Tommi Suvitaival
Data Scientist - Researcher (Asst. Prof.-Level)
Data Scientist - Researcher (Asst. Prof.-Level)
The lipidome in alcohol-related liver disease (ALD).
In this publication, we show that sphingomyelins (SMs) are depleted with liver fibrosis, both, in the liver and in circulation. The depletion is stronger in ‘pure’ ALD than in NAFLD-like ALD, and it is associated with an elevated risk of disease progression. Moreover, we show by Mendelian randomization that ALD has a causal link to lower blood SM level in general population.
The pathogenesis of type 1 diabetes.
I have reviewed, how the lipidome is affected at the onset of type 1 diabetes. This publication is based on an open-access database of findings from relevant scientific articles on the topic, which I created and made available for further research and updating. Read the publication for a shortlist of relevant lipids that I propose as a starting point for further validation studies.
lipidomeR is a new tool for lipidome-wide visualization of statistical associations.
The tool creates integrative heatmaps of patterns in the entire measured lipidome. The package can be installed in R with the command 'install.packages("lipidomeR")'. See lipidomeR.org for reproducible examples, the manuscript preprint for guidance on the systematic interpretion of the results, and CRAN for documentation of the tool.
I am a data scientist with a background in machine learning and computational sciences, and a specific focus in molecular medicine.
While based in Stockholm, I work as researcher at the academic level of Assistant Professor at Steno Diabetes Center Copenhagen (SDCC). SDCC is the largest center of diabetes treatment in Scandinavia and it is funded by the Novo Nordisk Foundation.
I am affiliated with the Translational Type 1 Diabetes Research group, where I work as a bioinformatics and biostatistics specialist to process, analyze, visualize and understand complex omics data from the small molecule profiling platforms managed by the group. Moreover, I work 30 % as data science consultant to the Clinical and Translational Research Department in a single-handed advisory responsibility to 150+ researchers in five research groups.
During my career, I have acquired an in-depth knowledge of computational methods for data-driven analysis as well as a broad understanding of application areas in health and clinical research. Lately, the focus of my work has been in the development and application of computational methods for studying biomarkers of diabetes, its development, treatment and complications.
At SDCC, I have set up extensive computational pipelines for a streamlined processing, analysis and visualization of data from the team’s omics profiling platforms. While I continue to develop these solutions, I collaborate with clinicians, chemists, biologists and statisticians to help them understand complex research data and to uncover novel insights from measured molecular profiles in large clinical studies.
Since 2023, I am part of the Translational Type 1 Diabetes Research group led by M.D. Prof. Flemming Pociot. I work at the intersection of the Translational Type 1 Diabetes Research team and the Translational Omics and Islet Biology team.
Between 2018 and 2024, I worked with Drs. Cristina Legido-Quigley and Karolina Sulek to build and operate the computational foundations of omics data processing for what was then the Systems Medicine group. This work enabled the large mass-spectrometry-based cohort profiling projects, including IMI-INNODIA, IMI-RHAPSODY and GALAXY/MicrobLiver. We continue to work together on discovery research with the data generated in these cohorts.
Between 2016 and 2017, I was supervised by Prof. Lars Ove Dragsted and M.D. Prof. Peter Rossing, with whom I continue to collaborate on the PROFIL cohort and the PROTON project. I started my post-doctoral career in 2015 by working with Dr. Matej Orešič on novel lipidomics profiling projects.
I completed a PhD (Doctor of Science in Technology) from Aalto University and Helsinki Institute for Information Technology in 2014. For my doctoral research, I was privileged to work with Academy Prof. Samuel Kaski on Bayesian models for data integration across measurement domains, organisms and time points, in what is nowadays known as the Probabilistic Machine Learning research group.
As part of my PhD work, I had a great opportunity to visit University of Glasgow to work with Dr. Simon Rogers on non-parametric Bayesian modeling of mass-spectral measurements.
Prior to my doctoral studies, I completed a MSc. (Tech.) degree in bioinformation technology from Helsinki University of Technology in 2009. My Thesis on dimensionality-reducing modeling of covariates’ effects on molecular levels was instructed by Dr. Ilkka Huopaniemi.
My research career started in 2006, when I got an opportunity to work for two summers as an undergraduate intern in a computational physics group led by Prof. Jukka Tulkki. During the time, I wrote a BSc. (Tech.) Thesis on quantum photonics at what was then known as the Laboratory of Computational Engineering at Helsinki University of Technology.
