@article{latino2017eawag,
title = {Eawag-Soil in enviPath: a new resource for exploring regulatory pesticide soil biodegradation pathways and half-life data},
author = {Diogo Latino and Jörg Wicker and Martin Gütlein and Emanuel Schmid and Stefan Kramer and Kathrin Fenner},
doi = {10.1039/C6EM00697C},
year = {2017},
date = {2017-01-01},
journal = {Environmental Science: Process & Impact},
publisher = {The Royal Society of Chemistry},
abstract = {Developing models for the prediction of microbial biotransformation pathways and half-lives of trace organic contaminants in different environments requires as training data easily accessible and sufficiently large collections of respective biotransformation data that are annotated with metadata on study conditions. Here, we present the Eawag-Soil package, a public database that has been developed to contain all freely accessible regulatory data on pesticide degradation in laboratory soil simulation studies
for pesticides registered in the EU (282 degradation pathways, 1535 reactions, 1619 compounds and 4716 biotransformation half-life values with corresponding metadata on study conditions). We provide a thorough description of this novel data resource, and discuss important features of the pesticide soil degradation data that are relevant for model development. Most notably, the variability of half-life values for individual compounds is large and only about one order of magnitude lower than the entire range of median half-life values spanned by all compounds, demonstrating the need to consider study conditions in the development of more accurate models for biotransformation prediction. We further show how the data can be used to find missing rules relevant for predicting soil biotransformation pathways. From this analysis, eight examples of reaction types were presented that should trigger the formulation of new biotransformation rules, e.g., Ar-OH methylation, or the extension of existing rules e.g., hydroxylation in aliphatic rings. The data were also used to exemplarily explore the dependence of half-lives of different amide pesticides on chemical class and experimental parameters. This analysis highlighted the value of considering initial transformation reactions for the development of meaningful quantitative-structure biotransformation relationships (QSBR), which is a novel opportunity of f ered by the simultaneous encoding of transformation reactions and corresponding half-lives in Eawag-Soil. Overall, Eawag-Soil provides an unprecedentedly rich collection of manually extracted and curated biotransformation data, which should be useful in a great variety of applications.},
keywords = {application, biodegradation, cheminformatics, data mining, enviPath, multi-label classification, REST, web services},
pubstate = {published},
tppubtype = {article}
}

@incollection{wicker2016ahybrid,
title = {A Hybrid Machine Learning and Knowledge Based Approach to Limit Combinatorial Explosion in Biodegradation Prediction},
author = {Jörg Wicker and Kathrin Fenner and Stefan Kramer},
editor = {Jörg Lässig and Kristian Kersting and Katharina Morik},
url = {http://dx.doi.org/10.1007/978-3-319-31858-5_5},
doi = {10.1007/978-3-319-31858-5_5},
isbn = {978-3-319-31858-5},
year = {2016},
date = {2016-04-21},
booktitle = {Computational Sustainability},
pages = {75-97},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {One of the main tasks in chemical industry regarding the sustainability of a product is the prediction of its environmental fate, i.e., its degradation products and pathways. Current methods for the prediction of biodegradation products and pathways of organic environmental pollutants either do not take into account domain knowledge or do not provide probability estimates. In this chapter, we propose a hybrid knowledge-based and machine learning-based approach to overcome these limitations in the context of the University of Minnesota Pathway Prediction System (UM-PPS). The proposed solution performs relative reasoning in a machine learning framework, and obtains one probability estimate for each biotransformation rule of the system. Since the application of a rule then depends on a threshold for the probability estimate, the trade-off between recall (sensitivity) and precision (selectivity) can be addressed and leveraged in practice. Results from leave-one-out cross-validation show that a recall and precision of approximately 0.8 can be achieved for a subset of 13 transformation rules. The set of used rules is further extended using multi-label classification, where dependencies among the transformation rules are exploited to improve the predictions. While the results regarding recall and precision vary, the area under the ROC curve can be improved using multi-label classification. Therefore, it is possible to optimize precision without compromising recall. Recently, we integrated the presented approach into enviPath, a complete redesign and re-implementation of UM-PPS.},
keywords = {application, biodegradation, cheminformatics, computational sustainability, enviPath, machine learning, metabolic pathways, multi-label classification},
pubstate = {published},
tppubtype = {incollection}
}

