Related Experiment Video
Updated: Jul 8, 2025
08:35
Achieving Efficient Fragment Screening at XChem Facility at Diamond Light Source
Published on: May 29, 2021
5.3K
FRAGSITE2: A structure and fragment-based approach for virtual ligand screening.
Hongyi Zhou1, Jeffrey Skolnick1
1Center for the Study of Systems Biology, School of Biological Sciences, Georgia Institute of Technology, Atlanta, Georgia, USA.
Protein Science : a Publication of the Protein Society
|December 15, 2023
Summary
FRAGSITE2 enhances virtual ligand screening (VLS) for drug discovery, identifying diverse small molecule binders for protein targets. This ligand homology modeling (LHM) method outperforms existing approaches, aiding in the discovery of novel drug candidates.
Area of Science:
- Computational chemistry and cheminformatics
- Drug discovery and development
- Bioinformatics and computational biology
Background:
- Protein function annotation and drug discovery rely on identifying small molecule binders.
- Virtual ligand screening (VLS) is a crucial early-stage method in drug discovery.
- Existing VLS methods, including ligand homology modeling (LHM) and deep learning, have limitations in identifying diverse binders.
Purpose of the Study:
- To introduce FRAGSITE2, an improved VLS method.
- To enhance the identification of diverse small molecule binders for protein targets, especially those lacking known binders.
- To provide a robust computational tool for early-stage drug discovery.
Main Methods:
- Development of FRAGSITE2, an advanced LHM-machine learning VLS approach.
- Benchmarking on DUD-E and DEKOIS2.0 datasets to evaluate performance against existing methods like FINDSITE, DenseFS, and RF-score-VS.
- Utilized boosted tree regression and compared performance against deep learning multiple layer perceptron and pretrained language models.
Main Results:
- FRAGSITE2 demonstrated significantly improved 1% enrichment factor (EF1%) on DUD-E and DEKOIS2.0 datasets, particularly for targets lacking known binders.
- Achieved superior ROC enrichment factor and area under the precision-recall curve (AUPR) compared to DenseFS on the DUD-E set.
- Showed substantially better performance than RF-score-VS and pretrained language models, with double the EF1% in specific comparisons.
Conclusions:
- FRAGSITE2 represents a significant advancement in VLS, offering more robust performance and enabling the discovery of novel binding ligands.
- The method is particularly effective for protein targets with limited or no known small molecule binders.
- FRAGSITE2 is available as a free web service for academic users, facilitating broader application in drug discovery research.
Related Concept Videos
02:40Ligand Binding Sites
12.9K
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...
12.9K
00:49Ligand Binding and Linkage
4.8K
Allosteric proteins have more than one ligand binding site; the binding of a ligand to any of these sites influences the binding of ligands to the other sites. When a protein is allosteric, its binding sites are called coupled or linked. In the case of enzymes, the site that binds to the substrate is known as the active site and the other site is known as the regulatory site. When a ligand binds to the regulatory site, this leads to conformational changes in the protein that can influence...
4.8K