DLSCORE: A Deep Learning Model for Predicting Protein-Ligand Binding Affinities
Preprints are manuscripts made publicly available before they have been submitted for formal peer review and publication. They might contain new research findings or data. Preprints can be a draft or final version of an author's research but must not have been accepted for publication at the time of submission.
In recent years, the cheminformatics community has seen an increased success with machine learning-based scoring functions for estimating binding affinities and pose predictions. The prediction of protein-ligand binding affinities is crucial for drug discovery research. Many physics-based scoring functions have been developed over the years. Lately, machine learning approaches are proven to boost the performance of traditional scoring functions. In this study, a novel deep learning based scoring function (DLSCORE) was developed and trained on the refined PDBBind v.2016 dataset using 348 BINding ANAlyzer (BINANA) descriptors. The neural networks of the DLSCORE model have different number of fully connected hidden layers. Our model, an ensemble of 10 networks, yielded a Pearson R2 of 0.82, a Spearman Rho R2 of 0.90, Kendall Tau R2 of 0.74, an RMSE of 1.15 kcal=mol, and an MAE of 0.86 kcal=mol for our test set. This software is available on Github at https://github.com/sirimullalab/dlscore.git