publications

@article{Wehr_2022,

title = {RespiraTox – Development of a QSAR model to predict human respiratory irritants},

author = {Matthias M. Wehr and Satinder S. Sarang and Martijn Rooseboom and Peter J. Boogaard and Andreas Karwath and Sylvia E. Escher},

url = {https://doi.org/10.1016%2Fj.yrtph.2021.105089},

doi = {10.1016/j.yrtph.2021.105089},

year  = {2022},

date = {2022-02-01},

urldate = {2022-02-01},

journal = {Regulatory Toxicology and Pharmacology},

volume = {128},

pages = {105089},

publisher = {Elsevier BV},

keywords = {cheminformatics, machine learning, QSAR},

pubstate = {published},

tppubtype = {article}

}

@article{RN17,

title = {Time extrapolation in regulatory risk assessment: The impact of study differences on the extrapolation factors},

author = {S E Escher and I Mangelsdorf and S Hoffmann-Doerr and F Partosch and Andreas Karwath and K Schroeder and A Zapf and M Batke},

doi = {10.1016/j.yrtph.2020.104584},

issn = {0273-2300},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

journal = {Regul Toxicol Pharmacol},

volume = {112},

pages = {104584},

keywords = {cheminformatics, QSAR},

pubstate = {published},

tppubtype = {article}

}

@article{gutlein2014,

title = {CheS-Mapper 2.0 for visual validation of (Q)SAR models},

author = {Martin Gütlein and Andreas Karwath and Stefan Kramer},

url = {http://dx.doi.org/10.1186/s13321-014-0041-7},

doi = {10.1186/s13321-014-0041-7},

year  = {2014},

date = {2014-09-23},

journal = {J. Cheminformatics},

volume = {6},

number = {1},

pages = {41},

abstract = {Background



Sound statistical validation is important to evaluate and compare the overall performance of (Q)SAR models. However, classical validation does not support the user in better understanding the properties of the model or the underlying data. Even though, a number of visualization tools for analyzing (Q)SAR information in small molecule datasets exist, integrated visualization methods that allow the investigation of model validation results are still lacking.



Results



We propose visual validation, as an approach for the graphical inspection of (Q)SAR model validation results. The approach applies the 3D viewer CheS-Mapper, an open-source application for the exploration of small molecules in virtual 3D space. The present work describes the new functionalities in CheS-Mapper 2.0, that facilitate the analysis of (Q)SAR information and allows the visual validation of (Q)SAR models. The tool enables the comparison of model predictions to the actual activity in feature space. The approach is generic: It is model-independent and can handle physico-chemical and structural input features as well as quantitative and qualitative endpoints.



Conclusions



Visual validation with CheS-Mapper enables analyzing (Q)SAR information in the data and indicates how this information is employed by the (Q)SAR model. It reveals, if the endpoint is modeled too specific or too generic and highlights common properties of misclassified compounds. Moreover, the researcher can use CheS-Mapper to inspect how the (Q)SAR model predicts activity cliffs. The CheS-Mapper software is freely available at http://​ches-mapper.​org.



Graphical abstract



Comparing actual and predicted activity values with CheS-Mapper.},

keywords = {cheminformatics, data mining, graph mining, validation, visualization},

pubstate = {published},

tppubtype = {article}

}

@article{guetlein2013,

title = {A Large-Scale Empirical Evaluation of Cross-Validation and External Test Set Validation in (Q)SAR},

author = {Martin Gütlein and Christoph Helma and Andreas Karwath and Stefan Kramer},

