Description
Leader of the group Life Sciences and Health: Leen Stougie.
The CWI Life Sciences and Health (LSH) group is a group of computer scientists and mathematicians whose research focus is on the analysis and design of models and algorithms as well as their direct application to important challenges in the LSH domain.
On the application side, our present team of researchers has expertise in, e.g., computational genomics, medical informatics, computational phylogenetics, and biological network analysis. On the methodological side, we come from different backgrounds, e.g., computational intelligence, computational data science, and operations research. Methodologically, we develop new theories, models, algorithms and decision support tools, for problems that arise mostly in collaboration with experimental biologists and medical experts. We actively collaborate in projects with academic hospitals, biological and biochemical research institutes, and industry. Click here for more information about our group structure.
The LSH group participates in the INRIA International team ERABLE.
Seminars: The LSH group organizes a monthly seminar.
Watch our group video to get a glimpse of our activities.
Vacancies
PhD students, on evolutionary machine learning for explainable AI in medicine.
Centrum Wiskunde & Informatica (CWI) and Leiden University Medical Center (LUMC) have two vacancies for talented PhD students, on evolutionary machine learning for explainable AI in medicine.
News
Best Italian PhD thesis prize for CWI's Giulia Bernardini
On 14 September 2021 the Italian chapter of EATCS awarded a prize for the Best Italian PhD Thesis in Theoretical Computer Science ex aequo to Giulia Bernardini (CWI) and Francesco Dagnino (University of Genova).
JoLEA: new lecture series on cutting-edge research on Evolutionary Algorithms
CWI, Leiden University, Utrecht University and VU Amsterdam proudly present the new Joint Lectures on Evolutionary Algorithms (JoLEA) series: top-quality lectures on EAs.
Three GECCO Awards for AI in healthcare
CWI researchers and partners won three awards for AI in healthcare at the ACM Genetic and Evolutionary Computation COnference (GECCO) 2021: the Best Paper Award in the Genetic Algorithms track, the SIGEVO Dissertation Award 2021 and a Silver HUMIES Award.
Funding for Explainable Artificial Intelligence for medical professionals
LUMC, Amsterdam UMC, and CWI have received funding from the Gieskes-Strijbis Fund to enhance the understanding of AI by doctors.
Members
- Matthias Bakker
- Martijn Bosma
- Peter Bosman
- Anton Bouter
- Aleksandr Chebykin
- Nick Cleintuar
- Joost Commandeur
- Arkadiy Dushatskiy
- Luc Everse
- Esteban Gabory
- Monika Grewal
- Arthur Guijt
- Damy Ha
- Joe Harrison
- Iwan Hoogenboom
- Nando Kartoredjo
- Jan Karel Lenstra
- Dazhuang Liu
- Anne Luesink
- Vincent Luo
- Joas Mulder
- Solon Pissis
- Renzo Scholman
- Evi Sijben
- Leen Stougie
- Michelle Sweering
- Marco Virgolin
- Wiktor Zuba
Associated Members
Publications
-
Bernardini, G, Conte, A., Gourdel, G., Grossi, R, Loukides, G, Pisanti, N, … Sweering, M.J.M. (2022). Hide and mine in strings: Hardness, algorithms, and experiments. IEEE Transactions on Knowledge and Data Engineering. doi:10.1109/TKDE.2022.3158063
-
Zhong, H, Loukides, G, & Pissis, S. (2022). Clustering sequence graphs. Data & Knowledge Engineering, 138, 101981.1–101981.21. doi:10.1016/j.datak.2022.101981
-
