Related Experiment Video
Updated: Aug 30, 2025

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
Published on: June 20, 2025
Deep learning approaches for conformational flexibility and switching properties in protein design
Lucas S P Rudden1, Mahdi Hijazi1, Patrick Barth1
1Institute of Bioengineering, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland.
Deep learning is advancing protein design by using generative models to create novel proteins. New methods are exploring protein flexibility to improve design accuracy and function.
Area of Science:
- Biochemistry
- Computational Biology
- Structural Biology
Background:
- Deep learning has revolutionized protein structure prediction.
- Generative models are increasingly applied to protein design for enhanced functionality and novel structures.
- Protein flexibility presents a significant challenge for accurate computational design.
Purpose of the Study:
- To review current protein design methodologies.
- To discuss how deep learning models address protein flexibility.
- To identify future directions in deep learning-based protein design.
Main Methods:
- Review of existing protein design techniques.
- Analysis of deep learning-based generative models for protein design.
- Examination of approaches that incorporate protein flexibility (e.g., conformational dynamics).
Main Results:
- Deep learning models show promise in designing proteins with tailored functions.
- Accommodating protein flexibility is crucial for successful de novo protein design.
- Current deep learning methods are evolving to better capture protein dynamics.
Conclusions:
- Deep learning offers powerful tools for protein design.
- Future research should focus on integrating dynamic flexibility into generative design models.
- Advancements in this field could lead to novel proteins for various applications.
Related Concept Videos
Intrinsically Disordered Proteins
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 Folding
Protein Structure Is Critical to Its Biological Function
Proteins perform a wide range of biological functions such as catalyzing chemical reactions, providing...
¹H NMR of Conformationally Flexible Molecules: Variable-Temperature NMR
¹H NMR of Conformationally Flexible Molecules: Temporal Resolution
Conservation of Protein Domains Over Different Proteins
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...

