Soutick Saha, PhD

Scientific Software Developer

Bioinformatics | Computational Biology | Data Science | Machine Learning

I am a Scientific Software Developer, and in my current role, I design and build bioinformatics and computational biology tools and functions. I have worked for Wolfram, the company known for its scientific software Mathematica, for over 3 years. My work combines software development, analyzing and benchmarking AI models, data integration using APIs, and large-scale biological analysis to support both researchers and educators. I have developed the Protein Visualization software package, a comprehensive tool that utilizes the power of visualization to study the fascinating world of biomolecules.

Prior to that, I completed my Ph.D. in physics from Purdue University, working in Dr. Andrew Mugler's lab. My research focus was on mathematical and computational modeling of migration in cells, more specifically, metastatic cancer and bacterial cells. My Ph.D. research was highly interdisciplinary and collaborative, and has resulted in several peer-reviewed publications and has received widespread media coverage.

During graduate school, I had the opportunity to work on data science and machine learning projects for Merck & Co. through the Purdue Data Mine program. This experience gave me a strong foundation in data science, artificial intelligence, machine learning, computer vision, and natural language processing while working on collaborative projects to automate different stages of the pharmaceutical formulation process.

Outside of work, I enjoy cooking, traveling, science communication, and merging my passion for art with biology (see my BioArt below)!

Connect with me on LinkedIn, where I regularly post about my work!

Bioinformatics Projects

My three most significant Bioinformatics projects are linked below. Visit the Bioinformatics tab for more information on my other projects.

Protein Visualization Software Package

(Software Development)

The Human Protein Atlas

(Omics Data Analysis)

The Human Protein-Protein Interaction Network

(Mentorship)

Data Science and Machine Learning Projects

My most significant data science and ML projects are from Purdue Data Mine in collaboration with Merck & Co. focused on automating the pharmaceutical formulation process. Visit the Data Science tab for other relevant projects.