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

Conserved Binding Sites

Conserved Binding Sites

Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
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...

You might also read

Related Articles

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

Sort by

Same author

From Sequential Molecular Adsorption on Atomically Precise Ag<sub>29</sub> Nanoclusters to Aggregates of Soot-Like Particles.

ACS nano·2026

Same author

A Molecular "Thermometer" for Measuring Effective Non-Local Exchange.

Journal of computational chemistry·2026

Same author

A Ruthenium-(Ph-BPE) Catalyst for Asymmetric Alkynylation of Fluoral: Enantioselection From 1 of 12 Fluxional Stereogenic-at-Ruthenium Complexes.

Angewandte Chemie (International ed. in English)·2026

Same author

How Spin Conductive are Oligo(p-phenylenes) in Trityl-Based Biradicals.

Journal of the American Chemical Society·2026

Same author

White-light powered autonomous molecular ratchet drives Pd<sup>II</sup> capsules out of equilibrium.

Chemical science·2026

Same author

Pore-Selective Fullerene Loading in a Porphyrin-Based Metal-Organic Framework Controls Photoinduced Charge-Transfer Dynamics.

The journal of physical chemistry letters·2026

Search research articles

Related Experiment Video

Updated: Jun 7, 2025

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

ConfRank: Improving GFN-FF Conformer Ranking with Pairwise Training.

Christian Hölzer¹, Rick Oerder^2,3, Stefan Grimme¹

¹Mulliken Center for Theoretical Chemistry, University of Bonn, Beringstr. 4, 53115 Bonn, Germany.

Journal of Chemical Information and Modeling

|November 20, 2024

Summary

ConfRank, a machine learning method, significantly improves molecular conformer ranking for drug discovery by using pairwise training. This approach enhances accuracy and speed, outperforming existing methods in identifying low-energy conformers.

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

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Published on: July 14, 2015

Related Experiment Videos

Last Updated: Jun 7, 2025

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

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

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Published on: July 14, 2015

Area of Science:

Computational chemistry
Drug discovery
Machine learning

Background:

Conformer ranking is vital for drug discovery but current methods face limitations in speed and accuracy.
Force computation constraints hinder large-scale screening applications.

Purpose of the Study:

To introduce ConfRank, a machine learning approach for enhanced conformer ranking.
To improve the accuracy and efficiency of identifying low-energy molecular conformers.

Main Methods:

Developed ConfRank, a machine learning model utilizing pairwise training.
Leveraged DimeNet++ architecture trained on large datasets (GEOM, QM9).
Evaluated performance against GFN-FF and GFN2-xTB using various metrics (RMSD, Spearman correlation).

Main Results:

ConfRank reduced pairwise RMSD from 5.65 to 0.71 kcal mol⁻¹.
Achieved up to 81% accuracy in identifying lowest energy conformers, significantly outperforming existing methods.
Demonstrated runtime accelerations up to 100x compared to GFN2-xTB.
Improved Spearman correlation to 0.90, reducing sign flip probability to 7%.

Conclusions:

ConfRank offers a cost-effective and scalable solution for accurate conformer ranking.
The pairwise training approach significantly enhances ranking performance, despite potential minor impacts on absolute energy prediction.
ConfRank shows promise for applications in drug discovery and (bio)molecular structure analysis.