Experimental Errors in QSAR Modeling Sets: What We Can Do and What We Cannot Do
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Numerous chemical data sets have become available for quantitative structure-activity relationship (QSAR) modeling studies. However, the quality of different data sources may be different based on the nature of experimental protocols. Therefore, potential experimental errors in the modeling sets may lead to the development of poor QSAR models and further affect the predictions of new compounds. In this study, we explored the relationship between the ratio of questionable data in the modeling sets, which was obtained by simulating experimental errors, and the QSAR modeling performance. To this end, we used eight data sets (four continuous endpoints and four categorical endpoints) that have been extensively curated both in-house and by our collaborators to create over 1800 various QSAR models. Each data set was duplicated to create several new modeling sets with different ratios of simulated experimental errors (i.e., randomizing the activities of part of the compounds) in the modeling process. A fivefold cross-validation process was used to evaluate the modeling performance, which deteriorates when the ratio of experimental errors increases. All of the resulting models were also used to predict external sets of new compounds, which were excluded at the beginning of the modeling process. The modeling results showed that the compounds with relatively large prediction errors in cross-validation processes are likely to be those with simulated experimental errors. However, after removing a certain number of compounds with large prediction errors in the cross-validation process, the external predictions of new compounds did not show improvement. Our conclusion is that the QSAR predictions, especially consensus predictions, can identify compounds with potential experimental errors. But removing those compounds by the cross-validation procedure is not a reasonable means to improve model predictivity due to overfitting.
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
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Hawkins, D. M. (2004) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci0342472 · Cited by 2,522 · cited 1×
“For each categorical data set, we randomly selected x % ( x = 5, 10, 15, 20, 25, 50) compounds from the two classes and exchanged their activity categories and then obtained six new modeling sets.”
Believe it or not: how much can we rely on published data on potential drug targets?
Prinz, F., Schlange, T., & Asadullah, K. (2011) · Nature Reviews Drug Discovery · doi:10.1038/nrd3439-c1 · Cited by 1,888
Repeatability of published microarray gene expression analyses
Ioannidis, J. P. A., Allison, D. B., Ball, C. A., Coulibaly, I., Cui, X., Culhane, A. C., Falchi, M., Furlanello, C., Game, L., Jurman, G., et al. (2009) · Nature Genetics · doi:10.1038/ng.295 · Cited by 551
A HUPO test sample study reveals common problems in mass spectrometry–based proteomics
HUPO Test Sample Working Group, Bell, A. W., Deutsch, E. W., Au, C. E., Kearney, R. E., Beavis, R., Sechi, S., Nilsson, T., & Bergeron, J. J. M. (2009) · Nature Methods · doi:10.1038/nmeth.1333 · Cited by 351
Quantitative Structure−Activity Relationship Modeling of Rat Acute Toxicity by Oral Exposure
Zhu, H., Martin, T. M., Ye, L., Sedykh, A., Young, D. M., & Tropsha, A. (2009) · Chemical Research in Toxicology · doi:10.1021/tx900189p · Cited by 287
Self-citationZhu, H., Zhang, J., Kim, M. T., Boison, A., Sedykh, A., & Moran, K. (2014) · Chemical Research in Toxicology · doi:10.1021/tx500145h · Cited by 154
Self-citation
Cited by
Big data and artificial intelligence modeling for drug discovery
Zhu, H. (2020) · Annual Review of Pharmacology and Toxicology · doi:10.1146/annurev-pharmtox-010919-023324 · Cited by 455
“Critical issues existed in previous QSAR modeling studies such as the use of small training sets (11), experimental data errors in training sets (12, 13), and a lack of experimental validations (14).”
BackgroundSelf-citationPrinciples of QSAR Modeling: Comments and Suggestions From Personal Experience
Gramatica, P. (2020) · International Journal of Quantitative Structure-Property Relationships · doi:10.4018/ijqspr.20200701.oa1 · Cited by 258
Ciallella, H. L., & Zhu, H. (2019) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.8b00393 · Cited by 227
Self-citationTowards reproducible computational drug discovery
Schaduangrat, N., Lampa, S., Simeon, S., Gleeson, M. P., Spjuth, O., & Nantasenamat, C. (2020) · Journal of Cheminformatics · doi:10.1186/s13321-020-0408-x · Cited by 208
“analyses have been published assessing the quality of screening libraries that identify compounds responsible for many of the false-positive results [11, 12] or investigate compound structure accuracy in various repositories [13, 14].”
Background
Metadata
- Authors
- Zhao, L., Wang, W., Sedykh, A., & Zhu, H.
- Venue
- ACS Omega
- Publisher
- American Chemical Society (ACS)
- Published
- 2017-06-19
- Volume
- 2
- Issue
- 6
- Pages
- 2805-2812
- ISSN
- 2470-1343 (ISSN-L)
- OpenAlex
- W2720702472
- Cited by
- 78
- References
- 8
- FWCI
- 5.38
- Type
- journal article
- Language
- en
- Open access
- gold
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Experimental Errors in QSAR Modeling Sets: What We Can Do and What We Cannot Do. https://app.cochat.ai/papers/10.1021/acsomega.7b00274
- The paper
- Zhao, L., Wang, W., Sedykh, A., & Zhu, H. (2017). Experimental Errors in QSAR Modeling Sets: What We Can Do and What We Cannot Do. ACS Omega. https://doi.org/10.1021/acsomega.7b00274
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.