{"id":160822,"date":"2025-07-02T03:00:50","date_gmt":"2025-07-02T01:00:50","guid":{"rendered":"https:\/\/www.cde.ual.es\/?p=160822"},"modified":"2025-07-01T13:58:06","modified_gmt":"2025-07-01T11:58:06","slug":"phd-position-at-the-university-of-bern-in-computational-biology-swirtzerland","status":"publish","type":"post","link":"https:\/\/www.cde.ual.es\/en\/phd-position-at-the-university-of-bern-in-computational-biology-swirtzerland\/","title":{"rendered":"PhD – Position at the University of Bern in Computational Biology – Swirtzerland"},"content":{"rendered":"

<\/p>\n

The PhD candidate will work on the development of interpretable deep learning for multi-omics data multi-scale models of the immune system with a focus on investigating cardiometabolic disease (CMD). We are seeking a highly motivated and ambitious PhD candidate for a project focused on developing interpretable deep learning models for the analysis of single-cell and spatially resolved multi-omics data associated with CMD. The PhD candidate will develop models that can automatically identify key molecular and morphological structures, such as clusters of cells, that are essential for making informed predictions. This project aims to enhance the use of multi-omics and spatially resolved data in clinical decision-making, hence, improving treatment guidance and prognosis.<\/p>\n

Key Responsibilities:
\n– Develop deep learning models for the analysis of spatially resolved data.
\n– Train this model using both publicly available single-cell data in CMD diseases, as well as spatially resolved molecular data generated by MIRACLE partners.
\n– Focus on model interpretability to identify significant spatial regions and immune profiles.
\n– Investigate and address uncertainties in AI models, adapting current reliability benchmarks for the analysis of single-cell datasets.
\n– Contribute to scientific recommendations on AI model robustness.<\/p>\n

Expected Outcomes:
\n– Novel interpretable deep learning models for the analysis of spatially resolved data.
\n– A novel AI-based classifier of immune profiles.<\/p>\n

Requirements<\/span><\/strong><\/p>\n

\n
\n

A degree (MSc, or equivalent) in Computational Biology, Bioinformatics, Systems Biology, or a STEM-related field, such as Mathematics, Physics, Computer science, etc. Additionally, a good understanding of Health or Life Sciences, for example, Biology, Microbiology, Molecular Biology, Immunology, Biomedical Sciences, or Biochemistry, will be considered an asset.<\/p>\n

Furthermore, the applicant should be able to perform team-oriented as well as independent work.<\/p>\n

\u2022\u00a0\u00a0 \u00a0Essential skills:<\/strong><\/p>\n

Proficiency in machine learning techniques.<\/p>\n

Strong programming skills, preferably in Python.<\/p>\n

Solid foundation in mathematical modelling, probability and statistics.<\/p>\n

Ability to work collaboratively in an interdisciplinary team.<\/p>\n

Good communication skills in English (both written and spoken).<\/p>\n

\u2022\u00a0\u00a0\u00a0\u00a0Good to have:<\/strong><\/p>\n

Experience in computational biology.<\/p>\n

Familiarity with multi-omics data analysis.<\/p>\n

Knowledge of interpretable deep learning methods.<\/p>\n

Good understanding of immunology and\/or microbiology.<\/p>\n<\/div>\n<\/div>\n

\n
Specific Requirements<\/strong><\/div>\n
\n