Related Experiment Video
Updated: Jun 27, 2025
10:21
Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
Published on: February 23, 2024
2.5K
RmsdXNA: RMSD prediction of nucleic acid-ligand docking poses using machine-learning method
Lai Heng Tan1, Chee Keong Kwoh2, Yuguang Mu3
1Interdisciplinary Graduate School, Nanyang Technological University, 61 Nanyang Drive, 637335 Singapore, Singapore.
Briefings in Bioinformatics
|May 2, 2024
Summary
A new machine learning model, RmsdXNA, accurately predicts ligand binding poses for nucleic acid targets. This tool enhances drug discovery by improving the identification of effective small molecule drugs for nucleic acid-based therapies.
Area of Science:
- Computational chemistry
- Drug discovery
- Machine learning applications in bioinformatics
Background:
- Small molecule drugs targeting nucleic acids (NA) are crucial for regulating biological processes.
- Current computational modeling, including molecular docking and scoring functions, often struggles with accurate prediction of ligand-NA binding poses.
Purpose of the Study:
- To develop a machine learning model, RmsdXNA, for predicting the root-mean-square-deviation (RMSD) of ligand docking poses in NA complexes.
- To enhance the accuracy of computational drug design for nucleic acid targets.
Main Methods:
- Development of the RmsdXNA machine learning model to predict RMSD for NA-ligand complexes.
- Validation using diverse NA-ligand complexes (metal complexes, peptides).
- Comparative analysis against rDock scoring function and experimental validation on RNA-small molecule complexes and MALAT1 using molecular dynamics simulations.
Main Results:
- RmsdXNA demonstrated a strong correlation between predicted and actual RMSD values.
- RmsdXNA outperformed rDock in ranking and identifying near-native poses for various NA-ligand complexes.
- RmsdXNA showed superior screening power for RNA-small molecule complexes and a higher success rate in identifying promising ligands via molecular dynamics simulations.
Conclusions:
- RmsdXNA offers an accurate and versatile tool for predicting ligand docking poses in nucleic acid complexes.
- The developed model significantly improves upon existing scoring functions, aiding in more effective drug discovery and development for NA-targeted therapies.
- The RmsdXNA code is publicly available to facilitate further research.
Related Concept Videos
02:40Ligand Binding Sites
12.8K
Proteins are dynamic macromolecules that carry out a wide variety of essential processes; however, the activities of most proteins depend on their interactions with other molecules or ions, known as ligands.
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
12.8K
01:49Conserved Binding Sites
4.2K
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...
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...
4.2K