@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{hardy2010collaborative,
title = {Collaborative development of predictive toxicology applications},
author = {Barry Hardy and Nicki Douglas and Christoph Helma and Micha Rautenberg and Nina Jeliazkova and Vedrin Jeliazkov and Ivelina Nikolova and Romualdo Benigni and Olga Tcheremenskaia and Stefan Kramer and Tobias Girschick and Fabian Buchwald and Jörg Wicker and Andreas Karwath and Martin Gütlein and Andreas Maunz and Haralambos Sarimveis and Georgia Melagraki and Antreas Afantitis and Pantelis Sopasakis and David Gallagher and Vladimir Poroikov and Dmitry Filimonov and Alexey Zakharov and Alexey Lagunin and Tatyana Gloriozova and Sergey Novikov and Natalia Skvortsova and Dmitry Druzhilovsky and Sunil Chawla and Indira Ghosh and Surajit Ray and Hitesh Patel and Sylvia Escher},
url = {http://www.jcheminf.com/content/2/1/7},
doi = {10.1186/1758-2946-2-7},
issn = {1758-2946},
year = {2010},
date = {2010-01-01},
journal = {Journal of Cheminformatics},
volume = {2},
number = {1},
pages = {7},
abstract = {OpenTox provides an interoperable, standards-based Framework for the support of predictive toxicology data management, algorithms, modelling, validation and reporting. It is relevant to satisfying the chemical safety assessment requirements of the REACH legislation as it supports access to experimental data, (Quantitative) Structure-Activity Relationship models, and toxicological information through an integrating platform that adheres to regulatory requirements and OECD validation principles. Initial research defined the essential components of the Framework including the approach to data access, schema and management, use of controlled vocabularies and ontologies, architecture, web service and communications protocols, and selection and integration of algorithms for predictive modelling. OpenTox provides end-user oriented tools to non-computational specialists, risk assessors, and toxicological experts in addition to Application Programming Interfaces (APIs) for developers of new applications. OpenTox actively supports public standards for data representation, interfaces, vocabularies and ontologies, Open Source approaches to core platform components, and community-based collaboration approaches, so as to progress system interoperability goals.The OpenTox Framework includes APIs and services for compounds, datasets, features, algorithms, models, ontologies, tasks, validation, and reporting which may be combined into multiple applications satisfying a variety of different user needs. OpenTox applications are based on a set of distributed, interoperable OpenTox API-compliant REST web services. The OpenTox approach to ontology allows for efficient mapping of complementary data coming from different datasets into a unifying structure having a shared terminology and representation.Two initial OpenTox applications are presented as an illustration of the potential impact of OpenTox for high-quality and consistent structure-activity relationship modelling of REACH-relevant endpoints: ToxPredict which predicts and reports on toxicities for endpoints for an input chemical structure, and ToxCreate which builds and validates a predictive toxicity model based on an input toxicology dataset. Because of the extensible nature of the standardised Framework design, barriers of interoperability between applications and content are removed, as the user may combine data, models and validation from multiple sources in a dependable and time-effective way.},
keywords = {application, cheminformatics, data mining, machine learning, REST, toxicity},
pubstate = {published},
tppubtype = {article}
}