Efficient iterative virtual screening with Apache Spark and conformal prediction
Abstract Background Docking and scoring large libraries of ligands against target proteins forms the basis of structure-based virtual screening. The problem is trivially parallelizable, and calculations are generally carried out on computer clusters or on large workstations in a brute force manner,...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2018-03-01
|
| Series: | Journal of Cheminformatics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13321-018-0265-z |
| _version_ | 1830518860505153536 |
|---|---|
| author | Laeeq Ahmed Valentin Georgiev Marco Capuccini Salman Toor Wesley Schaal Erwin Laure Ola Spjuth |
| author_facet | Laeeq Ahmed Valentin Georgiev Marco Capuccini Salman Toor Wesley Schaal Erwin Laure Ola Spjuth |
| author_sort | Laeeq Ahmed |
| collection | DOAJ |
| description | Abstract Background Docking and scoring large libraries of ligands against target proteins forms the basis of structure-based virtual screening. The problem is trivially parallelizable, and calculations are generally carried out on computer clusters or on large workstations in a brute force manner, by docking and scoring all available ligands. Contribution In this study we propose a strategy that is based on iteratively docking a set of ligands to form a training set, training a ligand-based model on this set, and predicting the remainder of the ligands to exclude those predicted as ‘low-scoring’ ligands. Then, another set of ligands are docked, the model is retrained and the process is repeated until a certain model efficiency level is reached. Thereafter, the remaining ligands are docked or excluded based on this model. We use SVM and conformal prediction to deliver valid prediction intervals for ranking the predicted ligands, and Apache Spark to parallelize both the docking and the modeling. Results We show on 4 different targets that conformal prediction based virtual screening (CPVS) is able to reduce the number of docked molecules by 62.61% while retaining an accuracy for the top 30 hits of 94% on average and a speedup of 3.7. The implementation is available as open source via GitHub (https://github.com/laeeq80/spark-cpvs) and can be run on high-performance computers as well as on cloud resources. |
| first_indexed | 2024-12-22T04:27:00Z |
| format | Article |
| id | doaj.art-647b2172fc6b440c92b120f8f2e9bb73 |
| institution | Directory Open Access Journal |
| issn | 1758-2946 |
| language | English |
| last_indexed | 2024-12-22T04:27:00Z |
| publishDate | 2018-03-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Cheminformatics |
| spelling | doaj.art-647b2172fc6b440c92b120f8f2e9bb732022-12-21T18:39:08ZengBMCJournal of Cheminformatics1758-29462018-03-011011810.1186/s13321-018-0265-zEfficient iterative virtual screening with Apache Spark and conformal predictionLaeeq Ahmed0Valentin Georgiev1Marco Capuccini2Salman Toor3Wesley Schaal4Erwin Laure5Ola Spjuth6Department of Computational Science and Technology, Royal Institute of Technology (KTH)Department of Pharmaceutical Biosciences, Uppsala UniversityDepartment of Pharmaceutical Biosciences, Uppsala UniversityDepartment of Information Technology, Uppsala UniversityDepartment of Pharmaceutical Biosciences, Uppsala UniversityDepartment of Computational Science and Technology, Royal Institute of Technology (KTH)Department of Pharmaceutical Biosciences, Uppsala UniversityAbstract Background Docking and scoring large libraries of ligands against target proteins forms the basis of structure-based virtual screening. The problem is trivially parallelizable, and calculations are generally carried out on computer clusters or on large workstations in a brute force manner, by docking and scoring all available ligands. Contribution In this study we propose a strategy that is based on iteratively docking a set of ligands to form a training set, training a ligand-based model on this set, and predicting the remainder of the ligands to exclude those predicted as ‘low-scoring’ ligands. Then, another set of ligands are docked, the model is retrained and the process is repeated until a certain model efficiency level is reached. Thereafter, the remaining ligands are docked or excluded based on this model. We use SVM and conformal prediction to deliver valid prediction intervals for ranking the predicted ligands, and Apache Spark to parallelize both the docking and the modeling. Results We show on 4 different targets that conformal prediction based virtual screening (CPVS) is able to reduce the number of docked molecules by 62.61% while retaining an accuracy for the top 30 hits of 94% on average and a speedup of 3.7. The implementation is available as open source via GitHub (https://github.com/laeeq80/spark-cpvs) and can be run on high-performance computers as well as on cloud resources.http://link.springer.com/article/10.1186/s13321-018-0265-zVirtual screeningDockingConformal predictionCloud computingApache Spark |
| spellingShingle | Laeeq Ahmed Valentin Georgiev Marco Capuccini Salman Toor Wesley Schaal Erwin Laure Ola Spjuth Efficient iterative virtual screening with Apache Spark and conformal prediction Journal of Cheminformatics Virtual screening Docking Conformal prediction Cloud computing Apache Spark |
| title | Efficient iterative virtual screening with Apache Spark and conformal prediction |
| title_full | Efficient iterative virtual screening with Apache Spark and conformal prediction |
| title_fullStr | Efficient iterative virtual screening with Apache Spark and conformal prediction |
| title_full_unstemmed | Efficient iterative virtual screening with Apache Spark and conformal prediction |
| title_short | Efficient iterative virtual screening with Apache Spark and conformal prediction |
| title_sort | efficient iterative virtual screening with apache spark and conformal prediction |
| topic | Virtual screening Docking Conformal prediction Cloud computing Apache Spark |
| url | http://link.springer.com/article/10.1186/s13321-018-0265-z |
| work_keys_str_mv | AT laeeqahmed efficientiterativevirtualscreeningwithapachesparkandconformalprediction AT valentingeorgiev efficientiterativevirtualscreeningwithapachesparkandconformalprediction AT marcocapuccini efficientiterativevirtualscreeningwithapachesparkandconformalprediction AT salmantoor efficientiterativevirtualscreeningwithapachesparkandconformalprediction AT wesleyschaal efficientiterativevirtualscreeningwithapachesparkandconformalprediction AT erwinlaure efficientiterativevirtualscreeningwithapachesparkandconformalprediction AT olaspjuth efficientiterativevirtualscreeningwithapachesparkandconformalprediction |