The goal of the Computational Health focus area is to develop theory and computational methods for complex data and systems in medicine and healthcare. We focus on scaling up computation for large numbers of genomes, machine learning methods for medical big data, as well as complex network modelling and mining.  We collaborate with top medical research groups and hospitals to bring our tools towards practical use in healthcare decision support systems.

Listed below are supervisors taking part of this call who have their own funding for positions in their research projects.

Apply now
Project Information

Harri Lähdesmäki (Aalto University)

Deep generative modeling for continuous-time dynamics and biomedicine

We are looking for postdoc to work on deep generative modeling for applications that are at the intersection of biomedicine and health as well as continuous-time dynamics. Our research work involves developing new deep generative modeling methods for large-scale health datasets from Finnish biobanks, computational immunology, various single-cell datasets, and general data-driven modeling methods for continuous-time dynamics. Methodologically, the work revolves primarily around conditional deep generative models, neural ODEs, and Bayesian methods. Work can focus more on method development or can also include applications, depending on applicant’s own preference. Applicants are expected to have good knowledge of machine/deep learning, statistics, programming, and (optionally) interest in bioinformatics and biomedicine. For more information, see our research group web page:

Matti Pirinen (University of Helsinki)

Multivariate variable selection with applications to genetics

Our current ability to measure massive numbers of variables, for example, in biological sciences (millions of DNA variants) or in personal health applications (thousands of time points in activity monitoring) call for efficient ways to separate the important variables from unimportant ones. Additionally, the outcome space of the variable selection problem may be multidimensional, e.g., we may search for DNA variants that affect both measured biomarker levels and disease risk. This setting calls for methods to decompose the multivariate outcome space into most informative components.

We are looking for a postdoctoral researcher to work on realistic multivariate variable selection problems where variables may have been measured incompletely and where we may have access only to statistical summaries of the underlying data. Our previous work include the Bayesian approach implemented in the FINEMAP algorithm ( We have also first-hand experience on large-scale genetic data analyses, including, e.g., the world’s largest study on migraine genetics (Nature Genetics 2022, 54: 152-160).

This project includes both theoretical (statistical) and empirical (simulations and genetic data analysis) components and is connected to the most recent resources of genetic and health-related data from Finland and across the world.

Pekka Marttinen (Aalto University)

Machine Learning for Health (ML4H)

Accumulation of health data has enabled researchers to study questions such as: how to accurately predict the risk of disease, how to provide personalized treatment based on real-time patient data, or how to use genomic data to understand disease or antibiotic resistance. Central challenges in ML4H include noisy data, multiple heterogeneous data sources, learning about causality, interpreting the models, and assessing the uncertainty of predictions, to name a few. We tackle these by developing models and algorithms which leverage modern machine learning principles: Bayesian neural networks, deep latent variable models, Gaussian processes, causal inference, transformers, reinforcement learning, and natural language processing. Successful applicants are expected to have outstanding skills in machine learning, statistics, applied mathematics, or a related field, and the topic may be adjusted based on the applicant’s interests to either methodology or applications; examples of both can be found in

Sampsa Hautaniemi (University of Helsinki)

Modeling and machine learning in precision oncology

Cross-disciplinary research group of Prof. Sampsa Hautaniemi aims at discovering causes for drug resistance in cancer patients and effective treatment options to overcome drug resistance using mathematical modeling and machine learning. We have strong track-record in modeling and computational method development (e.g.,, &  as well as translating research results to clinical practice (e.g., We coordinate one of the largest ovarian cancer precision oncology projects in the world funded by EU Horizon 2020 (DECIDER; In DECIDER our focus is to discover effective treatment options for ovarian cancer patients who do not respond to chemotherapy anymore. More information and all our publications are available at our group website:

We are looking for post-doctoral researchers with strong experience in mathematical or statistical modeling, machine learning and interest in using real-world cancer patient data in modeling and analysis. Basic knowledge of cancer biology or genetics is not required but is considered as a plus. Examples of the possible projects are: mathematical modeling tumor evolution during treatment using longitudinal data; causal analysis of single-cell data; development and use of Deep Learning methods in histopathological images/genomics data; multi-omics integration.

The Hautaniemi group belongs to the Research Program in Systems Oncology (ONCOSYS; ONCOSYS consists of internationally acclaimed basic, translational and clinical researchers who share the vision of using cutting-edge measurement technology, real-world data and AI in cancer research in order to discover effective diagnostic, prognostic and therapeutic approaches. If you enjoy doing science in an interdisciplinary and collaborative environment, consider applying to us.