Saptarshi Bej

Currently, I am working on understanding the molecular master switches which lead to rewiring of gene regulatory networks in common inflammatory bowel diseases and neuropsychiatric diseases, such as schizophrenia. The concept of the Gut-Brain axis has been one of the most explored fields in Medical research since the inception of this Millennium. The project aims at initiating a new strategic alliance between two e:Med centres (Bonn, Kiel) and one de.NBI node (Rostock). We hypothesize that a systems-guided redefinition of gut-brain cross-disease manifestation helps to recognize and understand the immunological and neurological network perturbations of the GBA in order to identify concrete targets for therapeutic reprogramming of gene expression based on RNA-guided inactive Cas9 (CRISPR/Cas9) thus restoring normal gene expression programs in disease affected cells. Our systems medicine approach takes several layers of potential deregulation (DNA, mRNA, non-coding RNAs, TFs and proteins) into account and aims to create a multi-dimensional model. The novel findings are expected to extend the results of successful GWAS studies and to build the basis for functional gut–brain axis (GBA) experiments.

Another field of research that I am pursuing currently is Machine learning and Deep learning. Learning from Cytometry data and using such data for diagnosis is the main aim of this research. State of the art flow and mass Cytometry enables us to measure ~40 marker intencities in cell populations retrieved from patient blood samples. Transforming such data into a Machine learning friendly form is a challange due to the so called "curse of dimensionality". I am trying to address this challenge through my research.

Also, I am investigating methods to train Machine learning models with small amount of data. It is a practical challenge in biomedical research to have small amount of patient data. It is difficult to produce accurate predictive models in such cases. With less amount of data, it is also challenging to validate the models and estimate their accuracies properly. I am trying to address these points and find a way to deal with them.