Dr. Bittremieux's research deals with developing advanced machine learning techniques to uncover novel knowledge from mass spectrometry-based proteomics and metabolomics data. While his current research mainly focuses on how deep learning can be used to analyze mass spectrometry data he is interested in a wide variety of bioinformatics problems. An important part of his work involves developing insights and computational approaches for quality control in biological mass spectrometry.
Techniquebioinformatics machine learning deep learning mass spectrometry proteomics metabolomics
Usersbioinformatics researchers computational biology researchers
Valorisation, grant and project management in the life science domain.
TechniqueValorisation, grant and project management in the life science domain.
UsersResearchers in life sciences, biotech and farma companies.
Innovations, Scientific communication
Analysis of dynamic network data Most works in network analysis concentrate on static graphs and find patterns such as the most in influential nodes in the network. Very few existing methods are able to deal with repeated interactions between nodes in a network. The main goal of the research in this topic is hence to fill this gap by developing methods to identify patterns in interactions between network nodes. We studied so-called information channels that indicate information flows. Process Mining In process mining the object of study are logs generated by business processes. Consider for instance a log generated by a leave request system, recording activities such as users logging in, opening a new request, managers approving requests, emails being sent by the system, etc. In process mining such logs are analyzed to better understand, monitor, and improve the business processes. One tasks in this context is detecting complex events. Complex events can be used to find pre-defined security problems or abnormalities. Often, however, anomalies may occur that are not foreseen in the systems. In order to be able to handle such cases, anomaly detection techniques are necessary. With the following work on model-based anomaly detection using dynamic Bayesian networks, we won the Business Process Intelligence challenge at the BPM 2018 conference: S. Pauwels and T. Calders. Detecting and Explaining Drifts in Yearly Grant Applications. In BPM Workshop Business Process Intelligence (BPI), 2018. Fairness-Aware Machine Learning In contemporary society we are continuously being profiled; banks have profiles to divide up people according to credit risk, insurance companies profile clients for accident risk, telephone companies profile users on their calling behavior, web corporations profile users according to their interests and preferences based on web activity and visitation patterns. These profiles are more and more built automatically by machine learning methods trained on historical data. Within society there are growing concerns that these machine learning methods do not have ethical or moral restrictions. Recent studies show indeed that in circumstances where historical data is biased, or when there is omitted variable bias, automatically learned methods may take decisions that could be considered discriminatory. Apart from ethical considerations, there are also legal restrictions to the use of profiling methods that blindly optimize accuracy without taking unwanted discriminatory effects into account. The recent General Data Protection Regulation (GDPR; Regulation (EU) 2016/679) explicitly mentions profiling (Art. 22 GDPR Automated individual decision-making, including profiling) as an activity in which decisions should not be based on personal data and suitable measures should be in place to safeguard the data subjects rights and freedoms and legitimate interests. Most profiling techniques, however, do not consider anti-discrimination legislation and may unintentionally produce models that are unfair and hence do not safeguard the data subjects freedoms. A further complication is that often detecting whether a model is unfair, is highly non-trivial.
Technique- Formalizing research problems mathematically; - Development of algorithmic solutions; - Study of computational properties of algorithms; - Case studies: application of developed techniques in real-life contexts.
UsersAll sectors in which machine learning is applied, including: - default prediction in the financial sector; - risk assessment in insurance; - outlier detection from log files for security monitoring; - predictive modelling. There are existing collaborations with insurance companies (fairness in machine leanring - building fair score models), bankin sector (default prediction), scientific institutes (BIRA: analysis of spectrograms for meteor detection),...
Development and study of advanced data mining and machine learning methods. In particular, we investigate: (i) new methods to efficiently discover interesting patterns in sequential data; (ii) new methods to detect contextual anomalies in heterogeneous sequential data; (iii) and new methods for multi-label classification in extremely large datasets. In addition, we investigate applications of these methods in areas such as the monitoring of wind farms and anomaly detection in an Industrial Internet of Things context.
