Key details:
Focus: Research internship on biological data curation and knowledge base enrichment.
Ideal candidate profile: Biology expert with strong analytical thinking and a passion for biomedical literature reading, interested in scientific knowledge formalisation and database maintenance.
Technical skills: No coding skills are required.
About the project:
The goal of the project is to create a repository of structured biological information that can be queried. We believe that this approach could alleviate the burden of keeping up with the ever-growing body of scientific literature and provide support in diverse tasks ranging from improved semantic search to the agentic formulation of new research hypotheses. The project utilises a biology-specific programming language used by biology experts to input information into the database.
To facilitate knowledge extraction from biomedical papers, we also work on Biological Natural Language Processing (BioNLP) tasks such as event extraction, named entity recognition, question answering and text summarization. We build and evaluate our own models as well as LLM-powered pipelines. On a smaller scale, we also create our own and modify the existing BioNLP-related datasets.
Your responsibilities will include:
processing and interpretation of large volumes of biomedical scientific literature on a regular basis
encodement of biological information into the database through a web-based editor using the biology-specific programming language
annotation of a large body of biomedical scientific texts using a web-based annotation tool
providing feedback on the accuracy and validity of model-generated output, as well as the content produced by peers
This internship project is planned as a paid six-month, part-time engagement with flexible working hours and a possibility for extension.
We are looking for Master’s and PhD students and graduates with a background in Cell biology, Molecular biology, Immunology, Medicine or related field to join our Biological Data Curation team.
The role is set within a dynamic project environment, where requirements and objectives may be adjusted over time. The position requires the ability to learn fast, as well as adaptability and openness to change. We expect full professional proficiency in English. While no coding skills are required, prior experience with programming languages, biological databases, biomedical text mining or ontologies is an advantage.