Relevance Vector Machines: Sparse Classification Methods for QSAR
Abstract
Sparse machine learning methods have provided substantial benefits to quantitative structure property modeling, as they make model interpretation simpler and generate models with improved predictivity. Sparsity is usually induced via Bayesian regularization using sparsity-inducing priors and by the use of expectation maximization algorithms with sparse priors. The focus to date has been on using sparse methods to model continuous data and to carry out sparse feature selection. We describe the relevance vector machine (RVM), a sparse version of the support vector machine (SVM) that is one of the most widely used classification machine learning methods in QSAR and QSPR. We illustrate the superior properties of the RVM by modeling eight data sets using SVM, RVM, and another sparse Bayesian machine learning method, the Bayesian regularized artificial neural network with Laplacian prior (BRANNLP). We show that RVM models are substantially sparser than the SVM models and have similar or superior performance to them.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421 · see citing works
What is a support vector machine?
Noble, W. S. (2006) · Nature Biotechnology · doi:10.1038/nbt1206-1565 · Cited by 4,307 · see citing works
Hedonic housing prices and the demand for clean air
Harrison, D., & Rubinfeld, D. L. (1978) · Journal of Environmental Economics and Management · doi:10.1016/0095-0696(78)90006-2 · Cited by 1,878 · see citing works
Multisurface method of pattern separation for medical diagnosis applied to breast cytology.
Wolberg, W. H., & Mangasarian, O. L. (1990) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.87.23.9193 · Cited by 1,039 · see citing works
Using the ADAP Learning Algorithm to Forecast the Onset of Diabetes Mellitus
Smith, J. W., Everhart, J. E., Dickson, W., Knowler, W. C., & Johannes, R. S. (1988) · PubMed Central · Cited by 813 · see citing works
Quantitative Structure–Property Relationship Modeling of Diverse Materials Properties
Le, T. C., Epa, V. C., Burden, F. R., & Winkler, D. A. (2012) · Chemical Reviews · doi:10.1021/cr200066h · Cited by 563 · see citing works
Self-citationAdaptive sparseness for supervised learning
Figueiredo, M. A. T. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1227989 · Cited by 536 · see citing works
Robust QSAR Models Using Bayesian Regularized Neural Networks
Burden, F. R., & Winkler, D. A. (1999) · Journal of Medicinal Chemistry · doi:10.1021/jm980697n · Cited by 242 · see citing works
Self-citationQuantitative Structure–Activity Relationship Models for Ready Biodegradability of Chemicals
Mansouri, K., Ringsted, T., Ballabio, D., et al. (2013) · Journal of Chemical Information and Modeling · doi:10.1021/ci4000213 · Cited by 222 · see citing works
Modeling Biological Activities of Nanoparticles
Epa, V. C., Burden, F. R., Tassa, C., Weissleder, R., Shaw, S. Y., & Winkler, D. A. (2012) · Nano Letters · doi:10.1021/nl303144k · Cited by 194 · see citing works
Self-citationTowards chromate-free corrosion inhibitors: structure–property models for organic alternatives
Winkler, D. A., Breedon, M., Hughes, A. E., et al. (2014) · Green Chemistry · doi:10.1039/c3gc42540a · Cited by 174 · see citing works
Self-citationMaterials for stem cell factories of the future
Celiz, A. D., Smith, J. G. W., Langer, R., Anderson, D. G., Winkler, D. A., Barrett, D. A., Davies, M. C., Young, L. E., Denning, C. N., & Alexander, M. R. (2014) · Nature Materials · doi:10.1038/nmat3972 · Cited by 155 · see citing works
Self-citationUse of Automatic Relevance Determination in QSAR Studies Using Bayesian Neural Networks
Burden, F. R., Ford, M. G., Whitley, D. C., & Winkler, D. A. (2000) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci000450a · Cited by 134 · see citing works
Self-citationModelling and predicting the biological effects of nanomaterials
Winkler, D. A., Burden, F. R., Yan, B., et al. (2014) · SAR and QSAR in environmental research · doi:10.1080/1062936x.2013.874367 · Cited by 114 · see citing works
Self-citationNonlinear SVM Approaches to QSPR/QSAR Studies and Drug Design
Doucet, J., Barbault, F., Xia, H., Panaye, A. D., & Fan, B. (2007) · Current Computer - Aided Drug Design · doi:10.2174/157340907782799372 · Cited by 89 · see citing works
Burden, F. R., & Winkler, D. A. (2000) · Chemical Research in Toxicology · doi:10.1021/tx9900627 · Cited by 88 · see citing works
Self-citationSalahinejad, M., Le, T. C., & Winkler, D. A. (2012) · Journal of Chemical Information and Modeling · doi:10.1021/ci3005012 · Cited by 78 · see citing works
Self-citationOptimal Sparse Descriptor Selection for QSAR Using Bayesian Methods
Burden, F. R., & Winkler, D. A. (2009) · QSAR & Combinatorial Science · doi:10.1002/qsar.200810173 · Cited by 76 · see citing works
Self-citationAutefage, H., Gentleman, E., Littmann, E., Hedegaard, M. A. B., von Erlach, T. C., O’Donnell, M., Burden, F. R., Winkler, D. A., & Stevens, M. M. (2015) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1419799112 · Cited by 72 · see citing works
Self-citationModelling blood–brain barrier partitioning using Bayesian neural nets
Winkler, D. A., & Burden, F. R. (2004) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2004.03.010 · Cited by 71 · see citing works
Self-citationAqueous Solubility Prediction: Do Crystal Lattice Interactions Help?
