About
Introduction
I'm working on the application of machine learning, algorithmic, and statistical approaches to genomics data in order to solve questions related to cancer
Questions
Question (1)
Dear all,
I'm a newbie to meta-analysis and forest plot. I've a dataframe of 10 studies. In addition to sample size, each study reports 4 clinical variables about Breast cancer: Age at diagnostic, proportion of patient under 50, proportion of stage 3 and 4 tumors, proportion of TNBC. I want to plot those proportions in one forest plot. Is that feasible ?
Projects
Project (1)
The project aims at designing of an optimized machine learning pipeline aiming at identifying short molecular biomarker signatures. The identified signatures can be used for tasks like Breast Cancer BC screening or predicting a reponse to Neoadjuvant Chemotherapy NAC treatment in BC. The core of the pipeline is a mixing between combinatorial optimization and Random Forest RF method.
