Research output per year
Research output per year
Personal profile
Short presentation
I am a specialist in Bayesian modelling and probabilistic machine learning. Currently, my research mostly focuses on probabilistic machine learning applied to protein structure prediction and protein evolution. I am particularly interested in the use of deep probabilistic programming, making use of the deep probabilistic programming languages Pyro and Numpyro, and the application of directional statistics to represent non-Euclidean data. My group also contributes to the development of Pyro and Numpyro.
Primary fields of research
Probabilistic machine learning, deep probabilistic progarmming, statistical structural bioinformatics
CV
ORCID: 0000-0003-2917-3602
Date of Birth: 24/06/1971
Contact: +45 23960613, [email protected]
Webpage: https://thamelry.github.io
Scientific focus areas: protein structure prediction, structural biology,, Bayesian statistics, machine learning, data science, deep probabilistic programming
Education
|
Academic degree |
University |
Year |
|
PhD (protein crystallography) |
Free University of Brussels (VUB), BE |
1999 |
|
Masters (bio-engineer) |
Free University of Brussels (VUB), BE |
1994 |
Positions
|
Position |
Place |
From |
To |
|
Visiting associate professor (50%) |
DIKU |
2016 |
Now |
|
Visiting professor |
University of Leeds, UK |
2011 |
2016 |
|
Associate professor |
University of Copenhagen, DK |
2007 |
now |
|
Assistant professor |
University of Copenhagen, DK |
2004 |
2007 |
|
Postdoc - Head bioinformatics research initiative VUB |
Free University of Brussels (VUB), BE |
2002 |
2004 |
|
Postdoc |
Free University of Brussels (VUB), BE and University of Århus, DK |
1999 |
2002 |
Selected offices, Academic Service, Professional activities 2012- 2016
|
Task |
Event |
From |
To |
|
Senior associate editor |
2023 |
Now | |
|
Main conference organizer |
Conference: Machine learning and molecules (190 participants, 13 international speakers) |
2017 | |
|
Main book editor |
Book: “Bayesian Methods in Structural Bioinformatics”. Springer Verlag. 386 pages. |
2012 | |
|
Conference organizer |
Conference: Machine Learning in Structural Bioinformatics (150 participants, 8 international speakers) |
2008 | |
|
Software developer |
Mocapy and Mocapy++: Machine learning library for dynamic Bayesian networks. |
2008 | |
|
Software developer |
Bio.PDB package in Biopython. Bio.PDB article cited 260 times. Biopython article cited 4110 times. Bio.PDB is still (in 2023) a standard and widely-used tool for structural bioinformatics. |
2004 |
Academic awards and honours
|
Award/honour |
Year |
|
Ishango prize for young scientists in Brussels capital region. |
2002 |
|
DSM Science & Technology Award Europe - 2nd prize. |
1999 |
Current funding
|
Principal Investigator (PI) / Partner |
Funding Source & Amount of Money |
Project title |
From |
To |
|
PI |
Villum Fonden - Villum EXPERIMENT, 1.837.956 DKK |
Predicting protein structure, mutations and dynamics with deep generative models. |
2023 |
2025 |
|
Partner. PI: Prof. Anders Lund, BRIC. |
Independent Research Fund Denmark-FNU, 2.863.996 DKK |
Identification and Characterization of Specialized Ribosome Subtypes |
2022 |
2025 |
|
PI (Co-applicant: Prof. Fritz Henglein, DIKU) |
Independent Research Fund Denmark-FTP, 5.901.438 DKK |
Deep probabilistic programming for protein structure prediction |
2020 |
2024 |
|
PI |
GKN Aerospace, Sweden, 2.053.400 DKK |
Application of deep learning in aerospace industry manufacturing. |
2019 |
2023 |
Current international collaborators
- Prof. Jotun Hein, U. Oxford, UK (protein evolution)
- Prof. John T. Kent and Prof. Kanti V. Mardia, U. Leeds, UK (directional statistics)
- Assoc. Prof. Christophe Ley, U. Luxembourg (statistics, machine learning)
- Assoc. Prof. Douglas Theobald, U. Brandeis, USA (protein evolution)
- Assist. Prof. Eric Nalisnick, U. Amsterdam (probabilistic machine learning)
Publication overview
- 48 publications in PubMed
- 26 as communicating author
- Highlights: PNAS (2), Mol. Biol. Evol., PLoS Comp. Biol. (2), ICML, ICLR
- 79 publications in ORCID (0000-0003-2917-3602)
- H-index and number of citations (Google Scholar): 31 / 7723.
