Compressive sensing based for mass spectrometry reconstruction

In this paper, we propose an efficient technique for dimensionality reduction of Mass Spectrometry (MS) data by employing Compressive Sensing (CS). Not only can CS significantly reduce MS data dimensionality, but it also will allow for full reconstruction of original data. The framework developed in this work is based on forming Sparse Difference (SD) to sparsify MS signals and implementing the Block Sparse Bayesian Learning (BSBL) to reconstruct MS data from its low dimension feature space. Our results show that the proposed approach outperforms the L1-minimization algorithm.