Utilizing machine learning-based QSAR model to overcome standalone consensus docking limitation in beta-lactamase inhibitors screening - a proof-of-concept study

Aug 6, 2026

Upload by Aurora

Virtual drug screening commonly uses consensus docking, which combines results from optimized docking experiments but often yields a lower success rate than the best single docking method due to its mathematical nature. This proof-of-concept study aims to overcome that limitation by integrating a random forest ensemble with quantitative structure-activity relationship (QSAR) modeling. In vitro beta-lactamase inhibitory screening validated docking-derived predictions after optimization of AutoDock Vina and DOCK6 protocols. DOCK6 achieved up to 70% identification of actives, while random-forest QSAR restored success to ~70% with false positives around 21%.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Abstract

Highlights

Introduction

Consensus docking limitations in virtual screening

Role of QSAR and machine learning in improving docking accuracy

Study rationale and optimization goals

Pitakbut etal. BMC Chemistry (2024) 18:249 [https://doi.org/10.1186/s13065-024-01324-x](https://doi.org/10.1186/s13065-024-01324-x) BMC Chemistry RESEARCH Open Access Utilizing machine learning-based QSAR model to overcome standalone consensus docking limitation in beta-lactamase inhibitors screening: a proof-of-concept study Thanet Pitakbut 1,3, Jennifer Munkert 1,2, Wenhui Xi3, Yanjie Wei3 and Gregor Fuhrmann 1,2* Abstract In virtual drug screening, consensus docking is a standard in-sil ico approach consisting of a combined result from optimized docking experiments, a minimum of two results combination. Therefore, consensus docking is subjected to a lower success rate than the best docking method due to its mathematical nature, an unavoidable limitation. This study aims to overcome this drawback via random forest, an ensemble machine learning model. First, in vitro beta-lactamase inhibitory screening was performed using an in-house chemical library. The in vitro results were later used as a validation. Consequently, we optimized docking protocols for AutoDock Vina and DOCK6 programs. With an appropriate scoring function, we found that DOCK6 could identify up to 70% of all active molecules, double the inappropriate. Further consensus analysis reduced the success rate to 50% . Simultaneously, a false positive rate was down to 16%, which was experimentally favorable for a drug search. Finally, we trained two quantitative structure-activity relationship (QSAR) models using logistic regression as a reference model and a random forest as a test model. After combining consensus docking results, random forest-based QSAR outperformed a logistic regression by restoring the success rate to 70% and maintaining a low false positive rate of around 21% . In conclusion, this study demonstrated the benefit of using a random forest (machine learning) -based QSAR model to overcome a standard consensus docking limitation in beta-lactamase inhibitor search as a proof-of-concept. Highlights • An optimized DOCK6 scoring can maximize the success in identifying active molecules by up to 70% . • Consensus docking can significantly reduce the false positive rate in determining experimental bioactive molecules compared to the best docking. • Integrating a random forest-based QSAR model into a virtual screening workflow extends the limited success rate of consensus docking. • An in-house screening reveals the first-time report of three bio beta-lactamase inhibitors. *Correspondence: Gregor Fuhrmann [gregor.fuhrmann@fau.de](gregor.fuhrmann@fau.de) Full list of author information is available at the end of the article © The Author(s) 2024. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creativecommons.org/l](http://creativecommons.org/l)icenses/by/4.0/. Graphical abstract Keywords Molecular docking, Consensus docking, Random forest-based QSAR model, Beta-lactamase inhibitory screening Introduction Since its introduction in the 1970s, computational-aided drug discovery and design (CADD) has continuously developed. A recent publication states that molecular docking is still among the most popular drug research tools used by leading academic laboratories and pharmaceut

FAQs

What limitation does the study target in consensus docking?

Consensus docking often produces a lower success rate than the best docking method because its combined, mathematical nature limits performance.

How is the random forest approach used in the workflow?

Two QSAR models are trained, using logistic regression as reference and random forest as the test model, and then combined with consensus docking results to improve success while keeping false positives low.

What were the key performance outcomes reported?

With an appropriate scoring function, DOCK6 identified up to 70% of active molecules; subsequent consensus analysis reduced success to 50%, while random-forest-based QSAR restored success to around 70% with false positives around 21%.

Aug 6, 2026

Upload by Aurora