PhD Position in DANIO-Recode
PhD Position in AI-Powered Data Exploration for Regenerative Biology
We are looking for a motivated and talented PhD student with a background in computer science, machine learning, or data science (bioinformatics experience is a plus) to join our team at the University of Ljubljana, Slovenia. The position is fully funded through the Marie Skłodowska-Curie Actions (MSCA) ITN program, with a planned start date no later than October 2025. The position is for three years.
About DANIO-ReCODE
DANIO-ReCODE is European Marie Skłodowska-Curie Doctoral Network that combines biology and computer science to study how zebrafish regenerate organs like the brain, heart, and eyes. The project uses large-scale genomics, single-cell sequencing, and machine learning to understand the gene regulatory mechanisms behind regeneration. Computer science researchers will develop tools for integrating and visualizing multi-omics data, including advanced genome browsers and AI-based chat interfaces. The ultimate goal is to uncover how regeneration works at the molecular level and to make these insights accessible for future applications in regenerative medicine.
About the Project
DANIO-ReCODE is a European Marie Skłodowska-Curie Doctoral Network that will recruit 15 PhD students to explore how zebrafish regenerate complex organs like the brain, heart, and eyes. The network brings together experimental biologists and computer scientists to uncover the gene regulatory mechanisms driving regeneration, using cutting-edge methods in single-cell and bulk sequencing, multi-omics data analysis, and advanced data visualization. One of the PhD projects, based at the University of Ljubljana, will focus on developing an AI-powered data chatbot that helps researchers explore complex regeneration datasets. This chatbot will combine scientific literature mining, integration of gene expression and epigenetic data, and interactive query systems based on large language models. The goal is to make high-dimensional biological data accessible through natural-language conversation, supporting discovery and hypothesis generation in regenerative genomics. This call is for candidates interested in this specific project at the intersection of machine learning, natural language processing, and bioinformatics.
Our Research Group
You will join the Bioinformatics Laboratory (Biolab) at the University of Ljubljana, an internationally recognized research group at the forefront of machine learning, explainable AI, and data visualization. Our lab is the creator of Orange, one of the most widely used open-source platforms for visual programming in data science, with over 500 universities worldwide using it for teaching and research. We collaborate with leading institutions across Europe and the U.S., and our work regularly appears in top journals such as Nature Communications, Bioinformatics, and PLOS Computational Biology.
Biolab is known for turning cutting-edge research into accessible tools that empower scientists, educators, and students — from advanced models for biomedical data analysis to interactive AI-powered educational platforms. As part of our team, you'll contribute to high-impact international projects, gain access to state-of-the-art computing resources, and work in an open, creative, and collaborative environment where your ideas can shape the future of AI and bioinformatics.
You can read about our work in the following recent publications:
- Poličar PG, Zupan B (2025) Mach Learn 114(2): 1–27.
Uncovering temporal patterns in visualizations of high-dimensional data - Demšar J, Zupan B (2024) PLoS Comput Biol 20(12): e1012574
Hands-on training about data clustering with Orange Data Mining Toolbox - Godec P, Pančur M, Ilenič N, Čopar A, Stražar M, Erjavec A et al. (2019) Nat Commun 10(1): 4551
Democratized image analytics by visual programming through integration of deep models and small-scale machine learning - Poličar PG, Špendl M, Curk T, Zupan B (2024) Bioinformatics 40: i20–i29
Teaching bioinformatics through the analysis of SARS-CoV-2: project-based training for computer science students - Poličar PG, Stražar M, Zupan B (2024) J Stat Softw 109(3): 1–30
OpenTSNE: a modular Python library for t-SNE dimensionality reduction and embedding - Poličar PG, Stražar M, Zupan B (2021) Mach Learn
Embedding to reference t-SNE space addresses batch effects in single-cell classification - Stražar M, Žagar L, Kokošar J, Tanko V, Erjavec A, Poličar PG et al. (2019) Bioinformatics 35(14): i4–i12
scOrange – a tool for hands-on training of concepts from single cell data analytics - Žitnik M, Zupan B (2015) IEEE Trans Pattern Anal Mach Intell 37(1): 41–53
Data fusion by matrix factorization
We value creativity, autonomy, and collaboration. You will be encouraged to publish, present, and develop your own ideas within the framework of the DANIO-Recode project.
Your Environment
The PhD position is based in the Bioinformatics Laboratory at the Faculty of Computer and Information Science, University of Ljubljana. The lab is well-equipped and friendly, with a dedicated kitchen, fridge, and great coffee. You'll work in a collaborative space with other PhD students and researchers from computer science, bioinformatics, and AI.
University of Ljubljana — Who Else Studied Here?
The University of Ljubljana is one of the oldest and largest universities in Central Europe. It has a long-standing tradition of excellence in computer science, particularly in artificial intelligence and data science, and is consistently ranked among the top universities in the region.
Many widely used machine learning methods and tools were invented here:
- Erik Štrumbelj introduced the core idea behind SHAP, one of the most popular techniques for explaining black-box models like neural networks. In his 2010 paper with Igor Kononenko, they proposed a game-theoretic approach for interpreting individual predictions — now a standard in explainable AI.
- Igor Kononenko and Marko Robnik Šikonja developed ReliefF, one of the most widely used feature scoring algorithms in supervised learning, known for its ability to capture feature interactions.
- Janez Demšar, in a Machine Learning paper cited over 20,000 times, proposed critical distance diagrams, a widely adopted method for statistically comparing machine learning algorithms across multiple datasets.
- Marinka Žitnik, now a professor at Harvard and a leading figure in AI for biomedicine, developed a matrix factorization approach to data fusion during her PhD at Biolab, laying the groundwork for numerous advances in integrative biomedical AI.
- Miha Štajdohar contributed to the development of Orange and went on to co-found Genialis, a cutting-edge biotech company specializing in biomarker discovery, where he now serves as CTO.
- Jure Leskovec, a renown professor of Machine Learning at Stanford, finished his undergraduate studies here and yearly holds courses on graph analysis at our University.
- Jure Žbontar finished his Ph.D. thesis in our group while being supervised by Jann LeCun, one of the inventors of current AI. Jure went to work with Facebook and is now with OpenAI.
At the University of Ljubljana, you will be joining a tradition of innovation and impact in the field of machine learning — with alumni who have shaped the global AI landscape.
Living in Ljubljana
Ljubljana, the capital of Slovenia, is located in the heart of Europe. It’s a vibrant, safe, and green city with excellent public infrastructure, affordable living, and a lively international student community. Slovenia offers easy travel access to the Alps, Adriatic Sea, Vienna, Venice, and the Balkans—all within a few hours.
Eligibility
This position is open to candidates who have not lived or worked in Slovenia in the past 3 years.
How to Apply
To apply, please fill in the following form and provide details about your background, motivation, and experience:
We expect many applications, so please be clear and specific in your answers. Applications will be reviewed on a rolling basis until the position is filled.