Low-Quality Structural and Interaction Data Improves Binding Affinity Prediction via Random Forest - Archive ouverte HAL Access content directly
Journal Articles Molecules Year : 2015

Low-Quality Structural and Interaction Data Improves Binding Affinity Prediction via Random Forest

(1) , (1) , (1) , (2)
1
2

Abstract

Docking scoring functions can be used to predict the strength of protein-ligand binding. It is widely believed that training a scoring function with low-quality data is detrimental for its predictive performance. Nevertheless, there is a surprising lack of systematic validation experiments in support of this hypothesis. In this study, we investigated to which extent training a scoring function with data containing low-quality structural and binding data is detrimental for predictive performance. We actually found that low-quality data is not only non-detrimental, but beneficial for the predictive performance of machine-learning scoring functions, though the improvement is less important than that coming from high-quality data. Furthermore, we observed that classical scoring functions are not able to effectively exploit data beyond an early threshold, regardless of its quality. This demonstrates that exploiting a larger data volume is more important for the performance of machine-learning scoring functions than restricting to a smaller set of higher data quality.
Fichier principal
Vignette du fichier
molecules-20-10947.pdf (961.71 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-01205333 , version 1 (25-09-2015)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Hongjian Li, Kwong-Sak Leung, Man-Hon Wong, Pedro J. Ballester. Low-Quality Structural and Interaction Data Improves Binding Affinity Prediction via Random Forest. Molecules, 2015, ⟨10.3390/molecules200610947⟩. ⟨hal-01205333⟩
56 View
137 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More