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 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.

Authors

Institutions

Publication Details

Journal
Journal of Chemical Information and Modeling
Published
2026-02-26
DOI
https://doi.org/10.1021/acs.jcim.5c02106
Citations
1
Primary Topic
Computational Drug Discovery Methods
Type
article
Field-Weighted Citation Impact
45.17
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A Computational Community Blind Challenge on Pan-Coronavirus Drug Discovery Data

Satya Pratik Srivastava, Giovanni Tricarico, Antonia S. J. S. Mey, Wim Dehaen et al.
1 citations
Journal of Chemical Information and Modeling
Computational Drug Discovery Methods
45.17
article

A Computational Community Blind Challenge on Pan-Coronavirus Drug Discovery Data

Satya Pratik Srivastava, Giovanni Tricarico, Antonia S. J. S. Mey, Wim Dehaen, Johan Hofmans, Floriane Montanari, Chien-Chih Wang, Ruel Cedeno, Azmine Toushik Wasi, Dave West, Irfan Alibay, Bruce A. Lefker, Ralph P. Robinson, Austin Tripp, Christoph Schran, Tamás Szommer, Galit Cohen, Peter Sjö, Van Ngoc Thuy La, Lianjin Cai, Jessica Stacey, Weijun Zhou, Marie-Pierre Dréanic, Haim Michael Barr, Noa Lahav, Kevin P. Bishop, Michael Lavi, Ryan Renslow, Ed Griffen, Lauren Reid, Teresa L. Head-Gordon, Long-Hung Dinh Pham, Kenneth Goossens, Bathmapriya Balakrishnan, Eelke B. Lenselink, Wojtek Treyde, Oscar Méndez‐Lucio, Kunyang Sun, John K. Fraser, Patrick Maher, Vladimir Chupakhin, Taoyu Niu, Finlay Clark, Zhaoxi Sun, Alexander Matthew Payne, Mallory R. Tollefson, Gerhard Wolber, Sean Colby, David L. Cousins, Maria A. Castellanos, Cas Wognum, Justin Purnomo, Rokas Elijošius, Yaowen Gu, Ashmita Bose, Karla Kirkegaard, Ida Titus, Mounika Srilakshmi, Muhammad Danial, Bofei Xu, Niklas Piet Doering, Alexis Dougha, Shirley Duberstein, Julien St-Laurent, Honore Etsmoberg, Bryce Eakin, Jozef Fülöp, Asma Feriel Khoualdi, Ryusei Ogino, Nopsinth Vithayapalert, Steffen Wedig, Rajeev Kumar Singh, Yue Liu, Sina Khosravi, Xiaolin Pan, Frank von Delft, Hugo Bohorquez, Sijie Liu, Luis Pinto, Laurent Hoffer, Daren Fearon, Ellena Jiang, Carles Corbi-Verge, Yizhou Ma, Anatol Ehrlich, Jonny Hsu, Hugo MacDermott-Opeskin, Cynthia Xu, Alec Davi, Andrew Quirke, Lars L. Schaaf, Blake Balcomb, Benjamin Kaminow, Daniel J. Cole, Imke Mayer, Alex Rich, John D. Chodera, Gwendolyn Fate, David D. L. Minh, Max Winokan, Ashok Palaniappan, Lu Zhu, Kate Huddleston, C. J. Brown, Stephane de Cesco, Valerij Talagayev, Alexandre Tkatchenko, Jasmin Cara Aschenbrenner, Alpha Lee, Lulu Kang, Auro Patnaik, Nick Lynch, Joshua T. Horton, Benjamin Birnbaum, Ryan Lithgo, Jackson Burns, W. Patrick Walters, Zhirong Liu, Mohamed Iliyas Abdul Haleem, Julien Michel, Charles W. E. Tomlinson, Jenke Scheen, Gunjan Baid
article en
1 citations

Abstract

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.

Journal of Chemical Information and ModelingVol. 66(6)
Quanta Technology (United States) (US), Ontario Institute for Cancer Research (CA), University of Nebraska–Lincoln (US), University of Vienna (AT), Drugs for Neglected Diseases Initiative (CH), Shahjalal University of Science and Technology (BD), Memorial Sloan Kettering Cancer Center (US), University of Wisconsin–Madison (US), Mashhad University of Medical Sciences (IR), University of Pittsburgh (US), Universidade de São Paulo (BR), University of California, San Francisco (US), Shenzhen University (CN), Illinois Institute of Technology (US), University of Luxembourg (LU), Peking University (CN), Université Paris Cité (FR), Heidelberg University (DE), University of Cambridge (GB), University of Massachusetts Amherst (US), Shiv Nadar University (IN), Discovery Centre (CA), Post University (US), Beijing Film Academy (CN), Diamond Light Source (GB), Morgridge Institute for Research (US), University of Oxford (GB), Thames Water (United Kingdom) (GB), Novavax (United States) (US), Tri-Institutional PhD Program in Chemical Biology (US), Japan Tobacco (Japan) (JP), Moscow Institute of Thermal Technology (RU), Vetenskap I Skolan (SE), Relay Therapeutics (United States) (US), The Alan Turing Institute (GB), Centre Hospitalier de Valence (FR), PharmaZell (Germany) (DE), Shenzhen Institutes of Advanced Technology (CN), University of Bío-Bío (CL), Shenzhen Technology University (CN), Recursion (United States) (US), 21c Consultancy (United Kingdom) (GB), Open Molecular Software Foundation, Imperial College London (GB), Weizmann Institute of Science (IL), New York University (US), Freie Universität Berlin (DE), Newcastle University (GB), Simulations Plus (United States) (US), University of Chemistry and Technology, Prague (CZ), SASTRA University (IN), University of California, Berkeley (US), Stanford University (US), University of Edinburgh (GB)
Industry, innovation and infrastructure
Openalex Percentile: Top 0%
Computational Drug Discovery Methods
45.17
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.