Skip to content
Open access

DockM8: an all-in-one open-source platform for consensus virtual screening in drug design

Sep 2026 · Journal of Cheminformatics · Vol 18 · 4 citations · 79 references
Medicine Computer Science

TL;DR

DockM8 is, to the authors' knowledge, the most comprehensive open-source platform to integrate the complete consensus structure-based virtual screening pipeline within a single, graphical-interface-driven tool, yielding over 55 million configurable protocols, a breadth unmatched by previously published consensus docking software.

Abstract

Virtual screening remains a critical step in structure-based drug design, yet variability in docking algorithms and scoring functions often limits its reliability. To address this challenge, we introduce DockM8, an open-source platform for consensus virtual screening that integrates pocket detection, ligand preparation, docking, rescoring, and consensus ranking within a single modular workflow. DockM8 supports five docking engines, 17 pose-selection methods, 17 scoring functions (SFs), and five consensus methods, all accessible through both a graphical user interface (GUI) and a Python application programming interface (API). Systematic evaluation on the DEKOIS 2.0, DUD-E, and Lit-PCBA datasets yielded median relative enrichments of 100%, 82.59%, and 8.85%, respectively, frequently matching or outperforming state-of-the-art approaches. Our findings further reveal that no pose-selection or consensus strategy universally excels, emphasizing the need for tailored, target-specific workflows. DockM8 is freely available under the GNU General Public License at https://github.com/DrugBud-Suite/DockM8. Scientific contribution DockM8 is, to our knowledge, the most comprehensive open-source platform to integrate the complete consensus structure-based virtual screening (SBVS) pipeline within a single, graphical-interface-driven tool, yielding over 55 million configurable protocols, a breadth unmatched by previously published consensus docking software. Through systematic multi-benchmark evaluation, we demonstrate that no single pose-selection or consensus strategy generalizes across targets, motivating a target-specific workflow-selection paradigm in place of prevailing one-size-fits-all heuristics. By delivering this tunability through a graphical interface rather than scripts, DockM8 brings rigorous, reproducible consensus virtual screening within reach of non-specialist medicinal chemists.

Read PDF

Similar papers

#software testing Open access Sep 2026

Pose Reproduction, Cross Docking, Database Enrichment, and Reverse Docking Benchmarks for DOCK6, Vina, and AutoDock 4 with Emphasis on Approved Drugs

This work introduces SB2025, a calculation-ready set of 1,244 protein-ligand complexes derived from the PDB, curated using literature-based ligand protonation states, and freely available in DOCK6, AutoDock Vina, and AutoDock 4 (AD4) formats.

Carissa P. Corbo, Scott Laverty, Robert C. Rizzo · 0 citations
#machine learning Preprint Oct 2026

PMO-Dock: Benchmarking Docking, Specificity, and Generalization in Molecular Optimization

This work introduces Practical Molecular Optimization for Docking (PMO-Dock), a benchmark and protocol for docking-based optimization consisting of 25 tasks covering hit generation, lead optimization, and a new specificity task requiring strong on-target binding while penalizing off-target interactions.

Gor Simonyan, Tatevik Abrahamyan, N. Abelyan et al. · 0 citations

In Silico Drug Design of Chikungunya Antivirals: Using Consensus Methods for Virtual Screening.

This chapter will conduct a virtual screening using AutoDock Vina, AutoDock4, and LeDock, and then combine their results employing the Exponential Consensus Ranking algorithm, to improve the predictive power of virtual screening and increase the probability of identifying true binders.

Leandro Battini · 0 citations
Open access Oct 2026

Democratizing Drug Discovery: A Scalable Open-Source Pipeline for Massive Specific Protein Target QSAR Modeling Using ChEMBL

The proprietary nature of AI/ML tools in drug discovery limits access to advanced virtual screening methodologies. To address this, we present an open-source, automated pipeline for large-scale Quantitative Structure−Activity Relationship (QSAR) modeling utilizing ChEMBL. Our batch processing system constructed 2263...

A. Zaliani, Arianna Pisati, A. Pozzi et al. · 0 citations
Review Sep 2026

Exploring Optimal Parameters for Ligand-Based Virtual Screening in Early Drug Discovery

The results support a staged screening design in which a pooled default is followed by ligand-specific calibration and expert review, and SCScore showed the highest association with the blinded consensus, but performance varied by ligand.

T. Sobodu, Victoria Johnson, Ryan Kern et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.