- Two most cited articles: 4078 and 750 citations.
- Textbook: “Bayesian methods in structural bioinformatics”, 386 pages, Springer, 2012.
- 36.000 downloads since 2012 on springer.com
Supervision
- Supervised 8 postdocs and 15 PhD students.
- Current group : 2 postdocs, 3 PhD students
Current teaching
- Introduction to data science (DIKU), 7.5 ECTS
- Structural bioinformatics (BIO), 7.5 ECTS
- Python programming for data science (BIO-DIKU), 7.5 ECTS
- Probabilistic machine learning (DIKU, 7.5 ECTS)
- Bioinformatics individual projects (BIO), 7.5 ECTS
Recent outreach
- Researchers develop AI tool to combat coronavirus variants of the future. KU press release, 2021
- Flere unge skal have en fremtid med AI og machine learning. TechSavvy, 2018.
Collaborations and top research areas from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
Research output
-
Abstraction, mimesis and the evolution of deep learning
Eklöf, J., Hamelryck, T., Last, C., Grima, A. & Snis, U. L., 2024, In: AI and Society. 39, 5, p. 2349–2357 9 p.Research output: Contribution to journal › Journal article › Research › peer-review
Open AccessFile2 Downloads (Pure) -
AI Implementation and Capability Development in Manufacturing: An Action Research Case
Eklöf, J., Snis, U. L., Hamelryck, T. W., Grima, A. & Rønning, O., 2024, Proceedings of the 57th Hawaii International Conference on System Sciences - HICSS 2024. Hawaii International Conference on System Sciences, 10 p.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Open AccessFile21 Downloads (Pure) -
Mixture Models for Spherical Data with Applications to Protein Bioinformatics
Mardia, K. V., Barber, S., Burdett, P. M., Kent, J. T. & Hamelryck, T., 2022, Directional Statistics for Innovative Applications: A Bicentennial Tribute to Florence Nightingale. Springer, p. 15-32 (Forum for Interdisciplinary Mathematics).Research output: Chapter in Book/Report/Conference proceeding › Book chapter › Research › peer-review
1 Citation (Scopus) -
Persistent Topology of Protein Space
Hamilton, W., Borgert, J. E., Hamelryck, T. & Marron, J. S., 2022, Research in Computational Topology 2. Springer, p. 223-244 (Association for Women in Mathematics Series, Vol. 30).Research output: Chapter in Book/Report/Conference proceeding › Book chapter › Research › peer-review
1 Citation (Scopus) -
Efficient Generative Modelling of Protein Structure Fragments using a Deep Markov Model
Thygesen, C. B., Al-Sibahi, A. S., Steenmanns, C. S., Sanz Moreta, L., Sørensen, A. B. & Hamelryck, T. W., 2021, International Conference on Machine Learning, 18-24 July 2021, Virtual. PMLR, p. 10258-10267 (Proceedings of Machine Learning Research, Vol. 139).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Open AccessFile1 Citation (Scopus)55 Downloads (Pure) -
Time-efficient Bayesian Inference for a (Skewed) von Mises Distribution on the Torus in a Deep Probabilistic Programming Language
Ronning, O., Ley, C., Mardia, K. V. & Hamelryck, T., 2021, 2021 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI). IEEE, p. 1-8Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
1 Citation (Scopus) -
A community proposal to integrate structural bioinformatics activities in ELIXIR (3D-Bioinfo Community) [version 1; peer review: 1 approved, 3 approved with reservations]
Orengo, C., Velankar, S., Wodak, S., Zoete, V., Bonvin, A. M. J. J., Elofsson, A., Feenstra, K. A., Gerloff, D. L., Hamelryck, T., Hancock, J. M., Helmer-Citterich, M., Hospital, A., Orozco, M., Perrakis, A., Rarey, M., Soares, C., Sussman, J. L., Thornton, J. M., Tuffery, P., Tusnady, G. & 3 others, , 2020, In: F1000Research. 9, 27 p., 278.Research output: Contribution to journal › Journal article › Research › peer-review
Open AccessFile10 Citations (Scopus)182 Downloads (Pure) -
Bayesian protein superposition using Hamiltonian Monte Carlo
Moreta, L. S., Al-Sibahi, A. S. & Hamelryck, T., Oct 2020, Proceedings - IEEE 20th International Conference on Bioinformatics and Bioengineering, BIBE 2020. IEEE, p. 1-11 9288019Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review