url = {http://onlinelibrary.wiley.com/doi/10.1002/minf.201200134/abstract},

doi = {10.1002/minf.201200134},

year  = {2013},

date = {2013-10-14},

urldate = {2013-10-14},

journal = {Molecular Informatics},

volume = {32},

number = {5-6},

pages = {516-528},

abstract = {(Q)SAR model validation is essential to ensure the quality of inferred models and to indicate future model predictivity on unseen compounds. Proper validation is also one of the requirements of regulatory authorities in order to accept the (Q)SAR model, and to approve its use in real world scenarios as alternative testing method. However, at the same time, the question of how to validate a (Q)SAR model, in particular whether to employ variants of cross-validation or external test set validation, is still under discussion. In this paper, we empirically compare a k-fold cross-validation with external test set validation. To this end we introduce a workflow allowing to realistically simulate the common problem setting of building predictive models for relatively small datasets. The workflow allows to apply the built and validated models on large amounts of unseen data, and to compare the performance of the different validation approaches. The experimental results indicate that cross-validation produces higher performant (Q)SAR models than external test set validation, reduces the variance of the results, while at the same time underestimates the performance on unseen compounds. The experimental results reported in this paper suggest that, contrary to current conception in the community, cross-validation may play a significant role in evaluating the predictivity of (Q)SAR models.},

keywords = {cheminformatics, crossvalidation, external validation, QSAR, validation},

pubstate = {published},

tppubtype = {article}

}

@article{gutlein2012,

title = {CheS-Mapper - Chemical Space Mapping and Visualization in 3D},

author = {Martin Gütlein and Andreas Karwath and Stefan Kramer},

url = {http://dx.doi.org/10.1186/1758-2946-4-7},

doi = {10.1186/1758-2946-4-7},

year  = {2012},

date = {2012-03-17},

journal = {J. Cheminformatics},

volume = {4},

pages = {7},

abstract = {Analyzing chemical datasets is a challenging task for scientific researchers in the field of chemoinformatics. It is important, yet difficult to understand the relationship between the structure of chemical compounds, their physico-chemical properties, and biological or toxic effects. To that respect, visualization tools can help to better comprehend the underlying correlations. Our recently developed 3D molecular viewer CheS-Mapper (Chemical Space Mapper) divides large datasets into clusters of similar compounds and consequently arranges them in 3D space, such that their spatial proximity reflects their similarity. The user can indirectly determine similarity, by selecting which features to employ in the process. The tool can use and calculate different kind of features, like structural fragments as well as quantitative chemical descriptors. These features can be highlighted within CheS-Mapper, which aids the chemist to better understand patterns and regularities and relate the observations to established scientific knowledge. As a final function, the tool can also be used to select and export specific subsets of a given dataset for further analysis.

},

keywords = {cheminformatics, clustering, dimensionality reduction, QSAR, visualization},

pubstate = {published},

tppubtype = {article}

}

@article{karwath06c,

title = {SMIREP: Predicting Chemical Activity from SMILES},

author = {Andreas Karwath and De Raedt, Luc},

url = {http://pubs.acs.org/doi/abs/10.1021/ci060159g},

doi = {10.1021/ci060159g},

year  = {2006},

date = {2006-10-12},

journal = {Journal of Chemical Information and Modeling},

volume = {46},

number = {6},

pages = {2432 - 2444},

abstract = {Most approaches to structure-activity-relationship (SAR) prediction proceed in two steps. In the first step, a typically large set of fingerprints, or fragments of interest, is constructed (either by hand or by some recent data mining techniques). In the second step, machine learning techniques are applied to obtain a predictive model. The result is often not only a highly accurate but also hard to interpret model. In this paper, we demonstrate the capabilities of a novel SAR algorithm, SMIREP, which tightly integrates the fragment and model generation steps and which yields simple models in the form of a small set of IF-THEN rules. These rules contain SMILES fragments, which are easy to understand to the computational chemist. SMIREP combines ideas from the well-known IREP rule learner with a novel fragmentation algorithm for SMILES strings. SMIREP has been evaluated on three problems: the prediction of binding activities for the estrogen receptor (Environmental Protection Agency's (EPA's) Distributed Structure-Searchable Toxicity (DSSTox) National Center for Toxicological Research estrogen receptor (NCTRER) Database), the prediction of mutagenicity using the carcinogenic potency database (CPDB), and the prediction of biodegradability on a subset of the Environmental Fate Database (EFDB). In these applications, SMIREP has the advantage of producing easily interpretable rules while having predictive accuracies that are comparable to those of alternative state-of-the-art techniques.},

keywords = {cheminformatics, graph mining, machine learning, QSAR, relational learning, scientific knowledge},

pubstate = {published},

tppubtype = {article}

}