@article{wicker2016envipath,
title = {enviPath - The Environmental Contaminant Biotransformation Pathway Resource},
author = {Jörg Wicker and Tim Lorsbach and Martin Gütlein and Emanuel Schmid and Diogo Latino and Stefan Kramer and Kathrin Fenner},
editor = {Michael Galperin},
url = {http://nar.oxfordjournals.org/content/44/D1/D502.abstract},
doi = {10.1093/nar/gkv1229},
year = {2016},
date = {2016-01-01},
journal = {Nucleic Acid Research},
volume = {44},
number = {D1},
pages = {D502-D508},
abstract = {The University of Minnesota Biocatalysis/Biodegradation Database and Pathway Prediction System (UM-BBD/PPS) has been a unique resource covering microbial biotransformation pathways of primarily xenobiotic chemicals for over 15 years. This paper introduces the successor system, enviPath (The Environmental Contaminant Biotransformation Pathway Resource), which is a complete redesign and reimplementation of UM-BBD/PPS. enviPath uses the database from the UM-BBD/PPS as a basis, extends the use of this database, and allows users to include their own data to support multiple use cases. Relative reasoning is supported for the refinement of predictions and to allow its extensions in terms of previously published, but not implemented machine learning models. User access is simplified by providing a REST API that simplifies the inclusion of enviPath into existing workflows. An RDF database is used to enable simple integration with other databases. enviPath is publicly available at https://envipath.org with free and open access to its core data.},
keywords = {application, biodegradation, cheminformatics, computational sustainability, data mining, enviPath, linked data, machine learning, metabolic pathways, multi-label classification},
pubstate = {published},
tppubtype = {article}
}

@phdthesis{wicker2013large,
title = {Large Classifier Systems in Bio- and Cheminformatics},
author = {Jörg Wicker},
url = {http://mediatum.ub.tum.de/node?id=1165858},
year = {2013},
date = {2013-01-01},
school = {Technische Universität München},
abstract = {Large classifier systems are machine learning algorithms that use multiple
classifiers to improve the prediction of target values in advanced
classification tasks. Although learning problems in bio- and
cheminformatics commonly provide data in schemes suitable for large
classifier systems, they are rarely used in these domains. This thesis
introduces two new classifiers incorporating systems of classifiers
using Boolean matrix decomposition to handle data in a schema that
often occurs in bio- and cheminformatics.

The first approach, called MLC-BMaD (multi-label classification using
Boolean matrix decomposition), uses Boolean matrix decomposition to
decompose the labels in a multi-label classification task. The
decomposed matrices are a compact representation of the information
in the labels (first matrix) and the dependencies among the labels
(second matrix). The first matrix is used in a further multi-label
classification while the second matrix is used to generate the final
matrix from the predicted values of the first matrix.
MLC-BMaD was evaluated on six standard multi-label data sets, the
experiments showed that MLC-BMaD can perform particularly well on data
sets with a high number of labels and a small number of instances and
can outperform standard multi-label algorithms.
Subsequently, MLC-BMaD is extended to a special case of
multi-relational learning, by considering the labels not as simple
labels, but instances. The algorithm, called ClassFact
(Classification factorization), uses both matrices in a multi-label
classification. Each label represents a mapping between two
instances.
Experiments on three data sets from the domain of bioinformatics show
that ClassFact can outperform the baseline method, which merges the
relations into one, on hard classification tasks.

