A Curvature Guided Composite Kernel Framework for Differential Gene Selection in Cancer Transcriptomics

Identification of differentially expressed genes is a crucial step for downstream tasks on gene data such asbiomarker discovery, drug target identification. Traditional Methods assume negative binomial distribution onRNA-sequence data and models the DEGs using either generalized linear models or by estimatingdispersion and assumption of mean-variance rate. The proposed method uses axiomatic approach by usingquantum mechanics principles to project transcript data onto a Hilbert space using a composite kernel. Usingthe curvature generated by the transcripts on the latent manifold within the Hilbert space, a gravitationalsearch inspired mechanism is used to identify the optimal number of differentially expressed genes byminimizing a representational loss function, and a reduced gene feature space is constructed as the potentialdifferentially expressed genes. The proposed method has been compared with existing empirical methodsfor validation using proper statistical and biological benchmark analysis.