The prediction of protein ligand binding affinities are very crucial for drug discovery research. Moelcular docking is widely used in finding initial hits in the early drug discovery stages. Though docking programs have successsully used for years, they are still not fully reliable. Many physics based scoring functions are developed over the years. However, Machine learning based scoring functions are proven to outperform the traditional scoring functions. In this study, a deep learning based algorithm trained on the recent PDBBind data using Binding Analyzer (BINANA ) descriptors will be presented.The model is generated using 348 descriptors generated using BINANA code and consists of three hidden layers. We have achieved an R<sup>2 </sup>of 0.96 for our training set and 0.76 for our test set. Validation of the model using ROC curves and enrichment factors along with comparision to other scoring functions (NNscore, vina) will be presented

DLScore: New deep learning based scoring function for reliable protein-ligand scoring

255th National Meeting (2018)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.