My name is Soumya Banerjee (first name pronounced as show-mo) and I am a post-doctoral research fellow with experience working in USA and Germany.

I analyze complex problems and implement new statistical and machine learning techniques for deriving insights from large amounts of data. 

Read more about my projects and skills here.

My research interest is in computational immunology. I use techniques from computer science to solve problems in immunology and take inspiration from the immune system to solve problems in computer science.

a) Using techniques from computer science to solve problems in immunology.

I use machine learning techniques to solve problems in biology, especially immunology. The tools of my trade are ordinary differential equation (ODE) models and spatially explicit agent based models (ABMs) to understand kinetics of West Nile Virus (WNV). I use Hierarchical Bayesian non-linear mixed effects models to simulate immune response in different species.

b) Taking inspiration from the immune system to solve problems in computer science.

My work suggests how chemical signals and the physical architecture of the immune system may lead to nearly scale-invariant immune search and response. I look at how we can take inspiration from this and create human-engineered distributed systems with faster search and response characteristics.

BioSoumya Banerjee has a PhD in Computer Science from the University of New Mexico, USA. He worked in Los Alamos National Laboratories while he was in graduate school. Prior to graduate school, he was a software engineer working in the financial services sector for Fortune 500 clients.

His work is at the intersection of computer science and biological systems – he uses tools from computer science to study biological systems and takes inspiration from biological systems to design more efficient human-engineered systems.  He is skilled in machine learning techniques and mathematical modelling using spatially explicit agent-based models and computationally tractable differential equation models.

He works closely with people from other domains, especially experimentalists. His work has been recognized with a University of New Mexico Student Award for Innovation in Informatics in 2010.

He takes pride in writing industrial-strength software, which he attributes to years working in industry and skills honed in academia. As of January 2015, he was ranked within the top 200 worldwide on MATLAB Central (an online repository for Matlab code contributed by users all over the world).

All in small letters

View Soumya Banerjee's profile on LinkedIn

Soumya Banerjee's citations

Soumya Banerjee