Benchmarking AlphaFold ‐enabled molecular docking predictions for antibiotic discovery
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...
| Main Authors: | , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
EMBO
2023
|
| Online Access: | https://hdl.handle.net/1721.1/147788 |
| _version_ | 1811076570038665216 |
|---|---|
| author | Wong, Felix Krishnan, Aarti Zheng, Erica J Stärk, Hannes Manson, Abigail L Earl, Ashlee M Jaakkola, Tommi Collins, James J |
| author2 | Massachusetts Institute of Technology. Department of Biological Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Biological Engineering Wong, Felix Krishnan, Aarti Zheng, Erica J Stärk, Hannes Manson, Abigail L Earl, Ashlee M Jaakkola, Tommi Collins, James J |
| author_sort | Wong, Felix |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T10:24:16Z |
| format | Article |
| id | mit-1721.1/147788 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T10:24:16Z |
| publishDate | 2023 |
| publisher | EMBO |
| record_format | dspace |
| spelling | mit-1721.1/1477882023-02-01T03:42:39Z Benchmarking AlphaFold ‐enabled molecular docking predictions for antibiotic discovery Wong, Felix Krishnan, Aarti Zheng, Erica J Stärk, Hannes Manson, Abigail L Earl, Ashlee M Jaakkola, Tommi Collins, James J Massachusetts Institute of Technology. Department of Biological Engineering 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. 2023-01-30T19:08:03Z 2023-01-30T19:08:03Z 2022 2023-01-30T18:53:03Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/147788 Wong, Felix, Krishnan, Aarti, Zheng, Erica J, Stärk, Hannes, Manson, Abigail L et al. 2022. "Benchmarking AlphaFold ‐enabled molecular docking predictions for antibiotic discovery." Molecular Systems Biology, 18 (9). en 10.15252/MSB.202211081 Molecular Systems Biology Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf EMBO Wiley |
| spellingShingle | Wong, Felix Krishnan, Aarti Zheng, Erica J Stärk, Hannes Manson, Abigail L Earl, Ashlee M Jaakkola, Tommi Collins, James J Benchmarking AlphaFold ‐enabled molecular docking predictions for antibiotic discovery |
| 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 |
| url | https://hdl.handle.net/1721.1/147788 |
| work_keys_str_mv | AT wongfelix benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery AT krishnanaarti benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery AT zhengericaj benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery AT starkhannes benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery AT mansonabigaill benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery AT earlashleem benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery AT jaakkolatommi benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery AT collinsjamesj benchmarkingalphafoldenabledmoleculardockingpredictionsforantibioticdiscovery |