Michael Khan

Papers

Total Citations

H-Index

About

Michael Khan is a computational biologist and bioimage informatics researcher whose work sits at the intersection of proteomics, machine learning, and cellular imaging. His research focuses on developing novel computational methods to analyze complex protein interaction data within individual cells, leveraging advanced bioimaging techniques to uncover the heterogeneity that exists even among neighboring cells within the same tissue. His most notable contribution, the DiSWOP measure (2013), introduced a groundbreaking approach to cell-level protein network analysis in localized proteomics image data, earning 13 citations and addressing a critical gap in understanding how proteins colocalize and interact at the single-cell level. Complementing this work, Khan has made significant strides in cell phenotyping, developing a locality preserving nonlinear embedding paradigm for mining cell phenotypes in multi-tag bioimages (2012) and further refining these methods in subsequent fluorescent bioimage analyses (2014), each garnering 8 citations. Together, these contributions form a cohesive body of work that equips researchers with more sophisticated tools for decoding cellular complexity, with direct implications for cancer research, tissue pathology, and precision medicine. His research represents an important bridge between biological imaging and computational data analysis.