Dmitry Devetyarov

Peptides Generated Ex Vivo from Serum Proteins by Tumor-Specific Exopeptidases Are Not Useful Biomarkers in Ovarian Cancer

BACKGROUND The serum peptidome may be a valuable source of diagnostic cancer biomarkers. Previous mass spectrometry (MS) studies have suggested that groups of related peptides discriminatory for different cancer types are generated ex vivo from abundant serum proteins by tumor-specific exopeptidases. We tested 2 complementary serum profiling strategies to see if similar peptides could be found that discriminate ovarian cancer from benign cases and healthy controls. METHODS We subjected identically collected and processed serum samples from healthy volunteers and patients to automated polypeptide extraction on octadecylsilane-coated magnetic beads and separately on ZipTips before MALDI-TOF MS profiling at 2 centers. The 2 platforms were compared and case control profiling data analyzed to find altered MS peak intensities. We tested models built from training datasets for both methods for their ability to classify a blinded test set. RESULTS Both profiling platforms had CVs of approximately 15% and could be applied for high-throughput analysis of clinical samples. The 2 methods generated overlapping peptide profiles, with some differences in peak intensity in different mass regions. In cross-validation, models from training data gave diagnostic accuracies up to 87% for discriminating malignant ovarian cancer from healthy controls and up to 81% for discriminating malignant from benign samples. Diagnostic accuracies up to 71% (malignant vs healthy) and up to 65% (malignant vs benign) were obtained when the models were validated on the blinded test set. CONCLUSIONS For ovarian cancer, altered MALDI-TOF MS peptide profiles alone cannot be used for accurate diagnoses.

Prediction with Confidence Based on a Random Forest Classifier

Conformal predictors represent a new flexible framework that outputs region predictions with a guaranteed error rate. Efficiency of such predictions depends on the nonconformity measure that underlies the predictor. In this work we designed new nonconformity measures based on a random forest classifier. Experiments demonstrate that proposed conformal predictors are more efficient than current benchmarks on noisy mass spectrometry data (and at least as efficient on other type of data) while maintaining the property of validity: they output fewer multiple predictions, and the ratio of mistakes does not exceed the preset level. When forced to produce singleton predictions, the designed conformal predictors are at least as accurate as the benchmarks and sometimes significantly outperform them.

Highly accurate detection of ovarian cancer using CA125 but limited improvement with serum matrix-assisted laser desorption/ionization time-of-flight mass spectrometry profiling.

Objectives: Our objective was to test the performance of CA125 in classifying serum samples from a cohort of malignant and benign ovarian cancers and age-matched healthy controls and to assess whether combining information from matrix-assisted laser desorption/ionization (MALDI) time-of-flight profiling could improve diagnostic performance. Materials and Methods: Serum samples from women with ovarian neoplasms and healthy volunteers were subjected to CA125 assay and MALDI time-of-flight mass spectrometry (MS) profiling. Models were built from training data sets using discriminatory MALDI MS peaks in combination with CA125 values and tested their ability to classify blinded test samples. These were compared with models using CA125 threshold levels from 193 patients with ovarian cancer, 290 with benign neoplasm, and 2236 postmenopausal healthy controls. Results: Using a CA125 cutoff of 30 U/mL, an overall sensitivity of 94.8% (96.6% specificity) was obtained when comparing malignancies versus healthy postmenopausal controls, whereas a cutoff of 65 U/mL provided a sensitivity of 83.9% (99.6% specificity). High classification accuracies were obtained for early-stage cancers (93.5% sensitivity). Reasons for high accuracies include recruitment bias, restriction to postmenopausal women, and inclusion of only primary invasive epithelial ovarian cancer cases. The combination of MS profiling information with CA125 did not significantly improve the specificity/accuracy compared with classifications on the basis of CA125 alone. Conclusions: We report unexpectedly good performance of serum CA125 using threshold classification in discriminating healthy controls and women with benign masses from those with invasive ovarian cancer. This highlights the dependence of diagnostic tests on the characteristics of the study population and the crucial need for authors to provide sufficient relevant details to allow comparison. Our study also shows that MS profiling information adds little to diagnostic accuracy. This finding is in contrast with other reports and shows the limitations of serum MS profiling for biomarker discovery and as a diagnostic tool.

Multiprobabilistic Venn Predictors with Logistic Regression

This paper describes the methodology of providing multiprobability predictions for proteomic mass spectrometry data. The methodology is based on a newly developed machine learning framework called Venn machines. They allow us to output a valid probability interval. We apply this methodology to mass spectrometry data sets in order to predict the diagnosis of heart disease and early diagnoses of ovarian cancer. The experiments show that probability intervals are valid and narrow. In addition, probability intervals were compared with the output of a corresponding probability predictor.

Conditional Prediction Intervals for Linear Regression

We construct prediction intervals for the linear regression model with IID errors with a known distribution, not necessarily Gaussian. The coverage probability of our prediction intervals is equal to the nominal confidence level not only unconditionally but also conditionally given a natural sigma-algebra of invariant events. This implies, in particular, the perfect calibration of our prediction intervals in the on-line mode of prediction.

Online Prediction of Ovarian Cancer

In this paper we apply computer learning methods to the diagnosis of ovarian cancer using the level of the standard biomarker CA125 in conjunction with information provided by mass spectrometry. Our algorithm gives probability predictions for the disease. To check the power of our algorithm we use it to test the hypothesis that CA125 and the peaks do not contain useful information for the prediction of the disease at a particular time before the diagnosis. It produces p -values that are less than those produced by an algorithm that has been previously applied to this data set. Our conclusion is that the proposed algorithm is especially reliable for prediction the ovarian cancer on some stages.