Postdoctoral researcher machine learning of gene isoform variants in immune c

Job description

Gene splicing can generate multiple transcripts (isoforms) from a single gene, potentially influencing disease mechanisms. However, for many genes, the full repertoire of isoforms is still unknown and therefore knowledge on the impact of isoforms for rare diseases in clinical settings is limited. With the development of long-read sequencing technologies, reliable identification and quantification of these transcripts is now possible. We are seeking a motivated postdoctoral researcher to investigate and predict the relationship between gene isoforms and (rare) disease.

You will study the impact of (rare) genetic variants on isoform expression using long-read single-cell expression data from immune cells (blood and gut). Your main tasks will include:

• Developing methodology to improve isoform quantification from short-read data, leveraging long-read data as a reference.
• Designing and implementing AI-driven models to predict the effects of genetic variation on isoform expression from genome sequences.
• Prioritizing isoforms for disease-relevant phenotypes using inferred functional data.
• Extending existing tools to move from gene to isoform function prediction.

The methods you develop will help increase the diagnostic yield for rare disease patients. Applications will include analysis of large-scale whole genome sequencing datasets from UMCG patients and international consortia (e.g., Solve

RD, Genomics-England, GREGoR). You will disseminate findings through high-impact publications and presentations at international conferences. This position is part of the single-cell eQTLGen consortium, led by the Functional Genomics group at UMCG’s Department of Genetics. You will have access to unique datasets and benefit from collaboration within an international network.

• A PhD (or are close to graduating) in machine learning, bioinformatics, statistical genetics, molecular biology, or a related field.
• Proficiency in English and good team and organizational skills.
• Strong programming and data analysis skills (e.g., Python, R, Java, Bash).
• Experience with AI or sequence-based models (preferred).
• Experience with long-read sequencing data (preferred).
• Affinity with statistics or willingness to learn.