A5079908211- Computational Drug Discovery Methods
- Anomaly Detection Techniques and Applications
- Machine Learning and Data Classification
- Adversarial Robustness in Machine Learning
- Analytical Chemistry and Chromatography
- Advanced Image and Video Retrieval Techniques
- Machine Learning and Algorithms
- Color perception and design
- Text and Document Classification Technologies
- Machine Learning in Materials Science
- Statistical and Computational Modeling
- Data Mining Algorithms and Applications
- Algorithms and Data Compression
- Water Quality Monitoring Technologies
- Robotics and Sensor-Based Localization
- Metabolomics and Mass Spectrometry Studies
- Advanced Chemical Sensor Technologies
- Seismic Performance and Analysis
- Advanced Database Systems and Queries
- Data-Driven Disease Surveillance
- Hydrological Forecasting Using AI
- Isotope Analysis in Ecology
- Mass Spectrometry Techniques and Applications
- Multimodal Machine Learning Applications
- Olfactory and Sensory Function Studies
University of Auckland
2018-2025
University of Applied Sciences Mainz
2017
Johannes Gutenberg University Mainz
2012-2017
Technical University of Munich
2006-2010
Swiss Federal Institute of Aquatic Science and Technology
2010
University of Minnesota
2010
ETH Zurich
2010
The University of Minnesota Biocatalysis/Biodegradation Database and Pathway Prediction System (UM-BBD/PPS) has been a unique resource covering microbial biotransformation pathways primarily xenobiotic chemicals for over 15 years. This paper introduces the successor system, enviPath (The Environmental Contaminant Biotransformation Resource), which is complete redesign reimplementation UM-BBD/PPS. uses database from UM-BBD/PPS as basis, extends use this database, allows users to include their...
Abstract Human beings continuously emit chemicals into the air by breath and through skin. In order to determine whether these emissions vary predictably in response audiovisual stimuli, we have monitored carbon dioxide over one hundred volatile organic compounds a cinema. It was found that many airborne cinema varied distinctively reproducibly with time for particular film, even different screenings audiences. Application of scene labels advanced data mining methods revealed specific film...
In recent years, the integration of machine learning techniques into chemical reaction product prediction has opened new avenues for understanding and predicting behaviour substances. The necessity such predictive methods stems from growing regulatory social awareness environmental consequences associated with persistence accumulation residues. Traditional biodegradation rely on expert knowledge to perform predictions. However, creating this is becoming increasingly prohibitive due...
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 chemical safety assessment requirements REACH legislation as it supports access experimental data, (Quantitative) Structure-Activity Relationship models, toxicological information through integrating platform that adheres regulatory OECD principles. Initial research defined essential components...
The link between colour and emotion its possible similarity across cultures are questions that have not been fully resolved. Online, 711 participants from China, Germany, Greece the UK associated 12 terms with 20 discrete in their native languages. We propose a machine learning approach to quantify (a) consistency specificity of colour-emotion associations (b) degree which they country-specific, on basis accuracy statistical classifier decoding term evaluated given trial ratings predicting...
The 2017 Puebla, Mexico, earthquake event led to significant damage in many buildings Mexico City. In the months following earthquake, civil engineering students conducted detailed building assessments throughout city. They collected information and structural characteristics for 340 City urban area, with an emphasis on Roma Condesa neighborhoods where they assessed 237 buildings. These are of particular interest due availability seismic records captured by nearby recording stations,...
Developing models for the prediction of microbial biotransformation pathways and half-lives trace organic contaminants in different environments requires as training data easily accessible sufficiently large collections respective that are annotated with metadata on study conditions. Here, we present Eawag-Soil package, a public database has been developed to contain all freely regulatory pesticide degradation laboratory soil simulation studies pesticides registered EU (282 pathways, 1535...
Current methods for the prediction of biodegradation products and pathways organic environmental pollutants either do not take into account domain knowledge or provide probability estimates. In this article, we propose a hybrid knowledge- machine learning-based approach to overcome these limitations in context University Minnesota Pathway Prediction System (UM-PPS). The proposed solution performs relative reasoning learning framework, obtains one estimate each biotransformation rule system....
This paper introduces a new multi-label classifier based on Boolean matrix decomposition. decomposition is used to extract, from the full label matrix, latent labels representing useful combinations of original labels. Base level models predict labels, which are subsequently transformed into actual by multiplication with second The method tested six publicly available datasets varying numbers experimental evaluation shows that works particularly well large number and strong dependencies among them.
Attention-deficit/hyperactivity disorder (ADHD) is a heterogeneous neurodevelopmental condition with high prevalence of co-occurring conditions, contributing to increased difficulty in long-term management. Genome-wide association studies have identified variants shared between ADHD and psychiatric disorders; however, the genetic mechanisms are not fully understood. We integrated gene expression spatial organization data into two-sample Mendelian randomization study for putatively causal...
Forecasting surges in hospital admissions caused by severe respiratory infections is of crucial importance during the winter season to enable proactive management and timely decision-making prevent healthcare system overload. As time series derived from surveillance systems for these cases are sparse encode weak seasonality patterns, machine learning key computing accurate forecasts. The most recent algorithmic advance forecasting adaptation generative pre-trained transformers (GPTs). Those...
<title>Abstract</title> Bias in machine learning models remains a critical challenge, particularly datasets with numeric features where discrimination may be subtle and hard to detect. Existing fairness frameworks rely on expert knowledge of marginalized groups, such as specific racial categorical defining them. Furthermore, most evaluate bias rather than datasets, despite the fact that model can often traced back dataset shortcomings. Our research aims remedy this gap by capturing flaws set...
Abstract enviPath is a widely used database and prediction system for microbial biotransformation pathways of primarily xenobiotic compounds. Data are freely available both via web interface public REST API. Since its initial release in 2016, we extended the data improved performance usability overall system. We now provide three diverse sets, covering different environments under experimental conditions. This also enabled developing pathway model that applicable to more set chemicals. In...
Humans emit numerous volatile organic compounds (VOCs) through breath and skin. The nature rate of these emissions are affected by various factors including emotional state. Previous measurements VOCs CO2 in a cinema have shown that certain chemicals reproducibly emitted audiences reacting to events particular film. Using data from films with age classifications, we studied the relationship between emission multiple classifier (0, 6, 12, 16) view developing new chemically based objective...
While the physiological response of humans to emotional events or stimuli is well-investigated for many modalities (like EEG, skin resistance, ...), surprisingly little known about exhalation so-called Volatile Organic Compounds (VOCs) at quite low concentrations in such stimuli. VOCs are molecules relatively small mass that quickly evaporate sublimate and can be detected air surrounds us. The paper introduces a new field application data mining, where trace gas responses people reacting...
Abstract The prediction of metabolism and biotransformation pathways xenobiotics is a highly desired tool in environmental sciences, drug discovery, (eco)toxicology. Several systems predict single transformation steps or complete as series parallel subsequent steps. Their performance commonly evaluated on the level step. Such an approach cannot account for some specific challenges that are caused by properties experiments. That is, missing products reference data occur only low...