Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Mar:33:392-399.
doi: 10.1016/j.bspc.2016.12.003. Epub 2017 Jan 16.

Prostate cancer recognition based on mass spectrometry sensing data and data fingerprint recovery

Khalfalla Awedat  1 , Ikhlas Abdel-Qader  2 , James R Springstead  3
Affiliations

Prostate cancer recognition based on mass spectrometry sensing data and data fingerprint recovery

Khalfalla Awedat et al. Biomed Signal Process Control. 2017 Mar.

Abstract

The high dimensionality and noisy spectra of Mass Spectrometry (MS) data are two of the main challenges to achieving high accuracy recognition. The objective of this work is to produce an accurate prediction of class content by employing compressive sensing (CS). Not only can CS significantly reduce MS data dimensionality, but it will also allow for full reconstruction of original data. We are proposing a weighted mixing of L1- and L2-norms via a regularization term as a classifier within compressive sensing framework. Using performance measures such as OSR, PPV, NPV, Sen and Spec, we show that the L2-algorithm with regularization terms outperforms the L1-algorithm and Q5 under all applicable assumptions. We also aimed to use Block Sparse Bayesian Learning (BSBL) to reconstruct the MS data fingerprint which has also shown better performance results that those of L1-norm. These techniques were successfully applied to MS data to determine patient risk of prostate cancer by tracking Prostate-specific antigen (PSA) protein, and this analysis resulted in better performance when compared to currently used algorithms such as L1 minimization. This proposed work will be particularly useful in MS data reduction for assessing disease risk in patients and in future personalized medicine applications.

Keywords: BSBL; Compressive sensing; Confusion matrix; MS-classification; Mass spectrometry.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
An overview of the proposed framework for MS data classification.
Fig. 2
Fig. 2
The difference between two diseased samples and a diseased sample with a healthy sample in prostate cancer MS dataset.
Fig. 3
Fig. 3
Histogram showing residuals ri(y) of the test sample with respect to the projection of sparse representation computed δri by L2-norm.
Fig. 4
Fig. 4
The regulation parameters versus the performance parameters (a) accuracy, (b) Specificity, (c) PPV and (d) Sensitivity.
Fig. 5
Fig. 5
The average recovery error of L1-minimization and BSBL-BO under different measurement rates.
Fig. 6
Fig. 6
An example of recovering an MS data sample using two scenarios: (a) BSBL-BO technique and (b) L1-minminization.
See this image and copyright information in PMC

References

    1. Conrad Tim, et al. Sparse Proteomics Analysis-A compressed sensing-based approach for feature selection and classification of high-dimensional proteomics mass spectrometry data. 2015 arXiv preprint arXiv:1506.03620. - PMC - PubMed
    1. Hong Yan-jun, et al. Discrimination analysis of mass spectrometry proteomics for ovarian cancer detection. Acta Pharmacol Sin. 2008;29(10):1240–1246. - PubMed
    1. Du Pan, Kibbe Warren A, Lin Simon M. Improved peak detection in mass spectrum by incorporating continuous wavelet transform-based pattern matching. Bioinformatics. 2006;22(17):2059–2065. - PubMed
    1. Lilien Ryan H, Farid Hany, Donald Bruce R. Probabilistic disease classification of expression-dependent proteomic data from mass spectrometry of human serum. J Comput Biol. 2003;10(6):925–946. - PubMed
    1. Guyon Isabelle, et al. Gene selection for cancer classification using support vector machines. Mach Learn. 2016;46(1–3):389–422.

LinkOut - more resources