Andrea Ganna
@andganna.bsky.social
Associate Prof in health data science @HiLIFE_helsinki @FIMM_UH - MGH/Harvard - Playing with all kind of data - http://dsgelab.org
Job opportunity! 📢 The Faculty of Science and FIMM @helsinki.fi are recruiting a Research Fellow / University Researcher in AI for Population Health and Genomics for a fixed-term appointment of maximum 4 years. Apply by July 31: jobs.helsinki.fi/job/Helsinki... @andganna.bsky.social
Can we quantify the impact of individual DNA mutations on healthcare costs? In our new preprint we ran the largest GWAS of healthcare costs to date: 1,429,889 individuals, 11 cohorts, 7 countries, across inpatient, outpatient, primary care, and prescription expenditure 💰🧬
🔎 “Nowadays we have more data than ever.” 🧬 How can #healthdata, #genomics and #AI help us better understand disease? Our @andganna.bsky.social explains how large-scale datasets can reveal risk factors, disease pathways and patterns that targeted research may miss. youtu.be/kTXxmYiCZJU
#MeetTheSpeaker - Health Data and a Fairer AI with Andrea Ganna
YouTube video by Human Technopole
youtu.be
📢I'm setting up a new team at the @humantechnopole in Milan. We have several openings in AI applied to nationwide health data, biobank-scale -omics. Milan is a beautiful city and at @humantechnopole is top notch. You can find post-doc positions here: careers.humantechnopole.it/job/Postdoc/...
Postdoc
Postdoc
careers.humantechnopole.it
FIMM is joining forces with @ellisinstitute.fi to launch the FINe-Health Foundry project aiming to build the world’s first nationwide healthcare foundation model. The project has received ~€5M in Business Finland's Rise to Challenge funding. @andganna.bsky.social www.helsinki.fi/en/hilife-he...
Rise to Challenge funding for building the world’s first nationwide foundation model for healthcare | HiLIFE – Helsinki Institute of Life Science | University of Helsinki
FIMM joins forces with ELLIS Institute Finland to establish a new, globally competitive excellence cluster aimed at unlocking next-generation decision-making in healthcare and beyond.
helsinki.fi
MSc Lisa Eick from @andganna.bsky.social's group will defend her doctoral dissertation "Improving Cross-Biobank Genetics Through Phenotype Refinement and Machine Learning" @helsinki.fi on 29 May at 13:00. Opponent: Associate Prof Sandra Sanchez-Roige (UCSD) 🔗 tapahtumat.helsinki.fi/en-FI/page/6...
New preprint on a controversial topic: Through which socioeconomic mechanisms do individuals with higher genetic predisposition for educational attainment end up with higher income over their working life? We study this using uniquely rich Finnish data.
New preprint 👇 Does diagnostic misclassification in EHR-based psychiatry GWAS suppress genetic discovery? We use simulations and FinnGen data to expand the SuperControl framework and propose a new ML approach (PRISMA) to boost signal discovery. Led by Lisa Eick & Zhiyu Yang!
This week on The Genetics Podcast, @andganna.bsky.social joined host Patrick Short to discuss advances in genetics and data-driven medicine, including the the promise and limits of polygenic risk scores for disease prediction and clinical trials. 🎧 podcasts.apple.com/fi/podcast/e...
🚨New preprint out Mapping real-world statin adherence at population scale (doi.org/10.64898/202...) We analysed >1 million long-term statin users in Finland and Italy (Lombardy), identified adherence patterns, and examined baseline factors associated with declining adherence.
Longitudinal patterns and determinants of statin adherence in over one million individuals from Finland and Italy
Medication adherence is critical for effective management of chronic diseases and reducing healthcare burdens. Statins, commonly prescribed for cardiovascular disease prevention, require sustained, li...
doi.org
New preprint 👇 Does diagnostic misclassification in EHR-based psychiatry GWAS suppress genetic discovery? We use simulations and FinnGen data to expand the SuperControl framework and propose a new ML approach (PRISMA) to boost signal discovery. Led by Lisa Eick & Zhiyu Yang!
🌟 Applications for the 2026 Leena Peltonen School of Human Genetics are open! Back after a great 2025 edition: ~20 global leaders and ~20 PhD students shaping the future of genomics. 📅 July 26–30, 2026 📍 Wellcome Genome Campus, UK 📝 Apply by March 6 → www.lpshg.com
🌟 Applications for the 2026 Leena Peltonen School of Human Genetics are open! Back after a great 2025 edition: ~20 global leaders and ~20 PhD students shaping the future of genomics. 📅 July 26–30, 2026 📍 Wellcome Genome Campus, UK 📝 Apply by March 6 → www.lpshg.com
— Genetiikka vaikuttaa persoonallisuuteemme, ja persoonallisuutemme vaikuttaa siihen, mitä opiskelemme. Voimme nyt havaita näitä yhteyksiä selvemmin suoraan DNA:stamme, sanoo @andganna.bsky.social. Linkki Nature Genetics -lehdessä julkaistuun tutkimukseen: www.nature.com/articles/s41...
Genetic associations with educational fields - Nature Genetics
Genome-wide analyses of 10 educational fields identify 17 associated loci. Analysis of genetic clustering across specializations identifies two key dimensions that show genetic overlap with personalit...
nature.com
Jakob German from @andganna.bsky.social's group @hilife-helsinki.bsky.social will defend his doctoral dissertation "Genetically-Informed Real-World Evidence and Trial Design on 12 Dec. Linda Kachuri, Stanford University, will serve as the opponent. Welcome! 🔗 tapahtumat.helsinki.fi/en-FI/page/6...
