LBS-Comparison results
<p>These are the data underlying the analysis for our manuscript "<em>Comparative analysis of methods for the prediction of protein-ligand binding sites</em>".</p> <p>In this work, we gather 11 ligand binding site predictors, spanning 30 years, focusing on the latest machine learning based methods, such as VN-EGNN, IF-SitePred, GrASP, PUResNet, and DeepPocket and comparing them to established methods such as P2Rank or fpocket and earlier methods such PocketFinder, Ligsite and Surfnet. We compare these eleven methods thoroughly and benchmark them against our curated reference dataset, LIGYSIS, to perform an objective assessment of their prediction capabilities. An informed ranking of the methods, as well as a series of reflections and guidelines to advance this field result as conclusions of this analysis, which represents the most thorough analytical comparison of ligand binding site prediction methods to date, offering a clear framework for future developments in the field of ligand binding site prediction.</p>
ShareScore
32/100
Overall dataset sharing score
Score breakdown
These five areas show where the dataset supports — or may limit — practical reuse.
- Stewardship
- 4
- Harmonization
- 4
- Access
- 16
- Reuse readiness
- 8
- Engagement
- 0
Dataset details
- Repository
- zenodo
- Published
- July 28, 2024
- License
- cc-by-4.0
- DOI
- 10.5281/zenodo.13121413
Scored with release 0.9.0
ScienceDex for faculty
Your academic CV and NIH biosketch
Make your CV in your school's format and your NIH biosketch from it, then download both as Word files.