AutoRevDock: An open‐source toolkit for scalable reverse docking

Reverse docking is a pivotal computational strategy for drug repurposing and polypharmacology studies, yet existing tools often suffer from limitations in throughput, accuracy, and reliance on centralized servers. To overcome these challenges, we present AutoRevDock, an open‐source Python toolkit de...

Full description

Saved in:
Bibliographic Details
Published in:Protein science Vol. 34; no. 11; pp. e70358 - n/a
Main Authors: Luo, Qing, Mu, Yuguang, Zheng, Liangzhen, Guo, Jingjing
Format: Journal Article
Language:English
Published: Hoboken, USA John Wiley & Sons, Inc 01.11.2025
Wiley Subscription Services, Inc
Subjects:
Drug Repositioning
drug repurposing
drug‐target interaction
Humans
Molecular Docking Simulation - methods
Proteins - chemistry
Proteomes
reverse docking
Software
target fishing
target prediction
Toolkits
drug‐target interaction
target fishing
target prediction
drug repurposing
reverse docking
ISSN:0961-8368, 1469-896X, 1469-896X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Reverse docking is a pivotal computational strategy for drug repurposing and polypharmacology studies, yet existing tools often suffer from limitations in throughput, accuracy, and reliance on centralized servers. To overcome these challenges, we present AutoRevDock, an open‐source Python toolkit designed to streamline and enhance the reverse docking workflow. Key features include: (1) support for two established docking engines (AutoDock Vina and idock) with a hybrid scoring scheme (Vina_SFCT, combining the Vina score with a scoring function correction term (SFCT)); (2) pre‐processed target libraries covering the human proteome and DrugBank pharmacologically active targets; (3) support for custom target libraries and fully automated local execution. Benchmark evaluations demonstrate that idock operates over 40 times faster than AutoDock Vina. For multiple‐target drugs, Vina_SFCT outperforms the default scoring function in identifying biologically relevant targets. Furthermore, incorporating protein family information leads to increased hit rates, suggesting enhanced predictive power for real‐world applications. By combining robust methodology with user‐centric design, AutoRevDock offers a scalable solution for high‐throughput target fishing in drug discovery. The toolkit is freely available at https://github.com/AI4Bio-GuoLAB/AutoRevDock.git.
Bibliography:Nir Ben‐Tal
Review Editor
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0961-8368
1469-896X
1469-896X
DOI:10.1002/pro.70358