A computational community blind challenge on pan-coronavirus drug discovery data
Computational blind challenges offer critical, unbiased opportunities to assess and accelerate scientific progress, as demonstrated by a breadth of breakthroughs over the past decade. We report the outcomes and key insights from an open science community blind challenge focused on computational meth...
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Article (Journal) |
| Lingua: | inglese |
| Pubblicazione: |
23 March 2026
|
| In: |
Journal of chemical information and modeling
Year: 2026, Volume: 66, Fascicolo: 6, Pages: 3129-3149 |
| ISSN: | 1549-960X |
| DOI: | 10.1021/acs.jcim.5c02106 |
| Accesso online: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1021/acs.jcim.5c02106
|
| Note sull'autore: | Hugo MacDermott-Opeskin, Jenke Scheen, Cas Wognum, Joshua T. Horton, Devany West, Alexander Matthew Payne, Maria A. Castellanos, Sean Colby, Edward Griffen, David Cousins, Jessica Stacey, Lauren Reid, Jasmin Cara Aschenbrenner, Daren Fearon, Blake Balcomb, Peter Marples, Charles W.E. Tomlinson, Ryan Lithgo, Andre S. Godoy, Max Winokan, Haim Barr, Noa Lahav, Michael Lavi, Shirley Duberstein, Galit Cohen, Gwendolyn Fate, Bruce Lefker, Ralph Robinson, Tamas Szommer, Nick Lynch, David D. L. Minh, Van Ngoc Thuy La, Lulu Kang, Kate Huddleston, Ryan Renslow, Mallory Tollefson, W. Patrick Walters, Cynthia Xu, Jonny Hsu, Julien St-Laurent, Honore Etsmoberg, Lu Zhu, Andrew Quirke, Mohamed Iliyas Abdul Haleem, Irfan Alibay, Gunjan Baid, Benjamin Birnbaum, Kevin P. Bishop, Hugo Bohorquez, Ashmita Bose, C.J. Brown, Jackson Burns, Lianjin Cai, Ruel Cedeno, Stephane de Cesco, Vladimir Chupakhin, Finlay Clark, Daniel J. Cole, Carles Corbi-Verge, Muhammad Danial, Alec Davi, Wim Dehaen, Niklas Piet Doering, Alexis Dougha, Marie-Pierre Dréanic, Bryce Eakin, Anatol Ehrlich, Rokas Elijosius, Jozef Fülöp, Anthony Gitter, Kenneth Goossens, Yaowen Gu, Teresa Head-Gordon, Laurent Hoffer, Johan Hofmans, Ellena Jiang, Benjamin Kaminow, Sina Khosravi, Asma Feriel Khoualdi, Eelke Bart Lenselink, Zhirong Liu, Yue Liu, Sijie Liu, Yizhou Ma, Patrick Maher, Imke Mayer, Oscar Mendez-Lucio, Antonia S.J.S. Mey, Julien Michel, Floriane Montanari, Taoyu Niu, Ryusei Ogino, Ashok Palaniappan, Xiaolin Pan, Auro Patnaik, Long-Hung Pham, Luis Pinto, Justin Purnomo, Alex Rich, Lars Schaaf, Christoph Schran, Rajeev Kumar Singh, Mounika Srilakshmi, Satya Pratik Srivastava, Kunyang Sun, Zhaoxi Sun, Valerij Talagayev, Balamurugan Thirukonda Subramanian Balakrishnan, Ida Titus, Alexandre Tkatchenko, Wojtek Treyde, Giovanni Tricarico, Austin Tripp, Nopsinth Vithayapalert, Yingze Wang, Azmine Toushik Wasi, Steffen Wedig, Gerhard Wolber, Bofei Xu, Weijun Zhou, Frank von Delft, Alpha Lee, Karla Kirkegaard, Peter Sjö, James S. Fraser, and John D. Chodera |
| Riassunto: | Computational blind challenges offer critical, unbiased opportunities to assess and accelerate scientific progress, as demonstrated by a breadth of breakthroughs over the past decade. We report the outcomes and key insights from an open science community blind challenge focused on computational methods in drug discovery, using lead optimization data from the AI-driven Structure-enabled Antiviral Platform Discovery Consortium’s pan-coronavirus antiviral discovery program, in partnership with Polaris and the OpenADMET project. This collaborative initiative invited global participants from both academia and industry to develop and apply computational methods to predict the biochemical potency and crystallographic ligand poses of small molecules against key coronavirus targets, Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) and Middle East Respiratory Syndrome Coronavirus (MERS-CoV) main protease (Mpro), as well as multiple ADMET assay end points, using previously undisclosed comprehensive experimental drug discovery data sets as benchmarks. By evaluating submissions across multiple tasks and compounds, we established performance leaderboards and conducted meta-analyses to assess methodological strengths, common pitfalls, and areas for improvement. This analysis provides a foundation for best practices in real-world machine learning evaluation, grounded in community-driven benchmarking. We also highlight how next-generation platforms, such as Polaris, enable rigorous challenge design, embedded evaluation frameworks, and broad community engagement. This paper reports the collective findings of the challenge, offering a high-level overview of the data, evaluation infrastructure, and top-performing strategies. We further provide context and support for the accompanying papers authored by the challenge participants in this special issue, which explore individual approaches in greater depth. Together, these contributions aim to advance reproducible, trustworthy, and high-impact computational methods in drug discovery, and to explore best practices and pitfalls in future blind challenge design and execution, including planned initiatives for the OpenADMET project. |
|---|---|
| Descrizione del documento: | Online veröffentlicht: 26. Februar 2026 Gesehen am 17.06.2026 |
| Descrizione fisica: | Online Resource |
| ISSN: | 1549-960X |
| DOI: | 10.1021/acs.jcim.5c02106 |