TechniqueDevelopment of algorithmic solutions to (un)supervised machine learning problems; Formalizing research problems mathematically; Development of algorithmic solutions; Analysis of properties of algorithms; Case studies: application of developed techniques in real-life contexts.
UsersAll sectors in which data mining or machine learning is applied. More specifically, anomaly detection, prediction and/or discovering patterns in sequential data, such as event log data and time series. There are existing collaborations for: (i) predicting labels for federal police; (ii) condition monitoring in wind turbine farms (using pattern mining); (iii) anomaly detection in water consumption of supermarket chains; (iv) data cleaning and entity resolution to combine different databases.
Pattern mining, Data science, Machine learning, Data mining
Development and study of advanced methods for data storage, cleaning, processing and querying of vast amounts of data.
TechniqueDatabase Systems, Data Cleaning Methods, Provenance techniques, Indexing methods.
UsersBig data analysts and users of data managements systems.
Theoretical study, Data providers, Information technology
Development and study of advanced methods for Data Mining, Big Data Analytics, Recommender Systems, Data Cleaning, and other technologies related to the management and analysis of large amounts of data.
TechniqueData Mining, Big Data Analytics, Recommender Systems, Data Cleaning
UsersAnalysts and managers of large amounts of data
Informatics, Data quality, Pattern mining, Mathematics, Data analysis, Data mining
Both biological sciences and clinical medicine are currently overwhelmed by vast amounts of complex data and are becoming increasingly dependent on information technology for data analysis, interpretation and organisation. Although powerful data mining techniques are being developed within and outside the University, they are still underutilized in the life sciences. We aim to bring state-of-the-art data mining techniques to life science applications by setting up interdisciplinary collaborations between computer scientists, life scientists and clinicians. Core activities are: 1) the introduction, adaptation and application of innovative pattern mining and machine learning techniques to heterogeneous 'omics data (genome, transcriptome, proteome and metabolome) and to clinical information; 2) using these techniques to generate computational (network) models for biological systems and diseases; and 3) the development of interactive and intuitive visualizations of complex life science data and pattern mining results.
TechniqueVarious bioinformatics, data mining and artificial intelligence techniques: analysis, interpretation, pattern mining, integration of heterogeneous 'omics data (genome, transcriptome, proteome, metabolome), sequence and structure analysis, spectrum analysis and interpretation, functional analysis of molecular data, multivariate statistics, network theory, algorithmic modeling, advanced machine learning, deep learning, advanced data visualization, prototyping
UsersLife scientists, biomedical researchers, clinicians, molecular biologists
Artificial intelligence, Systems biology, Systems medicine, Pattern mining, Computational biology, Bioinformatics, Data mining
My current research interest is the development of automated methods for pharmaceutical compounds identification, i.e. structure elucidation of drug impurities and degradation products. Major research activities include building large spectral library from historical pharmaceutical data and developing advanced machine learning models for compound substructure recommendation. Data used in this study are massive high-resolution mass spectrometry data accumalated in Janssen Pharmaceuticals.
TechniqueMass spectrometry, Machine learning, Network and Graphs, Web server development
UsersLife scientists, biomedical researchers, clinicians, molecular biologists, microbiologist
Dr. Meysman specializes in the application of data mining and artificial intelligence techniques on biomedical data. He has worked on molecular 'omics data, genetic data, medical data and immunological data. He has experience with several common bioinformatics pipelines and has aided in the development of bioinformatics databases.
TechniqueThe data mining expertise includes a wide range of techniques from unsupervised methods (e.g. principle component analysis, frequent item set mining) to supervised methods (e.g. lasso regression, random forest, convolutional neural networks).
UsersDr. Meysman has collaborated in the past with research hospitals, general practitioners, biotech and pharma companies.
Computational biology, Bioinformatics, Immunogenicity