Chen, H, Dong, C, Fan, L, Loukides, G, Pissis, S, & Stougie, L. (2021). Differentially Private string sanitization for frequency-based mining tasks. In Proceedings of the 21st IEEE International Conference on Data Mining, ICDM 2021 (pp. 41–50). doi:10.1109/ICDM51629.2021.00014
-
Bernardini, G, Chen, H, Fici, G, Loukides, G, & Pissis, S. (2021). Reverse-safe data structures for text indexing. In Proceedings of the Workshop on Algorithm Engineering and Experiments (pp. 199–213). doi:10.1145/3461698
-
Luo, X, Kang, X, & Schönhuth, A. (2021). phasebook: haplotype-aware de novo assembly of diploid genomes from long reads. Genome Biology, 22(1). doi:10.1186/s13059-021-02512-x
-
Conte, A., Grossi, R, Loukides, G, Pisanti, N, Pissis, S, & Punzi, G. (2021). Beyond the BEST Theorem: Fast assessment of Eulerian Trails. In Proceedings of Fundamentals of Computation Theory (pp. 162–175). doi:10.1007/978-3-030-86593-1_11
-
Loukides, G, & Pissis, S. (2021). Bidirectional string anchors: A new string sampling mechanism. In Annual European Symposium on Algorithms (pp. 64:1–64:21). doi:10.4230/LIPIcs.ESA.2021.64
-
Chen, H, Conte, A., Grossi, R, Loukides, G, Pissis, S, & Sweering, M.J.M. (2021). On breaking truss-based communities. In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery & Data Mining (pp. 117–126). doi:10.1145/3447548.3467365
-
Przewozniczek, M.W, Komarnicki, M.M, Bosman, P.A.N, Thierens, D, Frej, B, & Luong, N.H. (2021). Hybrid linkage learning for permutation optimization with Gene-pool optimal mixing evolutionary algorithms. In GECCO 2021 Proceedings (pp. 1442–1450). doi:10.1145/3449726.3463152
-
Bliek, L, Guijt, A, & Karlsson, R. (2021). Hospital simulation model optimisation with a random ReLU expansion surrogate model. In GECCO 2021 Proceedings (pp. 13–14). doi:10.1145/3449726.3463279
Software
VirtualLeaf: a modeling framework for plant tissue morphogenesis
VirtualLeaf is a computer modeling framework for the simulation of plant tissue morphogenesis, i.e., the biological development of an organism's shape
Current projects with external funding
-
Statistical Models for Structural Genetic Variants in the Genome of the Netherlands
-
Algorithms for PAngenome Computational Analysis (ALPACA)
-
Fast, accurate, and insightful brachytherapy treatment planning for cervical cancer through artificial intelligence (Brachytherapy treatment)
-
Distributed and Automated Evolutionary Deep Architecture Learning with Unprecedented Scalability (DAEDALUS)
-
Evolutionary eXplainable Artificial Medical INtelligence Engine (EXAMINE)
-
Fusible Evolutionary Deep Neural Network Mixture Learning from Distributed Data for Robust Medical Image Analysis (FEDMix)
-
Multi-Objective Deformable Image Registration (MODIR) – An Innovative Synergy of Multi-Objective Optimization, Machine Learning, and Biomechanical Modeling for the Registration of Medical Images with (MODIR)
-
Networks
-
Networks COFUND postdocs
-
Uitlegbare kunstmatige intelligentie (None)
-
Optimization for and with Machine Learning (OPTIMAL)
-
Pan-genome Graph Algorithms and Data Integration (PANGAIA)
-
Transparent, Reliable and Unbiased Smart Tool for AI (TRUST-AI)
Related partners
-
AMC Medical Research
-
CNRS
-
Elekta Limited
-
European Molecular Biology Laboratory
-
INRIA
-
Universita di Pisa
-
Xomnia
-
Academisch Medisch Centrum
-
Biomedical Imaging Group Rotterdam
-
Erasmus Universiteit Rotterdam
-
Geneton S.R.O.
-
Heinrich-Heine-Universitaet Dusseldorf
-
Illumina Cambridge
-
Institut Pasteur
-
Leids Universitair Mediach Centrum
-
Univerzita Komenskeho V Bratislave
-
Universiteit Leiden
-
Universitaet Bielefeld
-
Universita' Degli Studi di Milano-Bicocca
-
Universiteit van Tilburg