Background
Transcriptomics provide insights into gene expression and with it the ability to analyse one of the fundamental processes of life - the translation from gene to protein. single Cell RNA sequencing (scRNAseq) is a technology that measures transcriptomics on the single cell level. However, biological data is highly complex, variability and noisy, making it challenging to analyse and wo.
By building on pre-trained general scRNAseq deep learning model we want to fine-tune and train the model task specific. Examples of existing models are Geneformer https://www.nature.com/articles/s41586-023-06139-9 or scGPT https://www.nature.com/articles/s41592-024-02201-0. If the student decides that existing models are not suitable there is also the option to build/train from scratch.
The goal is to fine-tune the model to differentiate between different sub-cell types, cell differentiation stages and cell cycle stages. However, for a lot of these categories, no labelled data exists so the student will need to identify different methods to create labels, such as pseudo time/ trajectory analysis (https://scanpy.readthedocs.io/en/stable/tutorials/index.html).
Potential downstream applications of the fine-tuned model are:
the identification of potential biomarkers, differentiating between the different classes/ cell stages. For example, by trying to explain the model.
Adjust the model to work with other transcriptomics technologies like microarray or qPCR with the goal of being able to differentiate between cell stages based on a limited number of genes only.
________________________________________________________________________________________________________
Requirements
To successfully complete the project, the student should have experience with designing and modifying deep learning models and knowledge about GPU training, preferably experience with the DTU HPC facility and Python. In addition, the student should have an interest in biology/ bioinformatics and be able to work independently.
Supervisors
Line K. H. Clemmensen [[lkhc@dtu.dk]{.underline}]
Manja Grønberg, [mgegr@dtu.dk]{.underline}
Alisa Pavel [alpav@dtu.dk]{.underline}(mailto:alpav@dtu.dk)
We plan on running joint supervision meetings with students involved in simultaneous ongoing projects
_______________________________________________________________________________________________________