![Author ORCID: We display the ORCID iD icon alongside authors names on our website to acknowledge that the ORCiD has been authenticated when entered by the user. To view the users ORCiD record click the icon. [opens in a new tab]](https://chemrxiv.org/engage/assets/public/chemrxiv/images/logos/orcid.png)
Abstract
In this study, we introduce DockM8, an innovative open-source platform designed for consensus virtual screening in drug design. Leveraging various docking algorithms and scoring functions, DockM8 provides a highly customizable workflow for structure-based virtual screening. In rigorous evaluations across the DEKOIS 2.0, DUD-E, and Lit-PCBA datasets, DockM8 not only met but frequently surpassed state-of-the-art methods. Achieving average enrichments of 27%, 47.5%, and 13% respectively, DockM8 has proven its exceptional adaptability and generalizability across a variety of targets. Our study emphasizes the importance of tailoring the virtual screening strategy to specific targets, suggesting that no single pose selection or consensus method universally outperforms others. DockM8's user-friendly interface and minimal programming requirements make advanced virtual screening accessible to a broader scientific community. DockM8 is freely available at https://github.com/DrugBud-Suite/DockM8.
Supplementary materials
Title
Supporting Information
Description
Supporting Information containing the list of targets used in DUD-E, DEKOIS and Lit-PCBA. Contains further plots related to the benchmarking of DockM8 on DUD-E, DEKOIS and Lit-PCBA.
Actions
Title
DEKOIS Literature Data
Description
Performance metrics for selected literature methods on the DEKOIS 2.0 dataset. AUC, AUC-ROC, BEDROC, EF 0.5\%, EF 1\%, and EF 5\% are provided where available. Links to the relevant publications where the data was extracted from are also provided.
Actions
Title
DUD-E Literature Data
Description
Performance metrics for selected literature methods on the DUD-E dataset. AUC, AUC-ROC, BEDROC and EF 1\% are provided where available. Links to the relevant publications where the data was extracted from are also provided.
Actions
Title
Lit-PCBA Literature Data
Description
Performance metrics for selected literature methods on the Lit-PCBA dataset. AUC, AUC-ROC, BEDROC, EF 0.5\%, EF 1\% and EF 5\% are provided where available. Links to the relevant publications where the data was extracted from are also provided.
Actions
Title
DockM8-max methods for the DEKOIS dataset
Description
Performance metrics for DockM8-max on the DEKOIS 2.0 dataset. AUC, AUC-ROC, BEDROC, EF 0.5\%, EF 1\% and EF 5\% are provided.
Actions
Title
DockM8-max methods for the DUD-E dataset
Description
Performance metrics for DockM8-max on the DUD-E dataset. AUC, AUC-ROC, BEDROC, EF 0.5\%, EF 1\% and EF 5\% are provided.
Actions
Title
DockM8-max methods for the Lit-PCBA dataset
Description
Performance metrics for DockM8-max on the Lit-PCBA dataset. AUC, AUC-ROC, BEDROC, EF 0.5\%, EF 1\% and EF 5\% are provided.
Actions
