Chapter 19Proteomic Disease Classification Algorithm
In this chapter, we study an algorithm [1] to automatically classify the status of a patient to be healthy or to have a particular disease, based on the mass spectrum (MS) data of his or her blood serum. We have been studying proteins in this book using atomic-resolution biophysical methods such as NMR and X-ray crystallography. MS, in contrast, allows us to assay and compare the masses of many proteins at the same time.
Proteomic Disease Classification
Mass spectrometry (MS) provides ultrahigh-resolution mass information. A mass spectrum consists of a set of (“mass-to-charge”) values and corresponding relative intensities that are a function of all ionized molecules present with that ratio; is mass and is charge; is plotted on the horizontal axis, and the corresponding relative intensity is plotted on the vertical axis of a typical mass spectrum. Mass spectrometry classification algorithms (MSCAs) are designed to discriminate one condition from another by comparing their mass spectra. For example, an MSCA can tell whether or not a patient has a particular disease from MS data of his peripheral blood.
Methods
Spectral space Each spectrum is represented as a point in an -dimensional space, where is the number of values for which relative intensities are recorded per spectrum.
Training set A set of data-class pairs , where is the data and is the class that belongs to. For example, is the mass spectrum of a patient, and indicating the health status of the patient. In this study, diseased can only mean one particular disease, for example, ovarian cancer. An extension was considered in Lilien et al. [1] to multiple classes (more than two).
Classifier A classifier is a mapping from data to classes. Usually, the classifier is first trained on a training set, then, for any data (points in the spectral space), it outputs a class for the data (for example, diseased or healthy).
Q5: An MSCA Algorithm
An MSCA called Q5 was introduced in Lilien et al. [1]. In the training step, it first reduces the dimension of the data in the training set by PCA. The dimension is reduced to the intrinsic dimensionality of the problem, which is the number of samples (in this case, patient blood samples) minus the number of classes. Then, a hyperplane is computed by linear discriminant analysis (LDA) so that the projections of data in the training set onto best discriminate the two classes, in terms of the ratio of the in-class variance to the between-class variance.
In the testing step, for a point in the spectral space, Q5 first reduces the dimension of by projecting it to the same subspace computed in the training step. Then, the reduced-dimension data is further projected to . Finally, a probabilistic classifier is applied to compute which class belongs to.
More precisely, Q5 works as follows:
Training Stage
Input Data spectrum represented as column vectors. (healthy) and (disease). Let , , .
PCA
- Compute all-class-mean .
- Let and be the zero-mean matrices obtained by subtracting from and , respectively. Let be the matrix.
- Let . Compute the eigenvalues and normalized eigenvectors of , denoted by and (), respectively. That is, for any , .
- Sort and discard the eigenvectors corresponding to small eigenvalues. Let the remaining eigenvectors be .
- Reduce the dimension of by . For any , let ; for any , let .
LDA
- Compute the within-class means. Let and .
- Compute the within-class scatter matrix by
where the columns of are ; the columns of are .
- Compute the between-class scatter matrix by
- Let be the normalized generalized eigenvector of and corresponding to the largest generalized eigenvalue . That is, .
Let (respectively ) be the mean of the (respectively ).
Output , , , and .
Testing or Prediction Stage
Input in the spectral space, and a threshold .
Let .
Probabilistic Classifier
- Let be the midpoint of and . Choose such that .
- Compute (). If for some , then output is in class . Otherwise output ambiguous.
Results and Discussion
Q5 was demonstrated on several MS data sets for patients with ovarian and prostate cancer. In all cases, excellent accuracy was obtained in disease classification. In Lilien et al. [1], an extension was described to identify biomarkers as well. In addition to impressive experimental accuracy, Q5 has guarantees, as an algorithm, of efficiency, soundness, and completeness. Such algorithms can probe the network of proteins that interact in cancer processes, and may help translate MCSA diagnosis toward the clinic.
This chapter shows how geometric techniques from statistical estimation and machine learning can be used to develop an algorithm for cancer proteomics, which uses data from a mass spectrometer to distinguish between healthy and diseased blood in humans. While geometry pervades the algorithms in this book, Lilien et al. [1] can be viewed as an investigation of geometry at a larger scale—instead of considering a single protein (or a small number of proteins) and their interactions, this chapter discussed algorithms for classifying and characterizing the geometry of the oncoproteome (i.e., the space of “all” expressed cancer proteins) as projected onto the mass-to-charge ratios of their proteolytic digest.
Reference
[1] R. Lilien, H. Farid and B. Donald. Journal of Computational Biology. 10;6(2003):925–946.