Three Useful Dimensions for Domain Applicability in QSAR Models Using Random Forest
The DOI matches its Crossref record.
Abstract
One popular metric for estimating the accuracy of prospective quantitative structure-activity relationship (QSAR) predictions is based on the similarity of the compound being predicted to compounds in the training set from which the QSAR model was built. More recent work in the field has indicated that other parameters might be equally or more important than similarity. Here we make use of two additional parameters: the variation of prediction among random forest trees (less variation among trees indicates more accurate prediction) and the prediction itself (certain ranges of activity are intrinsically easier to predict than others). The accuracy of prediction for a QSAR model, as measured by the root-mean-square error, can be estimated by cross-validation on the training set at the time of model-building and stored as a three-dimensional array of bins. This is an obvious extension of the one-dimensional array of bins we previously proposed for similarity to the training set [Sheridan et al. J. Chem. Inf. Comput. Sci.2004, 44, 1912-1928]. We show that using these three parameters simultaneously adds much more discrimination in prediction accuracy than any single parameter. This approach can be applied to any QSAR method that produces an ensemble of models. We also show that the root-mean-square errors produced by cross-validation are predictive of root-mean-square errors of compounds tested after the model was built.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cited by
Time-Split Cross-Validation as a Method for Estimating the Goodness of Prospective Prediction.
Sheridan, R. P. (2013) · Journal of Chemical Information and Modeling · doi:10.1021/ci400084k · Cited by 376
Self-citationExposing the Limitations of Molecular Machine Learning with Activity Cliffs
van Tilborg, D., Alenicheva, A., & Grisoni, F. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c01073 · Cited by 337
Uncertainty quantification: Can we trust artificial intelligence in drug discovery?
Yu, J., Wang, D., & Zheng, M. (2022) · iScience · doi:10.1016/j.isci.2022.104814 · Cited by 59
“RF (Sheridan, 2012) 3.”
BackgroundReliable Prediction Errors for Deep Neural Networks Using Test-Time Dropout
Cortés-Ciriano, I., & Bender, A. (2019) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.9b00297 · Cited by 51
“…default parameter values were used except for the number of trees, which was set to 100, as using a larger number of trees does not result in increased generalization capability and this value has been found to be a suitable choice in previous chemical structure-activity modelling studies 56,57 .”
Method
Metadata
- Authors
- Sheridan, R. P.
- Venue
- Journal of Chemical Information and Modeling
- Publisher
- American Chemical Society (ACS)
- Published
- 2012-03-09
- Volume
- 52
- Issue
- 3
- Pages
- 814-823
- ISSN
- 1549-9596 (ISSN-L)
- 1549-960X
- OpenAlex
- W2048611698
- Cited by
- 124
- References
- 0
- FWCI
- 9.50
- Type
- journal article
- Language
- en
- Open access
- closed
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.