Canonical polyadic decomposition for unsupervised linear feature extraction from protein profiles

We propose a method for unsupervised linear feature extraction through tensor decomposition. The linear feature extraction can be formulated as a canonical polyadic decomposition (CPD) of a third-order tensor when transformation matrix is constrained to be equal to the Khatri-Rao product of two matrices. Therefore, standard algorithms for computing CPD decomposition can be used for feature extraction. The proposed method is validated on publicly available low-resolution mass spectra of cancerous and non-cancerous samples. Obtained results indicate that this approach could be of practical importance in analysis of protein expression profiles.