Furthermore, large classifier systems are used on two cheminformatics
data sets, the first one is used to predict the environmental fate of
chemicals by predicting biodegradation pathways. The second is a data
set from the domain of predictive toxicology. In biodegradation
pathway prediction, I extend a knowledge-based system and incorporate
a machine learning approach to predict a probability for
biotransformation products based on the structure- and knowledge-based
predictions of products, which are based on transformation rules. The
use of multi-label classification improves the performance of the
classifiers and extends the number of transformation rules that can be
covered.
For the prediction of toxic effects of chemicals, I applied large
classifier systems to the ToxCasttexttrademark data set, which maps
toxic effects to chemicals. As the given toxic effects are not easy to
predict due to missing information and a skewed class
distribution, I introduce a filtering step in the multi-label
classification, which finds labels that are usable in multi-label
prediction and does not take the others in the
prediction into account. Experiments show
that this approach can improve upon the baseline method using binary
classification, as well as multi-label approaches using no filtering.

The presented results show that large classifier systems can play a
role in future research challenges, especially in bio- and
cheminformatics, where data sets frequently consist of more complex
structures and data can be rather small in terms of the number of
instances compared to other domains.},
keywords = {application, biodegradation, bioinformatics, cheminformatics, data mining, enviPath, machine learning, multi-label classification, multi-relational learning, toxicity},
pubstate = {published},
tppubtype = {phdthesis}
}

@article{wicker2010predicting,
title = {Predicting biodegradation products and pathways: a hybrid knowledge- and machine learning-based approach},
author = {Jörg Wicker and Kathrin Fenner and Lynda Ellis and Larry Wackett and Stefan Kramer},
url = {http://bioinformatics.oxfordjournals.org/content/26/6/814.full},
doi = {10.1093/bioinformatics/btq024},
year = {2010},
date = {2010-01-01},
journal = {Bioinformatics},
volume = {26},
number = {6},
pages = {814-821},
publisher = {Oxford University Press},
abstract = {Motivation: Current methods for the prediction of biodegradation products and pathways of organic environmental pollutants either do not take into account domain knowledge or do not provide probability estimates. In this article, we propose a hybrid knowledge- and machine learning-based approach to overcome these limitations in the context of the University of Minnesota Pathway Prediction System (UM-PPS). The proposed solution performs relative reasoning in a machine learning framework, and obtains one probability estimate for each biotransformation rule of the system. As the application of a rule then depends on a threshold for the probability estimate, the trade-off between recall (sensitivity) and precision (selectivity) can be addressed and leveraged in practice.Results: Results from leave-one-out cross-validation show that a recall and precision of ∼0.8 can be achieved for a subset of 13 transformation rules. Therefore, it is possible to optimize precision without compromising recall. We are currently integrating the results into an experimental version of the UM-PPS server.Availability: The program is freely available on the web at http://wwwkramer.in.tum.de/research/applications/biodegradation/data.Contact: kramer@in.tum.de},
keywords = {application, biodegradation, cheminformatics, computational sustainability, enviPath, machine learning, metabolic pathways},
pubstate = {published},
tppubtype = {article}
}

@inproceedings{wicker2008machine,
title = {Machine Learning and Data Mining Approaches to Biodegradation Pathway Prediction},
author = {Jörg Wicker and Kathrin Fenner and Lynda Ellis and Larry Wackett and Stefan Kramer},
editor = {Will Bridewell and Toon Calders and Ana Karla de Medeiros and Stefan Kramer and Mykola Pechenizkiy and Ljupco Todorovski},
url = {http://www.ecmlpkdd2008.org/files/pdf/workshops/ipm/9.pdf},
year = {2008},
date = {2008-01-01},
booktitle = {Proceedings of the Second International Workshop on the Induction of Process Models at ECML PKDD 2008},
keywords = {application, biodegradation, cheminformatics, computational sustainability, enviPath, machine learning, metabolic pathways},
pubstate = {published},
tppubtype = {inproceedings}
}