** NEW ** – (April 2025) –
Master’s thesis project or a lab immersion project
Using machine learning to develop a multimodal, deconvolutional package for bulk and single cell RNA sequencing
Over the past twenty years, transcriptomics has been used to investigate gene expression changes under a myriad of conditions, revealing salient insights into infectious diseases, cancer and more. Recent advances have even allowed for gene expression patterns to be captured at a single cellular level (scRNAseq), leading to insights into how cell type proportions and cell type specific gene expression impact global patterns. However, scRNAseq is expensive – an order of magnitude more expensive than tissue level transcriptomics (bulk RNAseq). Furthermore, the vast majority of publicly available databases are bulk RNAseq, meaning single cell insights cannot be derived from them.
As a result, a plethora of deconvolutional tools have been developed to estimate single-cell-level information from bulk RNAseq. These are based on converting a counts matrix of genes x samples into cell type proportions and/or a cell type expression matrix. These have had moderate accuracy, but still remain lacking for widespread applicability.
To address this, we are employing deep learning approaches to develop a deconvolutional tool that combines multiple transcriptomic modalities. We plan to first develop pipelines to extract orthogonal information from transcriptomic data beyond expression. Then, by using various ML techniques to integrate these layers together, we plan to develop a more comprehensive tool that can address the shortcomings of existing tools.
We are looking for a motivated student to participate in this novel project. We are looking for a student with programming skills in R, python, and previous experience with machine learning. Experience with transcriptomics analysis and deconvolution are valuable, yet not required.
The project will be supervised by Simon Tang and Jacques Fellay.
Expected duration: 3-6 months, exact timeline to be discussed
If you are interested, please contact Simon Tang ([email protected]).
********************************************************************
** NEW ** – (March 2025) –
Master’s semester project or a summer project
Combining machine learning techniques to efficiently determine the need for HCC screening among people with HIV
Hepatocellular carcinoma (HCC) is a common cause of morbidity and death in persons living with HIV. Because curative HCC treatment is possible upon early detection by liver ultrasound, international guidelines recommend twice-a-year liver ultrasound screening, which necessarily results in over-screening. To date, no prediction tool exists that can simultaneously prevent over-screening and accurately capture HCC cases. To solve this, we are combining machine learning techniques to develop an individualized risk assessment AI-based tool that can readily identify patients in need of routine ultrasound screening for HCC. The use of such tool could extend to other populations and diseases. The tool is being calibrated with clinical, laboratory, behavioural, genetic and sociodemographic data from the Swiss HIV Cohort Study (www.shcs.com).
We are looking for a motivated student to participate in this individualised medicine project. We are looking for a student with programing skills in Python and previous experience with machine learning. Experience with R, time series analyses and pattern recognition are valuable, yet not required.
The project will be supervised by Luisa Salazar-Vizcaya from Inselpital, Mariam Ait Oumelloul and Jacques Fellay.
Expected duration: 3-4 months
If you are interested, please contact Mariam Ait Oumelloul ([email protected]).
Master Thesis Projects
Master Thesis Projects are started once the 90 credits of master cycle are obtained.
Projects should last 17 weeks – they are worth 30 credits.
Master Thesis Projects must be done individually.
Semester Projects and Lab Immersions
LST and BIOING students may do one semester project and several lab immersion(s) during their Master studies.
Semester projects are worth 12 credits, lab immersion 8 credits.