed Durian, incorporating protein-ligand data, experimental affinity, and physicochemical/geometric metrics.
Utilized three docking methods (QuickVina2, Surflex, Gnina) in 'Dock' and 'Score' modes for binding affinity evaluation.
Applied Durian to benchmark six 3D molecular generation models: LiGAN, Pocket2Mol, DiffSBDD, SBDD, GraphBP, and SurfGen.

Main Results:

Most models generated drug-like molecules with reasonable properties but struggled with novelty, rationality, and synthetic accessibility.
Durian revealed varying limitations across models, highlighting the need for multiobjective optimization.
SurfGen and SBDD showed strong overall performance but require improvements in conformational rationality.

Conclusions:

Durian provides a robust framework for evaluating 3D molecular generation models.
Multiobjective optimization is crucial for developing practical 3D generative models for drug discovery.
The framework offers guidance for selecting and refining generative models in drug design pipelines.