Vincent Fortuin, MSc CBB ETH UZH

"The scientist is not a person who gives the right answers, he's one who asks the right questions." - Claude Lévi-Strauss

PhD Student

E-Mail
fortuin@get-your-addresses-elsewhere.inf.ethz.ch
Phone
+41 44 633 66 87
Address
ETH Zürich
Department of Computer Science
Biomedical Informatics Group
Universitätsstrasse 6
CAB F 53.1
8006 Zürich
Room
CAB F 51.2
twitter
@vincefort

I am interested in the interface between deep learning and probabilistic modeling. I am particularly keen to develop models that are more interpretable and data efficient, since these are two major requirements in the field of health care.

I did my undergraduate studies in Molecular Life Sciences at the University of Hamburg, where I worked on phylogeny inference for quickly mutating virus strains with Andrew Torda. I then went to ETH Zürich to study Computational Biology and Bioinformatics, in a joint program with the University of Zürich, with a focus on systems biology and machine learning. My master's thesis was about the application of deep learning to gene regulatory network inference under supervision of Manfred Claassen. During my studies I also spent some time in Jacob Hanna's group at the Weizmann Institute of Science, working on multiomics data analysis in stem cell research. Before joining the Biomedical Informatics group as a PhD student, I worked on deep learning applications in natural language understanding at Disney Research.

Abstract The reconstruction of gene regulatory networks from time resolved gene expression measurements is a key challenge in systems biology with applications in health and disease. While the most popular network inference methods are based on unsupervised learning approaches, supervised learning methods have proven their potential for superior reconstruction performance. However, obtaining the appropriate volume of informative training data constitutes a key limitation for the success of such methods. Here, we introduce a supervised learning approach to detect gene-gene regulation based on exclusively synthetic training data, termed surrogate learning, and show its performance for synthetic and experimental time-series. We systematically investigate different simulation configurations of biologically representative time-series of transcripts and augmentation of the data with a measurement model. We compare the resulting synthetic datasets to experimental data, and evaluate classifiers trained on them for detection of gene-gene regulation from experimental time-series. For classifiers, we consider hybrid convolutional recurrent neural networks, random forests and logistic regression, and evaluate the reconstruction performance of different simulation settings, data pre-processing and classifiers. When training and test time-courses are generated from the same distribution, we find that the largest tested neural network architecture achieves the best performance of 0.448 +/- 0.047 (mean +/- std) in maximally achievable F1 score over all datasets outperforming random forests by 32.4 % +/- 14 % (mean +/- std). Reconstruction performance is sensitive to discrepancies between synthetic training and test data, highlighting the importance of matching training and test data domains. For an experimental gene expression dataset from E.coli, we find that training data generated with measurement model, multi-gene perturbations, but without data standardization is best suited for training classifiers for network reconstruction from the experimental test data. We further demonstrate superiority to multiple unsupervised, state-of-the-art methods for networks comprising 20 genes of the experimental data from E.coli (average AUPR best supervised = 0.22 vs best unsupervised = 0.07). We expect the proposed surrogate learning approach to be broadly applicable. It alleviates the requirement for large, difficult to attain volumes of experimental training data and instead relies on easily accessible synthetic data. Successful application for new experimental conditions and other data types is only limited by the automatable and scalable process of designing simulations which generate suitable synthetic data.

Authors Stefan Ganscha, Vincent Fortuin, Max Horn, Eirini Arvaniti, Manfred Claassen

Submitted bioRxiv Preprints

Link DOI

Abstract Human professionals are often required to make decisions based on complex multivariate time series measurements in an online setting, e.g. in health care. Since human cognition is not optimized to work well in high-dimensional spaces, these decisions benefit from interpretable low-dimensional representations. However, many representation learning algorithms for time series data are difficult to interpret. This is due to non-intuitive mappings from data features to salient properties of the representation and non-smoothness over time. To address this problem, we propose to couple a variational autoencoder to a discrete latent space and introduce a topological structure through the use of self-organizing maps. This allows us to learn discrete representations of time series, which give rise to smooth and interpretable embeddings with superior clustering performance. Furthermore, to allow for a probabilistic interpretation of our method, we integrate a Markov model in the latent space. This model uncovers the temporal transition structure, improves clustering performance even further and provides additional explanatory insights as well as a natural representation of uncertainty. We evaluate our model on static (Fashion-)MNIST data, a time series of linearly interpolated (Fashion-)MNIST images, a chaotic Lorenz attractor system with two macro states, as well as on a challenging real world medical time series application. In the latter experiment, our representation uncovers meaningful structure in the acute physiological state of a patient.

Authors Vincent Fortuin, Matthias Hüser, Francesco Locatello, Heiko Strathmann, Gunnar Rätsch

Submitted arXiv Preprints

Link

Abstract We present a novel approach to modeling stories using recurrent neural networks. Different story features are extracted using natural language processing techniques and used to encode the stories as sequences. These sequences can be learned by deep neural networks, in order to predict the next story events. The predictions can be used as an inspiration for writers who experience a writer's block. We further assist writers in their creative process by generating visualizations of the character interactions in the story. We show that suggestions from our model are rated as highly as the real scenes from a set of films and that our visualizations can help people in gaining deeper story understanding.

Authors Vincent Fortuin, Romann M. Weber, Sasha Schriber, Diana Wotruba, Markus Gross

Submitted The Thirtieth AAAI Conference on Innovative Applications of Artificial Intelligence

Link