Causal Inference using Genetic & Genomic Data to understand Neurological Disorders
Causality, as the name suggests, refers to the field of study concerned with the modeling of underlying cause-effect relationships in data that we wish to analyze. The motivation behind studying causality stems from the need to make sense of the data, to guide actions and policies and to learn from the resulting successes or failures in a way that traditional tried-and-tested statistical and machine learning methods fail to do. This type of an analysis especially holds relevance in a biological setting where understanding the dynamics of the causal factors for a particular trait (say, a disease) is of much more importance than merely studying the associations thereof. In my research, I am interested in exploring the applications of causal inference and discovery methods to complex polygenic disorders (including but not limited to neurological disorders like Alzheimer’s or Parkinson’s) for obtaining meaningful causal insights, furthering downstream analyses, identifying primary causal variants and understanding their molecular mechanisms. Currently, I am focusing on understanding the population specific genetics of complex diseases by developing improved polygenic risk score models using Bayesian probabilistic modelling approaches.
Conferences/Workshops
EMBO|EMBL: AI and Biology Symposium - March 12th-15th 2024 - Advanced Training Center, EMBL Heidelberg, Germany.
International Summer School on "Ancestry Meets Molecular Health", at the Heidelberg Center Latin America, Santiago de Chile, Nov. 20th-24th 2023.
Mathematical Modelling of Infectious Diseases: Models, Data and Basics of Calibration" at National Disease Modelling Consortium, IIT Bombay, June 2023.
Publications
Journal: Kamal, R., Bag, M. & Kule, M. On the cryptanalysis of S-DES using nature inspired optimization algorithms. Evolutionary Intelligence Vol. 14, issue 1, Special Issue on Nature Inspired Optimization and its Application to Engineering, Springer, Berlin Heidelberg, 163-173(2021). DOI:10.1007/s12065-020-00417-5
Conference Proceedings: Kamal R., Bag M., Kule M. (2020) On the Cryptanalysis of S-DES Using Binary Cuckoo Search Algorithm. In: Das A., Nayak J., Naik B., Pati S., Pelusi D. (eds) Computational Intelligence in Pattern Recognition. Advances in Intelligent Systems and Computing, vol 999. Springer, Singapore. (pp. 23-32). DOI:10.1007/978-981-13-9042-5_3
Analysis of Viral Diseases Using Metaheuristic Techniques and Machine Learning
Final Year B.Tech Project Thesis | IIEST, Shibpur | 2019-2020
Applications of Metaheuristic Optimization Techniques to Machine Learning and Deep Learning
Summer Research Internship | IIT BHU | 2019
Cryptanalysis of S-DES using Nature Inspired Optimization Algorithms
Research Internship | IIEST Shibpur | 2018
Studies in Basic Cryptology Techniques
B.Tech Mini Project | IIEST Shibpur | 2018