25-29 September 2017 (5th edition) – registration open!
Academic Medical Center, Amsterdam, the Netherlands
Route and travel information
Dr. ir. Perry. Moerland (Academic Medical Center), prof. dr. ir. Marcel Reinders (Delft University of Technology), prof. dr. Lodewyk Wessels (Netherlands Cancer Institute)
The study load of this course is 3 EC. Participants will get a certificate after successfully completing this course.
Many problems in bioinformatics require classification: prediction of the class to which a certain object (i.e. a gene, protein, cell, patient, …) belongs. This calls for algorithms that can assign the most likely label (discrete output) to an object, given one or more measurements on that object. For most interesting problems, the underlying physics are too complex to explicitly design such an algorithm. In such cases, often a machine learning approach is taken: an algorithm is constructed, with parameters that are tuned based on an available dataset of training examples. The algorithm should predict the labels for these examples as well as possible, yet still generalize, i.e. perform well on objects not seen before. Some examples of classification problems in bioinformatics are gene finding (sequence in, gene presence out), diagnostics (gene expression data in, diagnosis out), data integration (measurements in, probability of interaction out), etc.
In this course, we will introduce basic techniques from the fields of pattern recognition and machine learning to solve bioinformatics problems in a mixture of theory and lab sessions. After having followed this course, the student has a good understanding of basic pattern recognition techniques and is able to recognize what method is most applicable to data analysis problems (s)he encounters in bioinformatics applications. Topics include parametric and non-parametric classifiers, feature selection, dimensionality reduction, clustering, hidden Markov models, neural networks, and support vector machines. The course is aimed at PhD students with a background in bioinformatics, computer science or a related field, and life sciences. Participants from the private sector are also welcome. A working knowledge of basic statistics and linear algebra is assumed. Preparation material on statistics and linear algebra will be distributed before the course, to be studied by students missing the required background.
The structure of the course is as follows:
- Monday (Introduction; Marcel Reinders): Introduction to pattern recognition: measurements, features, classification. Supervised vs. unsupervised learning, relation to regression. Bayesian framework: risk, cost; evaluation: ROCs, cross-validation. Density estimation: histograms, nearest neighbour, Parzen, Gaussian Bayesian classification.
- Tuesday (Classification; Perry Moerland): Parametric classifiers: (D)LDA, (D)QDA. Nonparametric classifiers: k-NN, Parzen. Discriminant analysis: LDA, logistic regression. Decision trees and random forests.
- Wednesday (Feature selection and extraction; Lodewyk Wessels): Feature selection: criteria, search algorithms (forward, backward, branch & bound). Sparse classifiers: Ridge, LASSO. Feature extraction: PCA, Fisher. Embeddings: MDS.
- Thursday (Clustering and HMMs; Perry Moerland): Hierarchical clustering. Agglomerative clustering. Model-based clustering: mixtures-of-Gaussians, Expectation-Maximization. Hidden Markov models.
- Friday (Selected advanced topics; Marcel Reinders): Artificial neural networks. Support vector machines. Classifier ensembles. Complexity and regularisation. Deep learning.
The course is aimed at PhD students with a background in bioinformatics, computer science or a related field, life sciences. Participants from the private sector are also welcome. A working knowledge of basic statistics and linear algebra is assumed. Preparation material on statistics and linear algebra will be distributed before the course, to be studied by students missing the required background.
After having followed this course, the student has a good understanding of basic pattern recognition and machine learning techniques and is able to recognize what method is most applicable to data analysis problems (s)he encounters in bioinformatics applications.
Maximum number of participants is 25, so register soon to be sure of a course seat!
The course fee includes:
- Course material: Handouts, a lab course manual and software required for the lab course (MATLAB toolboxes) will be made available online.
- Catering: Coffee, tea and soft drinks and lunch will be provided.
You can register for this course via the enrollment form.