Projects

The Smell of Fear

While the physiological response of humans to emotional events or stimuli is well-investigated for many modalities (like EEG, skin resistance, …), surprisingly little is known about the exhalation of so-called Volatile Organic Compounds (VOCs) at quite low concentrations in response to such stimuli. VOCs are molecules of relatively small mass that quickly evaporate or sublimate … Read more

enviPath

enviPath is both, a database and a prediction system, for the microbial biotransformation of organic environmental contaminants. The database provides the possibility to store and view experimentally observed biotransformation pathways, and supports the annotation of pathways with experimental and environmental conditions. The pathway prediction system provides different relative reasoning models to predict likely biotransformation pathways … Read more

Scavenger

Machine Learning methods and algorithms are often highly modular in the sense that they rely on a large number of subalgorithms that are in principle interchangeable. For example, it is often possible to use various kinds of pre- and post-processing and various base classifiers or regressors as components of the same modular approach. We propose … Read more

BMaD

Boolean matrix decomposition is a method to obtain a compressed representation of a matrix with Boolean entries. BMaD (Boolean Matrix Decomposition Framework) is a modular framework, written in Java, that unifies several Boolean matrix decomposition algorithms, and provide methods to evaluate their performance. The main advantages of the framework are its modular approach and hence the flexible … Read more

OpenTox

The overall objective of the EU FP7 project OpenTox was to develop a framework that provides a unified access to toxicity data, (Q)SAR models, procedures supporting validation and additional information that helps with the interpretation of (Q)SAR predictions. The OpenTox framework has been developed as an open source project to optimize the dissemination and impact, to allow … Read more

SINDBAD

To fully support the analysis of complex and structured data, new efficient computational methods  and suitable interfaces for data exploration have to be developed. Moreover, it is desirable to perform all tasks in the knowledge discovery process, from pre-processing to post-processing, on the basis of query languages. Inductive query languages should allow handling patterns/models as … Read more

Publications

Eawag-Soil in enviPath: a new resource for exploring regulatory pesticide soil biodegradation pathways and half-life data

Trading Off Accuracy for Efficiency by Randomized Greedy Warping

Cinema audiences reproducibly vary the chemical composition of air during films, by broadcasting scene specific emissions on breath

A Hybrid Machine Learning and Knowledge Based Approach to Limit Combinatorial Explosion in Biodegradation Prediction

A Nonlinear Label Compression and Transformation Method for Multi-Label Classification using Autoencoders

enviPath – The Environmental Contaminant Biotransformation Pathway Resource

Scavenger – A Framework for the Efficient Evaluation of Dynamic and Modular Algorithms

Cinema Data Mining: The Smell of Fear

BMaD – A Boolean Matrix Decomposition Framework

Large Classifier Systems in Bio- and Cheminformatics

Multi-label Classification Using Boolean Matrix Decomposition

SINDBAD and SiQL: Overview, Applications and Future Developments

Predicting biodegradation products and pathways: a hybrid knowledge- and machine learning-based approach

Collaborative development of predictive toxicology applications

SINDBAD SAILS: A service architecture for inductive learning schemes

SINDBAD and SiQL: An Inductive Database and Query Language in the Relational Model

Machine Learning and Data Mining Approaches to Biodegradation Pathway Prediction

An Inductive Database and Query Language in the Relational Model

Inductive Databases in the Relational Model: The Data as the Bridge