Publications - FAST Group

2026

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 L. 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, John D. Chodera

A computational community blind challenge on pan-Coronavirus drug discovery data Journal Article

In: J. Chem. Inf. Model., vol. 66, iss. 6, pp. 3129–3149, 2026.

Abstract | Links | BibTeX | Tags: Cheminformatics, Computational Chemistry, Drug Discovery

@article{MacDermott-Opeskin2026/10.1021/acs.jcim.5c02106,

title = {A computational community blind challenge on pan-Coronavirus drug discovery data},

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

url = {https://pubs.acs.org/doi/full/10.1021/acs.jcim.5c02106},

doi = {10.1021/acs.jcim.5c02106},

year  = {2026},

date = {2026-02-26},

urldate = {2026-02-26},

journal = {J. Chem. Inf. Model.},

volume = {66},

issue = {6},

pages = {3129–3149},

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.},

keywords = {Cheminformatics, Computational Chemistry, Drug Discovery},

pubstate = {published},

tppubtype = {article}

}

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.