Identifying tumor cells at the single cell level through machine learning

Tumours are highly complex tissues composed of cancerous cells, surrounded by a heterogeneous cellular microenvironment. A tumor’s response to treatments is governed by an interaction of the cancer cell’s intrinsic factors with external influences of the tumor microenvironment. Disentangling the heterogeneity within a tumor is a crucial step in the development and utilisation of effective cancer therapies. The single cell sequencing technology enables an effective molecular characterisation of single cells within the tumor. This technology can help deconvolute heterogeneous tumor samples and thus revolutionise personalised medicine. However, a governing challenge in cancer single cell analysis is cell annotation, that is, the assignment of a particular cell type or a cell state to each sequenced cell. The identification of tumor cells within single cell or spatial sequencing experiments remains a critical and limiting step for research, clinical, and commercial applications.

This webinar is part ofPerMedCoEwebinar series and is open for anyone interested in simulation of metabolic models,in applications of single cell and machine learning technologies, and in PerMedCoE tools and activities. The goal of PerMedCoE is to provide an efficient and sustainable entry point to the HPC/Exascale-upgraded methodology to translate omics analyses into actionable models of cellular functions of medical relevance. No prior knowledge is required.

• Exemplify the applications of single cell to identify tumour cells
• Describe a machine learning pipeline for distinguishing tumor cells from normal cells at the single cell level