1/ 🚨New paper in Nature Genetics Genetic factors are associated with the educational fields people study, from arts to engineering. Article: www.nature.com/articles/s41... FAQ: www.thehastingscenter.org/genomic-find...
Genetic associations with educational fields - Nature Genetics
Genome-wide analyses of 10 educational fields identify 17 associated loci. Analysis of genetic clustering across specializations identifies two key dimensions that show genetic overlap with personalit...
nature.com
Happy to have contributed to this study! Our personality and behaviors, as captured by genetic markers, also influence what we end up studying and, eventually, our professional careers
Rosa Cheesman@rosacheesman.bsky.social · 9mo ago1/ 🚨New paper in Nature Genetics Genetic factors are associated with the educational fields people study, from arts to engineering. Article: www.nature.com/articles/s41... FAQ: www.thehastingscenter.org/genomic-find...
EU vice-president Virkkunen launches RAISE: resource for AI science in Europe. Not exactly clear what this entails. But i understand: more money, more networking.
Are you in #Boston for #ASHG25? Come by and check out my poster (#1023) today from 2:30–4:30 PM. Would love to connect and discuss about it :)
Andrea Ganna@andganna.bsky.social · 10mo ago🎉 New preprint out! "Removing genetic effects on plasma proteins enhances their utility as disease biomarkers" We show that adjusting plasma proteins for genetic effects can make them stronger predictors of disease 👉 doi.org/10.1101/2025...
🎉 New preprint out! "Removing genetic effects on plasma proteins enhances their utility as disease biomarkers" We show that adjusting plasma proteins for genetic effects can make them stronger predictors of disease 👉 doi.org/10.1101/2025...
Very important paper for the geroscience hypothesis. Healthy aging is critical, even in the face of obvious disease states.
Andrea Ganna@andganna.bsky.social · 11mo ago🧬💥 Do the genetics that make you develop a disease also help you survive it? Not much. Our new study in Nature Genetics including 9 disease and 7 biobanks shows: • Susceptibility variants ≠ survival • PRSs for onset weak at predicting progression • Lifespan PRS predicts survival better
💥 New preprint & our first RCT! 💥 Does an extremely high or low BMI polygenic score influence weight loss after a diet intervention? GENEROOS is a 6-month randomized diet vs. control trial testing if genetic predisposition to higher BMI affects weight loss in overweight adults
A pretty comprehensive comparison of most actual #proteomics platforms: Current landscape of plasma proteomics from technical innovations to biological insights and biomarker discovery www.nature.com/articles/s42...
Current landscape of plasma proteomics from technical innovations to biological insights and biomarker discovery - Communications Chemistry
Plasma proteome profiling has surged as a promising avenue for biomarker discovery, yet comprehensive platform comparisons remain scarce. Here, the authors evaluate eight proteomics platforms, revealing key differences and complementary strengths, providing crucial insights for researchers into coverage trade-offs and implicating biomarker discovery and clinical applications.
nature.com
🧬💥 Do the genetics that make you develop a disease also help you survive it? Not much. Our new study in Nature Genetics including 9 disease and 7 biobanks shows: • Susceptibility variants ≠ survival • PRSs for onset weak at predicting progression • Lifespan PRS predicts survival better
“Towards modeling evolving longitudinal health trajectories with a transformer-based deep learning model” in collaboration with Pekka Marttinen at @AaltoUniversity www.sciencedirect.com/science/arti...
Towards modeling evolving longitudinal health trajectories with a transformer-based deep learning model
Health registers provide valuable insights into individuals’ health trajectories. This study explores the use of deep learning to model and analyze th…
sciencedirect.com
If you are interested in our pilot use of cross-EU health data ahead of the European Health Data Space implementation, check this out pubmed.ncbi.nlm.nih.gov/40926479/
User journeys in cross-European secondary use of health data: insights ahead of the European Health Data Space - PubMed
The European Health Data Space (EHDS) regulation aims to facilitate cross-border sharing of health data across Europe. However, practical challenges related to data access, interoperability, quality, ...
pubmed.ncbi.nlm.nih.gov
A project many years in the process, we’re pleased to present our work on multi-ancestry meta-analysis across a boatload of traits in the UK Biobank: www.nature.com/articles/s41...
Pan-UK Biobank genome-wide association analyses enhance discovery and resolution of ancestry-enriched effects - Nature Genetics
Genome-wide analyses for 7,266 traits leveraging data from several genetic ancestry groups in UK Biobank identify new associations and enhance resources for interpreting risk variants across diverse p...
nature.com
Cool work from @ewanbirney.bsky.social Moritz Gerstung, Tom Fitzgerald about modeling health trajectories with generative AI! www.nature.com/articles/s41...
Learning the natural history of human disease with generative transformers - Nature
Delphi-2M forecasts a person’s future health, covering more than 1,000 diseases, provides insights into co-morbidity dynamics and generates synthetic data for the training of AI models that have never...
nature.com
Some people call it a minefield. Others call it dangerous, even irresponsible. I call it the most promising field in life sciences. My love letter to social science genetics: communities.springernature.com/posts/a-love...
A Love Letter to Social Science Genetics
Some people call social science genetics a minefield. Others call it dangerous, even irresponsible. I call it the most promising field in life sciences.
communities.springernature.com
