Book Review: Protein-Ligand Interactions-From Molecular Recognition to Drug Design Methods. Edited by Hans-Joachim Böhm and Gisbert Schneider

ChemBioChem ◽  
2003 ◽  
Vol 4 (11) ◽  
pp. 1249-1250
Author(s):  
Andy Davis
Keyword(s):  
Molecular Recognition ◽  
Drug Design ◽  
Design Methods ◽  
Protein Ligand Interactions ◽  
Ligand Interactions

scholarly journals Structure- and ligand-based drug design approaches for neglected tropical diseases

2012 ◽  
Vol 84 (9) ◽  
pp. 1857-1866 ◽  
Author(s):  
Rafael V. C. Guido ◽  
Glaucius Oliva ◽  
Adriano D. Andricopulo
Keyword(s):  
Drug Design ◽  
Neglected Tropical Diseases ◽  
Poor People ◽  
Tropical Diseases ◽  
Protein Ligand Interactions ◽  
New Chemical Entities ◽  
Ligand Interactions ◽  
Complementary Nature ◽  
Further Development ◽  
D Investment

Drug discovery has moved toward more rational strategies based on our increasing understanding of the fundamental principles of protein–ligand interactions. Structure- (SBDD) and ligand-based drug design (LBDD) approaches bring together the most powerful concepts in modern chemistry and biology, linking medicinal chemistry with structural biology. The definition and assessment of both chemical and biological space have revitalized the importance of exploring the intrinsic complementary nature of experimental and computational methods in drug design. Major challenges in this field include the identification of promising hits and the development of high-quality leads for further development into clinical candidates. It becomes particularly important in the case of neglected tropical diseases (NTDs) that affect disproportionately poor people living in rural and remote regions worldwide, and for which there is an insufficient number of new chemical entities being evaluated owing to the lack of innovation and R&D investment by the pharmaceutical industry. This perspective paper outlines the utility and applications of SBDD and LBDD approaches for the identification and design of new small-molecule agents for NTDs.

scholarly journals Hidden Bias in the DUD-E Dataset Leads to Misleading Performance of Deep Learning in Structure-Based Virtual Screening

2019 ◽  
Author(s):  
Lieyang Chen ◽  
Anthony Cruz ◽  
Steven Ramsey ◽  
Callum J. Dickson ◽  
José S. Duca ◽  
...  
Keyword(s):  
Deep Learning ◽  
Virtual Screening ◽  
Molecular Recognition ◽  
Autodock Vina ◽  
Methodology Development ◽  
X Ray ◽  
Learning Biases ◽  
Protein Ligand Interactions ◽  
Ligand Interactions ◽  
Docking Program

<p>Recently much effort has been invested in using convolutional neural network (CNN) models trained on 3D structural images of protein-ligand complexes to distinguish binding from non-binding ligands for virtual screening. However, the dearth of reliable protein-ligand x-ray structures and binding affinity data has required the use of constructed datasets for the training and evaluation of CNN molecular recognition models. Here, we outline various sources of bias in one such widely-used dataset, the Directory of Useful Decoys: Enhanced (DUD-E). We have constructed and performed tests to investigate whether CNN models developed using DUD-E are properly learning the underlying physics of molecular recognition, as intended, or are instead learning biases inherent in the dataset itself. We find that superior enrichment efficiency in CNN models can be attributed to the analogue and decoy bias hidden in the DUD-E dataset rather than successful generalization of the pattern of protein-ligand interactions. Comparing additional deep learning models trained on PDBbind datasets, we found that their enrichment performances using DUD-E are not superior to the performance of the docking program AutoDock Vina. Together, these results suggest that biases that could be present in constructed datasets should be thoroughly evaluated before applying them to machine learning based methodology development. </p>

Sign in / Sign up

Export Citation Format

Share Document