Related Experiment Video
Updated: Sep 7, 2025

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules
Published on: July 25, 2013
Artificial intelligence guided conformational mining of intrinsically disordered proteins.
Aayush Gupta1, Souvik Dey1, Alan Hicks1
1Department of Chemistry, University of Illinois at Chicago, Chicago, IL, 60607, USA.
Artificial intelligence now predicts protein structures and conformational ensembles for intrinsically disordered proteins (IDPs). Generative autoencoders efficiently model IDP dynamics, overcoming limitations of traditional molecular dynamics simulations.
Area of Science:
- Computational biology
- Structural biology
- Artificial intelligence in protein science
Background:
- Intrinsically disordered proteins (IDPs) represent a significant portion of proteomes and explore vast conformational spaces.
- Molecular dynamics (MD) simulations are crucial for sampling IDP conformations but are computationally intensive.
Purpose of the Study:
- To develop an AI-driven method for generating comprehensive conformational ensembles of IDPs.
- To overcome the computational cost limitations of traditional MD simulations for IDPs.
Main Methods:
- Utilized generative autoencoders trained on short MD simulations.
- Encoded protein conformations into a reduced-dimensional latent space.
- Generated new conformations by sampling from a multivariate Gaussian distribution in the latent space and decoding.
Main Results:
- Generated conformational ensembles accurately reflect those obtained from extensive MD simulations.
- The generated ensembles were validated using experimental data, including small-angle X-ray scattering profiles and NMR chemical shifts.
- Demonstrated the efficiency of AI in capturing the conformational diversity of IDPs.
Conclusions:
- Generative autoencoders offer a powerful and computationally efficient approach for conformational mining of IDPs.
- AI has vast potential to advance the study of protein dynamics and function.
- This method significantly reduces the computational burden for exploring IDP conformational landscapes.
More Related Videos
07:08Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
Published on: July 14, 2015
07:24Paramagnetic Relaxation Enhancement for Detecting and Characterizing Self-Associations of Intrinsically Disordered Proteins
Published on: September 23, 2021
Related Concept Videos
Intrinsically Disordered Proteins
Protein Folding
Protein Structure Is Critical to Its Biological Function
Proteins perform a wide range of biological functions such as catalyzing chemical reactions, providing...
Conserved Binding Sites
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-protein Interfaces
Protein Organization
The primary structure of a protein is its amino acid sequence....
Molecular Chaperones and Protein Folding
The...