Turning high-throughput structural biology into predictive inhibitor design

A common challenge in drug design pertains to finding chemical modifications to a ligand that increases its affinity to the target protein. An underutilised advance is the increase in structural biology throughput, which has progressed from an artisanal endeavour to a monthly throughput of up to 100 different ligands against a protein in modern synchrotrons. However, the missing piece is a framework that turns high throughput crystallography data into predictive models for ligand design. Here we designed a simple machine learning approach that predicts protein-ligand affinity from experimental structures of diverse ligands against a single protein paired with biochemical measurements. Our key insight is using physics-based energy descriptors to represent protein-ligand complexes, and a learning-to-rank approach that infers the relevant differences between binding modes. We ran a high throughput crystallography campaign against the SARS-CoV-2 Main Protease (MPro), obtaining parallel measurements of over 200 protein-ligand complexes and the binding activity. This allows us to design a one-step library syntheses which improved the potency of two distinct micromolar hits by over 10-fold, arriving at a non-covalent and non-peptidomimetic inhibitor with 120 nM antiviral efficacy. Crucially, our approach successfully extends ligands to unexplored regions of the binding pocket, executing large and fruitful moves in chemical space with simple chemistry.

COVID Moonshot: Open Science Discovery of SARS-CoV-2 Main Protease Inhibitors by Combining Crowdsourcing, High-Throughput Experiments, Computational Simulations, and Machine Learning

<div><div><div><p>Herein we provide a living summary of the data generated during the COVID Moonshot project focused on the development of SARS-CoV-2 main protease (Mpro) inhibitors. Our approach uniquely combines crowdsourced medicinal chemistry insights with high throughput crystallography, exascale computational chemistry infrastructure for simulations, and machine learning in triaging designs and predicting synthetic routes. This manuscript describes our methodologies leading to both covalent and non-covalent inhibitors displaying protease IC50 values under 150 nM and viral inhibition under 5 uM in multiple different viral replication assays. Furthermore, we provide over 200 crystal structures of fragment-like and lead-like molecules in complex with the main protease. Over 1000 synthesized and ordered compounds are also reported with the corresponding activity in Mpro enzymatic assays using two different experimental setups. The data referenced in this document will be continually updated to reflect the current experimental progress of the COVID Moonshot project, and serves as a citable reference for ensuing publications. All of the generated data is open to other researchers who may find it of use.<br></p></div></div></div>

COVID Moonshot: Open Science Discovery of SARS-CoV-2 Main Protease Inhibitors by Combining Crowdsourcing, High-Throughput Experiments, Computational Simulations, and Machine Learning

<div><div><div><p>Herein we provide a living summary of the data generated during the COVID Moonshot project focused on the development of SARS-CoV-2 main protease (Mpro) inhibitors. Our approach uniquely combines crowdsourced medicinal chemistry insights with high throughput crystallography, exascale computational chemistry infrastructure for simulations, and machine learning in triaging designs and predicting synthetic routes. This manuscript describes our methodologies leading to both covalent and non-covalent inhibitors displaying protease IC50 values under 150 nM and viral inhibition under 5 uM in multiple different viral replication assays. Furthermore, we provide over 200 crystal structures of fragment-like and lead-like molecules in complex with the main protease. Over 1000 synthesized and ordered compounds are also reported with the corresponding activity in Mpro enzymatic assays using two different experimental setups. The data referenced in this document will be continually updated to reflect the current experimental progress of the COVID Moonshot project, and serves as a citable reference for ensuing publications. All of the generated data is open to other researchers who may find it of use.<br></p></div></div></div>

COVID Moonshot: Open Science Discovery of SARS-CoV-2 Main Protease Inhibitors by Combining Crowdsourcing, High-Throughput Experiments, Computational Simulations, and Machine Learning

Herein we provide a living summary of the data generated during the COVID Moonshot project focused on the development of SARS-CoV-2 main protease (Mpro) inhibitors. Our approach uniquely combines crowdsourced medicinal chemistry insights with high throughput crystallography, exascale computational chemistry infrastructure for simulations, and machine learning in triaging designs and predicting synthetic routes. This manuscript describes our methodologies leading to both covalent and non-covalent inhibitors displaying protease IC50 values under 150 nM and viral inhibition under 5 uM in multiple different viral replication assays. Furthermore, we provide over 200 crystal structures of fragment-like and lead-like molecules in complex with the main protease. Over 1000 synthesized and ordered compounds are also reported with the corresponding activity in Mpro enzymatic assays using two different experimental setups. The data referenced in this document will be continually updated to reflect the current experimental progress of the COVID Moonshot project, and serves as a citable reference for ensuing publications. All of the generated data is open to other researchers who may find it of use.

Rapid covalent-probe discovery by electrophile fragment screening

Covalent probes can display unmatched potency, selectivity and duration of action, however, their discovery is challenging. In principle, fragments that can irreversibly bind their target can overcome the low affinity that limits reversible fragment screening. Such electrophilic fragments were considered non-selective and were rarely screened. We hypothesized that mild electrophiles might overcome the selectivity challenge, and constructed a library of 993 mildly electrophilic fragments. We characterized this library by a new high-throughput thiol-reactivity assay and screened them against ten cysteine-containing proteins. Highly reactive and promiscuous fragments were rare and could be easily eliminated. By contrast, we found selective hits for most targets. Combination with high-throughput crystallography allowed rapid progression to potent and selective probes for two enzymes, the deubiquitinase OTUB2, and the pyrophosphatase NUDT7. No inhibitors were previously known for either. This study highlights the potential of electrophile fragment screening as a practical and efficient tool for covalent ligand discovery.