Global Gene Expression Analysis: Determine Hormone Signaling Activation in Human Breast Cancer Samples

70% of breast cancers can be classified as estrogen receptor positive (ER+). Recent evidences describe tumor as a very complex and heterogeneous disease, highlighting the importance of taking into consideration inter- and intra-tumor variability. Patient-derived xenografts (PDXs) emerged as promising and clinically-relevant preclinical model able to recapitulate the clinical settings. One promising way to estimate human cells receptivity to hormones is to analyse patient genes expression.

In this project, I explored a set of machine learning algorithms and features selection techniques to classify human cells implanted into mice according to their hormone receptivity by using only their gene expression.

According to the results of the study, we show that this method can be used to classify patient’s cells receptivity to hormones.

Find out more about that project on my Github:epfl-breast-cancer-ml-project.