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

Protein Folding

Protein Folding

Protein Folding

Protein Folding

Proteins are chains of amino acids linked together by peptide bonds. Upon synthesis, a protein folds into a three-dimensional conformation, critical to its biological function. Interactions between its constituent amino acids guide protein folding, and hence the protein structure is primarily dependent on its amino acid sequence.
Protein Structure Is Critical to Its Biological Function
Proteins perform a wide range of biological functions such as catalyzing chemical reactions, providing...

Protein Folding

Protein Folding

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...

Protein Organization

Protein Organization

Proteins are polymers of amino acid residues. They are versatile and responsible for different cellular functions, including DNA replication, molecular transport, catalysis, and structural support. Proteins have a hierarchical structure comprising at least three levels of organization: primary, secondary, and tertiary structure. Some large proteins have a quaternary structure where individual protein subunits are linked together.
The primary structure of a protein is its amino acid sequence....

Protein Organization

Protein Organization

You might also read

Related Articles

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

Sort by

Same author

Adversarial Sequence Mutations in AlphaFold and ESMFold Reveal Nonphysical Structural Invariance, Confidence Failures, and Concerns for Protein Design.

Computational and structural biotechnology journal·2026

Same author

Toward mechanistic virtual immune cells.

Nature biotechnology·2026

Same author

Understanding Substance Dependence: What Differentiates Addictive from Non-Addictive Drugs?

bioRxiv : the preprint server for biology·2026

Same author

A reliability-screened thalamocortical control-network phenotype tracks cocaine-use history in cocaine use disorder.

medRxiv : the preprint server for health sciences·2026

Same author

PHENOCAUZ: Linking Human Symptoms, Drug Side Effects and Efficacy to Their Molecular Causes Using Mendelian Disease Biology.

bioRxiv : the preprint server for biology·2026

Same author

Scalable discovery and validation of order-specific electronic health record event trajectories for interpretable adverse-outcome risk estimation.

Journal of biomedical informatics·2026

Search research articles

Related Experiment Video

Updated: May 5, 2026

Investigating Protein Sequence-structure-dynamics Relationships with Bio3D-web

Investigating Protein Sequence-structure-dynamics Relationships with Bio3D-web

Published on: July 16, 2017

AlphaInterp: Mechanistic Interpretability of AlphaFold 3 Reveals How Evolutionary Information Shapes Protein

Jonathan Feldman^1,2,3, Jeffrey Skolnick^2,3

¹College of Computing, Georgia Institute of Technology, Atlanta, Georgia, United States.

Biorxiv : the Preprint Server for Biology

|May 4, 2026

Summary

AlphaFold 3 uses evolutionary context, not just sequence, for protein structure prediction. Phylogenetic diversity in multiple sequence alignments is key, with divergent homologs outperforming near-identical ones for accuracy.

Keywords:

AlphaFold 3 evolutionary dependence mechanistic interpretability multiple sequence alignment protein structure prediction representational geometry

More Related Videos

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

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

Related Experiment Videos

Last Updated: May 5, 2026

Investigating Protein Sequence-structure-dynamics Relationships with Bio3D-web

Investigating Protein Sequence-structure-dynamics Relationships with Bio3D-web

Published on: July 16, 2017

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

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

Area of Science:

Computational Biology
Structural Biology
Bioinformatics

Background:

AlphaFold 3 achieves high accuracy in protein structure prediction.
The internal computations translating evolutionary data into structure remain unclear.

Purpose of the Study:

To perform the first mechanistic interpretability analysis of AlphaFold 3.
To understand how AlphaFold 3 utilizes evolutionary information for structure prediction.

Main Methods:

Systematic analysis of single and pair representations at four checkpoints.
Probing model behavior across adversarial-mutation, fold-switching, and structural-generalization benchmarks.
Investigating the impact of multiple sequence alignment (MSA) quality and diversity.

Main Results:

AlphaFold 3 relies on comparative evolutionary context over raw sequence.
Divergent homologs are more critical than numerous near-identical sequences.
Accuracy is maintained with degraded MSAs but collapses without them; phylogenetic diversity is crucial, not MSA depth.
The Pairformer compresses co-evolutionary data into a latent space encoding biophysical features.

Conclusions:

AlphaFold 3 functions as a sensitive fold recognition algorithm.
The model leverages MSAs to identify constrained positions and activate structural priors.
Understanding these mechanisms impacts protein structure prediction, evolutionary inference, and protein design.