LigTMap: Ligand and Structure-Based Target Identification and Activity Prediction for Small Molecules

07 September 2020, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

Motivation: Target prediction is a crucial step in modern drug discovery. However, existing experimental approaches to target prediction are time-consuming and costly.
Results: The LigTMap server provides a fully automated workflow to identify targets from 17 target classes with >6000 proteins. It is a hybrid approach, combining ligand similarity search with docking and binding similarity analysis, to predict putative targets. In the validation experiment, LigTMap achieved a top-10 success rate of almost 70%, with an average precision rate of 0.34. The class-specific prediction method improved the success rate further with enhanced precision. In an independent benchmarking test, LigTMap showed good performance compared to the currently best target prediction servers. LigTMap provides straightaway the PDB of a predicted target and the optimal ligand binding mode, which could facilitate structure-based drug design and the repurposing of existing drugs.

Keywords

Target prediction
binding affinity prediction
fingerprint similarity
binding interaction fingerprint
inverse docking
drug repurposing
PSOVina
random forest

Supplementary materials

Title
Description
Actions
Title
supplymentary
Description
Actions

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.