GPU-accelerated Chemical Similarity Assessment for Large Scale Databases
The assessment of chemical similarity between molecules is a basic operation in chemoinformatics, a computational area concerning with the manipulation of chemical structural information. Comparing molecules is the basis for a wide range of applications such as searching in chemical databases, train...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Elsevier B.V.
2014
|
| Online Access: | http://hdl.handle.net/1721.1/92298 |
| _version_ | 1826210028937281536 |
|---|---|
| author | Maggioni, Marco Santambrogio, Marco Domenico Liang, Jie |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Maggioni, Marco Santambrogio, Marco Domenico Liang, Jie |
| author_sort | Maggioni, Marco |
| collection | MIT |
| description | The assessment of chemical similarity between molecules is a basic operation in chemoinformatics, a computational area concerning with the manipulation of chemical structural information. Comparing molecules is the basis for a wide range of applications such as searching in chemical databases, training prediction models for virtual screening or aggregating clusters of similar compounds. However, currently available multimillion databases represent a challenge for conventional chemoinformatics algorithms raising the necessity for faster similarity methods. In this paper, we extensively analyze the advantages of using many-core architectures for calculating some commonly-used chemical similarity coe_cients such as Tanimoto, Dice or Cosine. Our aim is to provide a wide-breath proof-of-concept regarding the usefulness of GPU architectures to chemoinformatics, a class of computing problems still uncovered. In our work, we present a general GPU algorithm for all-to-all chemical comparisons considering both binary fingerprints and floating point descriptors as molecule representation. Subsequently, we adopt optimization techniques to minimize global memory accesses and to further improve e_ciency. We test the proposed algorithm on different experimental setups, a laptop with a low-end GPU and a desktop with a more performant GPU. In the former case, we obtain a 4-to-6-fold speed-up over a single-core implementation for fingerprints and a 4-to-7-fold speed-up for descriptors. In the latter case, we respectively obtain a 195-to-206-fold speed-up and a 100-to-328-fold speed-up. |
| first_indexed | 2024-09-23T14:40:11Z |
| format | Article |
| id | mit-1721.1/92298 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:40:11Z |
| publishDate | 2014 |
| publisher | Elsevier B.V. |
| record_format | dspace |
| spelling | mit-1721.1/922982022-09-29T10:04:33Z GPU-accelerated Chemical Similarity Assessment for Large Scale Databases Maggioni, Marco Santambrogio, Marco Domenico Liang, Jie Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Santambrogio, Marco Domenico The assessment of chemical similarity between molecules is a basic operation in chemoinformatics, a computational area concerning with the manipulation of chemical structural information. Comparing molecules is the basis for a wide range of applications such as searching in chemical databases, training prediction models for virtual screening or aggregating clusters of similar compounds. However, currently available multimillion databases represent a challenge for conventional chemoinformatics algorithms raising the necessity for faster similarity methods. In this paper, we extensively analyze the advantages of using many-core architectures for calculating some commonly-used chemical similarity coe_cients such as Tanimoto, Dice or Cosine. Our aim is to provide a wide-breath proof-of-concept regarding the usefulness of GPU architectures to chemoinformatics, a class of computing problems still uncovered. In our work, we present a general GPU algorithm for all-to-all chemical comparisons considering both binary fingerprints and floating point descriptors as molecule representation. Subsequently, we adopt optimization techniques to minimize global memory accesses and to further improve e_ciency. We test the proposed algorithm on different experimental setups, a laptop with a low-end GPU and a desktop with a more performant GPU. In the former case, we obtain a 4-to-6-fold speed-up over a single-core implementation for fingerprints and a 4-to-7-fold speed-up for descriptors. In the latter case, we respectively obtain a 195-to-206-fold speed-up and a 100-to-328-fold speed-up. National Institutes of Health (U.S.) (grant GM079804) National Institutes of Health (U.S.) (grant GM086145) 2014-12-12T19:16:42Z 2014-12-12T19:16:42Z 2011 Article http://purl.org/eprint/type/JournalArticle 18770509 http://hdl.handle.net/1721.1/92298 Maggioni, Marco, Marco Domenico Santambrogio, and Jie Liang. “GPU-Accelerated Chemical Similarity Assessment for Large Scale Databases.” Procedia Computer Science 4 (2011): 2007–2016. © 2011 Elsevier B.V. en_US http://dx.doi.org/10.1016/j.procs.2011.04.219 Procedia Computer Science Creative Commons Attribution http://creativecommons.org/licenses/by-nc-nd/3.0/ application/pdf Elsevier B.V. Elsevier |
| spellingShingle | Maggioni, Marco Santambrogio, Marco Domenico Liang, Jie GPU-accelerated Chemical Similarity Assessment for Large Scale Databases |
| title | GPU-accelerated Chemical Similarity Assessment for Large Scale Databases |
| title_full | GPU-accelerated Chemical Similarity Assessment for Large Scale Databases |
| title_fullStr | GPU-accelerated Chemical Similarity Assessment for Large Scale Databases |
| title_full_unstemmed | GPU-accelerated Chemical Similarity Assessment for Large Scale Databases |
| title_short | GPU-accelerated Chemical Similarity Assessment for Large Scale Databases |
| title_sort | gpu accelerated chemical similarity assessment for large scale databases |
| url | http://hdl.handle.net/1721.1/92298 |
| work_keys_str_mv | AT maggionimarco gpuacceleratedchemicalsimilarityassessmentforlargescaledatabases AT santambrogiomarcodomenico gpuacceleratedchemicalsimilarityassessmentforlargescaledatabases AT liangjie gpuacceleratedchemicalsimilarityassessmentforlargescaledatabases |