Research

My research interests include causal inference, deep neural networks, and probabilistic graphical models. My ultimate goal is to solve unanswered questions from highly dynamic, interdependent, and complex data sets using causality, machine learning, and Bayesian inference. Currently, I am working on data sets generated from microbiome studies. A microbiome is a community of microbes including bacteria, archaea, protists, fungi, and viruses that share an environmental niche. Microbes are the key players for health and diseases in the human body. So it is very critical to discover their mysterious patterns, activities, and interactions. I am a computer scientist, and I want to investigate the microbial world in the human body in a data-driven way. However, techniques I am working on are generalized, can easily be adapted in other domains like recommender system and social network analysis.

Publications:

• Musfiqur Rahman Sazal, Camilo Valdes, Trevor Cickovski, Arpit Mehta, Giri Narasimhan. Signed Causal Bayesian Networks from Microbiome. LXAI at NeurIPS 2019 (accepted)
• Daniel Ruiz-Perez, Musfiqur Rahman Sazal, Giri Narasimhan. Role of gut microbiota and their temporal interactions in kidney transplant recipients. LXAI at NeurIPS 2019 (accepted)
• Sazal, Musfiqur Rahman, et al. "Inferring Relationships in Microbiomes from Signed Bayesian Networks." 2018 IEEE 8th International Conference on Computational Advances in Bio and Medical Sciences (ICCABS). IEEE, 2018.
• Sazal, Md Musfiqur Rahman, et al. "Bangla handwritten character recognition using deep belief network." 2013 International Conference on Electrical Information and Communication Technology (EICT). IEEE, 2014. (28 citations)
• Sazal, Md Musfiqur Rahman, et al. "Inferring directional relationships in microbial communities using signed Bayesian networks" BMC Bioinformatics. (invited and under review)

Ongoing Research:

• Causal effects from static and time varying data sets
• Using causality and deep learning together for better prediction