Support-Vector-Machine-Based Ranking Significantly Improves the Effectiveness of Similarity Searching Using 2D Fingerprints and Multiple Reference Compounds
Abstract
Similarity searching using molecular fingerprints is computationally efficient and a surprisingly effective virtual screening tool. In this study, we have compared ranking methods for similarity searching using multiple active reference molecules. Different 2D fingerprints were used as search tools and also as descriptors for a support vector machine (SVM) algorithm. In systematic database search calculations, a SVM-based ranking scheme consistently outperformed nearest neighbor and centroid approaches, regardless of the fingerprints that were tested, even if only very small training sets were used for SVM learning. The superiority of SVM-based ranking over conventional fingerprint methods is ascribed to the fact that SVM makes use of information about database molecules, in addition to known active compounds, during the learning phase.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Many other ML methods used in QSAR modeling include k-nearest neighbors, partial least squares, support vector machines, relevance vector machines, random forest, Gaussian processes, and boosting.
“To put DNNs into context for QSAR, there are many other ML methods used in QSAR modeling including k-nearest neighbors (kNN),53 partial least squares (PLS)54, support vector machines (SVM),55 relevance vector machines, (RVM),56 random forest (RF),57 Gaussian processes (GP),58 and boosting59.”
From QSAR without borders (2020) · cites this paper as [55]
Cites
An Introduction to Support Vector Machines and Other Kernel-based Learning Methods
Cristianini, N., & Shawe-Taylor, J. (2000) · doi:10.1017/cbo9780511801389 · Cited by 13,855 · see citing works
Advances in kernel methods: support vector learning
Schölkopf, B., Burges, C. J. C., & Smola, A. J. (1999) · doi:10.5555/299094 · Cited by 5,809 · see citing works
ZINC − A Free Database of Commercially Available Compounds for Virtual Screening
Irwin, J. J., & Shoichet, B. K. (2005) · Journal of Chemical Information and Modeling · doi:10.1021/ci049714+ · Cited by 4,058 · see citing works
An introduction to kernel-based learning algorithms
Müller, K. R., Mika, S., Rätsch, G., Tsuda, K., & Schölkopf, B. (2001) · IEEE Transactions on Neural Networks · doi:10.1109/72.914517 · Cited by 3,485 · see citing works
Integration of virtual and high-throughput screening
Bajorath, J. (2002) · Nature Reviews Drug Discovery · doi:10.1038/nrd941 · Cited by 935 · see citing works
Self-citationSimilarity-based virtual screening using 2D fingerprints
Willett, P. (2006) · Drug Discovery Today · doi:10.1016/j.drudis.2006.10.005 · Cited by 849 · see citing works
Drug design by machine learning: support vector machines for pharmaceutical data analysis
Burbidge, R., Trotter, M. W. B., Buxton, B. F., & Holden, S. B. (2001) · Computers & Chemistry · doi:10.1016/s0097-8485(01)00094-8 · Cited by 688 · see citing works
Byvatov, E., Fechner, U., Sadowski, J., & Schneider, G. (2003) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci0341161 · Cited by 569 · see citing works
Molecular similarity analysis in virtual screening: foundations, limitations and novel approaches
Geppert, H., & Bajorath, J. (2007) · Drug Discovery Today · doi:10.1016/j.drudis.2007.01.011 · Cited by 466 · see citing works
Self-citationGraph kernels for chemical informatics
Ralaivola, L., Swamidass, S. J., Saigo, H., & Baldi, P. (2005) · Neural Networks · doi:10.1016/j.neunet.2005.07.009 · Cited by 449 · see citing works
Mason, J. S., Morize, I., Menard, P. R., Cheney, D. L., Hulme, C., & Labaudinière, R. F. (1999) · Journal of Medicinal Chemistry · doi:10.1021/jm9806998 · Cited by 375 · see citing works
Active Learning with Support Vector Machines in the Drug Discovery Process
Warmuth, M. K., Liao, J., Rätsch, G., et al. (2003) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci025620t · Cited by 356 · see citing works
Hert, J., Willett, P., Wilton, D. J., Acklin, P., Azzaoui, K., Jacoby, E., & Schuffenhauer, A. (2004) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci034231b · Cited by 310 · see citing works
Virtual Screening of Molecular Databases Using a Support Vector Machine
Jorissen, R. N., & Gilson, M. K. (2005) · Journal of Chemical Information and Modeling · doi:10.1021/ci049641u · Cited by 258 · see citing works
The Characterization of Chemical Structures Using Molecular Properties. A Survey
Livingstone, D. J. (1999) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci990162i · Cited by 253 · see citing works
Similarity Metrics for Ligands Reflecting the Similarity of the Target Proteins
Schuffenhauer, A., Floersheim, P., Acklin, P., et al. (2002) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci025569t · Cited by 251 · see citing works
Bender, A., Mussa, H. Y., Glen, R. C., & Reiling, S. (2003) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci034207y · Cited by 246 · see citing works
Bajorath, J. (2001) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci0001482 · Cited by 227 · see citing works
Self-citationChemical Similarity Using Geometric Atom Pair Descriptors
Sheridan, R. P., Miller, M. D., Underwood, D. J., & Kearsley, S. K. (1996) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci950275b · Cited by 183 · see citing works
Clustering of Large Databases of Compounds: Using the MDL “Keys” as Structural Descriptors
McGregor, M. J., & Pallai, P. V. (1997) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci960151e · Cited by 181 · see citing works
Stigmata: An Algorithm To Determine Structural Commonalities in Diverse Datasets
Shemetulskis, N. E., Weininger, D., Blankley, C. J., Yang, J. J., & Humblet, C. C. (1996) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci950169+ · Cited by 159 · see citing works
Searching Techniques for Databases of Two- and Three-Dimensional Chemical Structures
Willett, P. (2005) · Journal of Medicinal Chemistry · doi:10.1021/jm0582165 · Cited by 151 · see citing works
Combinatorial informatics in the post-genomics era
Agrafiotis, D. K., Lobanov, V. S., & Salemme, F. R. (2002) · Nature Reviews Drug Discovery · doi:10.1038/nrd791 · Cited by 113 · see citing works
Xue, L., Godden, J. W., Stahura, F. L., et al. (2003) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci030287u · Cited by 61 · see citing works
Tovar, A. T., Geppert, H., & Bajorath, J. (2006) · ChemMedChem · doi:10.1002/cmdc.200600225 · Cited by 51 · see citing works
Self-citationVirtual Screening Using Binary Kernel Discrimination: Analysis of Pesticide Data
Wilton, D. J., Harrison, R. F., Willett, P., Delaney, J. S., Lawson, K., & Mullier, G. W. (2006) · Journal of Chemical Information and Modeling · doi:10.1021/ci050397w · Cited by 44 · see citing works
Geppert, H., & Bajorath, J. (2006) · Journal of Chemical Information and Modeling · doi:10.1021/ci600303b · Cited by 36 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Muratov, E. N., Bajorath, J., Sheridan, R. P., Tetko, I. V., Filimonov, D., Poroikov, V., Oprea, T. I., Baskin, I. I., Varnek, A., Roitberg, A., et al. (2020) · Chemical Society Reviews · doi:10.1039/d0cs00098a · Cited by 913 · see citing works
Self-citationDing, B., Wang, J., Li, N., & Wang, W. (2013) · Journal of Chemical Information and Modeling · doi:10.1021/ci300508m · Cited by 45 · see citing works
- Authors
- Geppert, H., Horváth, T., Gärtner, T., Wrobel, S., & Bajorath, J.
- Affiliations
- University of Bonn (DE)
- Corresponding author
- Bajorath, Jürgen
- Venue
- Journal of Chemical Information and Modeling
- Publisher
- American Chemical Society (ACS)
- Published
- 2008-03-05
- Volume
- 48
- Issue
- 4
- Pages
- 742-746
- ISSN
- 1549-9596 (ISSN-L)
- 1549-960X
- OpenAlex
- W2024224430
- Cited by
- 63
- References
- 27
- Citations by year
- 2026: 2 · 2024: 1 · 2023: 1 · 2022: 4 · 2021: 3 · 2020: 3 · 2019: 3 · 2018: 1 · 2017: 4 · 2016: 3 · 2015: 2 · 2014: 1 · 2013: 6 · 2012: 5
- FWCI
- 10.55
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Chemical Information and Modeling (publishedVersion)
- PubMed (publishedVersion)
- Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft) (submittedVersion)
- Fraunhofer-Publica (Fraunhofer-Gesellschaft) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Chemistry › Physical and Theoretical Chemistry › History and advancements in chemistry
- Keywords
- similarity search, support vector machine, ranking algorithms, virtual screening, nearest neighbor search, limited training data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