Salahinejad, M., Le, T. C., & Winkler, D. A. (2013) · Molecular Pharmaceutics · doi:10.1021/mp4001958 · Cited by 70 · see citing works
Self-citationQuantitative Structure−Activity Relationship Studies Using Gaussian Processes
Burden, F. R. (2001) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci000459c · Cited by 65 · see citing works
Self-citationAn Optimal Self‐Pruning Neural Network and Nonlinear Descriptor Selection in QSAR
Burden, F. R., & Winkler, D. A. (2009) · QSAR & Combinatorial Science · doi:10.1002/qsar.200810202 · Cited by 65 · see citing works
Self-citationNew QSAR Methods Applied to Structure−Activity Mapping and Combinatorial Chemistry
Burden, F. R., & Winkler, D. A. (1998) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci980070d · Cited by 63 · see citing works
Self-citationRobust QSAR Models from Novel Descriptors and Bayesian Regularised Neural Networks
Winkler, D. A., & Burden, F. R. (2000) · Molecular Simulation · doi:10.1080/08927020008022374 · Cited by 61 · see citing works
Self-citationRapid QSPR model development technique for prediction of vapor pressure of organic compounds
KATRITZKY, A. R., Slavov, S. H., Dobchev, D. A., et al. (2006) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2006.10.001 · Cited by 61 · see citing works
Modelling human embryoid body cell adhesion to a combinatorial library of polymer surfaces
Epa, V. C., Yang, J., Mei, Y., Hook, A. L., Langer, R., Anderson, D. G., Davies, M. C., Alexander, M. R., & Winkler, D. A. (2012) · Journal of Materials Chemistry · doi:10.1039/c2jm34782b · Cited by 55 · see citing works
Self-citationModelling and Prediction of Bacterial Attachment to Polymers
Epa, V. C., Hook, A. L., Chang, C., et al. (2013) · Advanced Functional Materials · doi:10.1002/adfm.201302877 · Cited by 51 · see citing works
Probing enzyme-nanoparticle interactions using combinatorial gold nanoparticle libraries
Liu, Y., Winkler, D. A., Epa, V. C., Zhang, B., & Yan, B. (2014) · Nano Research · doi:10.1007/s12274-014-0618-5 · Cited by 31 · see citing works
Self-citationAtomistic Topological Indices Applied to Benzodiazepines using Various Regression Methods
Winkler, D. A., Burden, F. R., & Watkins, A. J. R. (1998) · Quantitative Structure-Activity Relationships · doi:10.1002/(sici)1521-3838(199801)17:01 · Cited by 31 · see citing works
Self-citationPredicting the Complex Phase Behavior of Self-Assembling Drug Delivery Nanoparticles
Le, T. C., Mulet, X., Burden, F. R., et al. (2013) · Molecular Pharmaceutics · doi:10.1021/mp3006402 · Cited by 27 · see citing works
Self-citationHuh, Y. H., Noh, M., Burden, F. R., Chen, J. C., Winkler, D. A., & Sherley, J. L. (2015) · Stem Cell Research · doi:10.1016/j.scr.2014.12.007 · Cited by 20 · see citing works
Self-citationIlluminating Flash Point: Comprehensive Prediction Models
Le, T. C., Ballard, M. J., Casey, P., et al. (2014) · Molecular Informatics · doi:10.1002/minf.201400098 · Cited by 18 · see citing works
Le, T. C., Conn, C. E., Burden, F. R., & Winkler, D. A. (2013) · Crystal Growth & Design · doi:10.1021/cg301730z · Cited by 18 · see citing works
Self-citationWinkler, D. A., & Burden, F. R. (2012) · Molecular BioSystems · doi:10.1039/c2mb05439f · Cited by 15 · see citing works
Self-citationA comparison of SVM and RVM for Document ClassificationPreprint
Rafi, M., & Shaikh, M. S. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1301.2785 · Cited by 14 · see citing works
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-citationMadiona, R. M. T., Bamford, S. E., Winkler, D. A., Muir, B. W., & Pigram, P. J. (2018) · Analytical Chemistry · doi:10.1021/acs.analchem.8b01951 · Cited by 25 · see citing works
Self-citation
- Authors
- Burden, F. R., & Winkler, D. A.
- Affiliations
- Commonwealth Scientific and Industrial Research Organisation (AU)
- Flinders University (AU)
- Corresponding author
- Winkler, David A.
- ORCID
- Winkler, David A.
- Venue
- Journal of Chemical Information and Modeling
- Publisher
- American Chemical Society (ACS)
- Published
- 2015-07-21
- Volume
- 55
- Issue
- 8
- Pages
- 1529-1534
- ISSN
- 1549-9596 (ISSN-L)
- 1549-960X
- OpenAlex
- W2405383071
- Cited by
- 51
- References
- 36
- Citations by year
- 2026: 5 · 2025: 1 · 2024: 1 · 2023: 1 · 2022: 5 · 2021: 5 · 2020: 6 · 2019: 6 · 2018: 11 · 2017: 3 · 2016: 6 · 2015: 1
- FWCI
- 7.20
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Chemical Information and Modeling (publishedVersion)
- PubMed (publishedVersion)
- 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 › Computer Science › Artificial Intelligence › Gaussian Processes and Bayesian Inference
- Keywords
- relevance vector machine, sparse classification, support vector machine, sparse Bayesian learning, sparsity-inducing priors, Bayesian regularization, QSPR, QSAR, model interpretability, feature selection
- MeSH terms
- Algorithms, Bayes Theorem, Quantitative Structure-Activity Relationship, Support Vector Machine
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
