Benchmarking AlphaFold‐enabled molecular docking predictions for antibiotic discovery

Abstract Efficient identification of drug mechanisms of action remains a challenge. Computational docking approaches have been widely used to predict drug binding targets; yet, such approaches depend on existing protein structures, and accurate structural predictions have only recently become availa...

Full description

Saved in:
Bibliographic Details
Main Authors: Felix Wong, Aarti Krishnan, Erica J Zheng, Hannes Stärk, Abigail L Manson, Ashlee M Earl, Tommi Jaakkola, James J Collins
Format: Article
Language:English
Published: Springer Nature 2022-09-01
Series:Molecular Systems Biology
Subjects:
Online Access:https://doi.org/10.15252/msb.202211081
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235393729265664
author Felix Wong
Aarti Krishnan
Erica J Zheng
Hannes Stärk
Abigail L Manson
Ashlee M Earl
Tommi Jaakkola
James J Collins
author_facet Felix Wong
Aarti Krishnan
Erica J Zheng
Hannes Stärk
Abigail L Manson
Ashlee M Earl
Tommi Jaakkola
James J Collins
author_sort Felix Wong
collection DOAJ
description Abstract Efficient identification of drug mechanisms of action remains a challenge. Computational docking approaches have been widely used to predict drug binding targets; yet, such approaches depend on existing protein structures, and accurate structural predictions have only recently become available from AlphaFold2. Here, we combine AlphaFold2 with molecular docking simulations to predict protein‐ligand interactions between 296 proteins spanning Escherichia coli's essential proteome, and 218 active antibacterial compounds and 100 inactive compounds, respectively, pointing to widespread compound and protein promiscuity. We benchmark model performance by measuring enzymatic activity for 12 essential proteins treated with each antibacterial compound. We confirm extensive promiscuity, but find that the average area under the receiver operating characteristic curve (auROC) is 0.48, indicating weak model performance. We demonstrate that rescoring of docking poses using machine learning‐based approaches improves model performance, resulting in average auROCs as large as 0.63, and that ensembles of rescoring functions improve prediction accuracy and the ratio of true‐positive rate to false‐positive rate. This work indicates that advances in modeling protein‐ligand interactions, particularly using machine learning‐based approaches, are needed to better harness AlphaFold2 for drug discovery.
format Article
id doaj-art-ad22b6add92747ceac4e104098c84d2d
institution Kabale University
issn 1744-4292
language English
publishDate 2022-09-01
publisher Springer Nature
record_format Article
series Molecular Systems Biology
spelling doaj-art-ad22b6add92747ceac4e104098c84d2d2025-08-20T04:02:49ZengSpringer NatureMolecular Systems Biology1744-42922022-09-0118912010.15252/msb.202211081Benchmarking AlphaFold‐enabled molecular docking predictions for antibiotic discoveryFelix Wong0Aarti Krishnan1Erica J Zheng2Hannes Stärk3Abigail L Manson4Ashlee M Earl5Tommi Jaakkola6James J Collins7Institute for Medical Engineering & Science, Massachusetts Institute of TechnologyInstitute for Medical Engineering & Science, Massachusetts Institute of TechnologyInfectious Disease and Microbiome Program, Broad Institute of MIT and HarvardComputer Science and Artificial Intelligence Laboratory, Massachusetts Institute of TechnologyInfectious Disease and Microbiome Program, Broad Institute of MIT and HarvardInfectious Disease and Microbiome Program, Broad Institute of MIT and HarvardComputer Science and Artificial Intelligence Laboratory, Massachusetts Institute of TechnologyInstitute for Medical Engineering & Science, Massachusetts Institute of TechnologyAbstract Efficient identification of drug mechanisms of action remains a challenge. Computational docking approaches have been widely used to predict drug binding targets; yet, such approaches depend on existing protein structures, and accurate structural predictions have only recently become available from AlphaFold2. Here, we combine AlphaFold2 with molecular docking simulations to predict protein‐ligand interactions between 296 proteins spanning Escherichia coli's essential proteome, and 218 active antibacterial compounds and 100 inactive compounds, respectively, pointing to widespread compound and protein promiscuity. We benchmark model performance by measuring enzymatic activity for 12 essential proteins treated with each antibacterial compound. We confirm extensive promiscuity, but find that the average area under the receiver operating characteristic curve (auROC) is 0.48, indicating weak model performance. We demonstrate that rescoring of docking poses using machine learning‐based approaches improves model performance, resulting in average auROCs as large as 0.63, and that ensembles of rescoring functions improve prediction accuracy and the ratio of true‐positive rate to false‐positive rate. This work indicates that advances in modeling protein‐ligand interactions, particularly using machine learning‐based approaches, are needed to better harness AlphaFold2 for drug discovery.https://doi.org/10.15252/msb.202211081AlphaFold2enzymatic activitymachine learningmolecular dockingprotein‐ligand interactions
spellingShingle Felix Wong
Aarti Krishnan
Erica J Zheng
Hannes Stärk
Abigail L Manson
Ashlee M Earl
Tommi Jaakkola
James J Collins
Benchmarking AlphaFold‐enabled molecular docking predictions for antibiotic discovery
Molecular Systems Biology
AlphaFold2
enzymatic activity
machine learning
molecular docking
protein‐ligand interactions
title Benchmarking AlphaFold‐enabled molecular docking predictions for antibiotic discovery
title_full Benchmarking AlphaFold‐enabled molecular docking predictions for antibiotic discovery
title_fullStr Benchmarking AlphaFold‐enabled molecular docking predictions for antibiotic discovery
title_full_unstemmed Benchmarking AlphaFold‐enabled molecular docking predictions for antibiotic discovery
title_short Benchmarking AlphaFold‐enabled molecular docking predictions for antibiotic discovery
title_sort benchmarking alphafold enabled molecular docking predictions for antibiotic discovery
topic AlphaFold2
enzymatic activity
machine learning
molecular docking
protein‐ligand interactions
url https://doi.org/10.15252/msb.202211081
work_keys_str_mv AT felixwong benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery
AT aartikrishnan benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery
AT ericajzheng benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery
AT hannesstark benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery
AT abigaillmanson benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery
AT ashleemearl benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery
AT tommijaakkola benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery
AT jamesjcollins benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery