Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “regression analysis”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,513 records · Page 84

A new surrogate modeling technique combining Kriging and polynomial chaos expansions – Application to uncertainty analysis in computational dosimetry

In numerical dosimetry, the recent advances in high performance computing led to a strong reduction of the required computational time to assess the specific absorption rate (SAR) characterizing the human exposure to electromagnetic waves. However, this procedure remains time-consuming and a single simulation can request several hours. As a consequence, the influence of uncertain input parameters on the SAR cannot be analyzed using crude Monte Carlo simulation. The solution presented here to perform such an analysis is surrogate modeling. This paper proposes a novel approach to build such a surrogate model from a design of experiments. Considering a sparse representation of the polynomial chaos expansions using least-angle regression as a selection algorithm to retain the most influential polynomials, this paper proposes to use the selected polynomials as regression functions for the universal Kriging model. The leave-one-out cross validation is used to select the optimal number of polynomials in the deterministic part of the Kriging model. The proposed approach, called LARS-Kriging-PC modeling, is applied to three benchmark examples and then to a full-scale metamodeling problem involving the exposure of a numerical fetus model to a femtocell device. The performances of the LARS-Kriging-PC are compared to an ordinary Kriging model and to a classical sparse polynomial chaos expansion. The LARS-Kriging-PC appears to have better performances than the two other approaches. A significant accuracy improvement is observed compared to the ordinary Kriging or to the sparse polynomial chaos depending on the studied case. This approach seems to be an optimal solution between the two other classical approaches. A global sensitivity analysis is finally performed on the LARS-Kriging-PC model of the fetus exposure problem.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Sampling-based Sublinear Low-rank Matrix Arithmetic Framework for Dequantizing Quantum Machine Learning

We present an algorithmic framework for quantum-inspired classical algorithms on close-to-low-rank matrices, generalizing the series of results started by Tang’s breakthrough quantum-inspired algorithm for recommendation systems [STOC’19]. Motivated by quantum linear algebra algorithms and the quantum singular value transformation (SVT) framework of Gilyén et al. [STOC’19], we develop classical algorithms for SVT that run in time independent of input dimension, under suitable quantum-inspired sampling assumptions. Our results give compelling evidence that in the corresponding QRAM data structure input model, quantum SVT does not yield exponential quantum speedups. Since the quantum SVT framework generalizes essentially all known techniques for quantum linear algebra, our results, combined with sampling lemmas from previous work, suffice to generalize all prior results about dequantizing quantum machine learning algorithms. In particular, our classical SVT framework recovers and often improves the dequantization results on recommendation systems, principal component analysis, supervised clustering, support vector machines, low-rank regression, and semidefinite program solving. We also give additional dequantization results on low-rank Hamiltonian simulation and discriminant analysis. Our improvements come from identifying the key feature of the quantum-inspired input model that is at the core of all prior quantum-inspired results: ℓ 2 -norm sampling can approximate matrix products in time independent of their dimension. We reduce all our main results to this fact, making our exposition concise, self-contained, and intuitive.

Computer Science↗

The statistical analysis of circadian phase and amplitude in constant-routine core-temperature data

Accurate estimation of the phases and amplitude of the endogenous circadian pacemaker from constant-routine core-temperature series is crucial for making inferences about the properties of the human biological clock from data collected under this protocol. This paper presents a set of statistical methods based on a harmonic-regression-plus-correlated-noise model for estimating the phases and the amplitude of the endogenous circadian pacemaker from constant-routine core-temperature data. The methods include a Bayesian Monte Carlo procedure for computing the uncertainty in these circadian functions. We illustrate the techniques with a detailed study of a single subject's core-temperature series and describe their relationship to other statistical methods for circadian data analysis. In our laboratory, these methods have been successfully used to analyze more than 300 constant routines and provide a highly reliable means of extracting phase and amplitude information from core-temperature data.

NASA Discipline Regulatory Physiology↗

Identification and Quantification of Carbon Phases in Conversion Fuel for the Transient Reactor Test Facility

As part of an overall effort to convert US research reactors to low-enriched uranium (LEU) fuel, a LEU conversion fuel is being designed for the Transient Reactor Test Facility (TREAT) at the Idaho National Laboratory. TREAT fuel compacts are comprised of UO{sub 2} fuel particles in a graphitic matrix material. In order to refine heat transfer modeling, as well as determine other physical and nuclear characteristics of the fuel, the amount and type of graphite and non-graphite phases within the fuel matrix must be known. In this study, we performed a series of complementary analyses, designed to allow detailed characterization of the graphite and phenolic resin based fuel matrix. Methods included Scanning Electron Microscopy, Raman spectroscopy, and X-ray Diffraction. Our results indicate that no single characterization technique will yield all of the desired information; however, through the use of statistical and empirical data analysis, such as curve fitting, partial least squares regression, volume extrapolation and spectra peak ratios, a degree of certainty for the quantity of each phase can potentially be obtained. Although no one type of analysis has provided a complete determination of the quantities and identities of all carbon phases present in the fuel matrix, additional information has been gathered and is being used to refine future analysis methods. From the three types of quantification performed, results have been within 1% (92.8%, 93.02% and 93.6% for BSE image analysis, XRD and Raman spectroscopy, respectively). More work remains to identify any trace crystalline carbonaceous phases that may be present, quantify any traces that are identified, and develop and use further complementary bulk phase quantification techniques. (authors)

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Regression with Small Data Sets: A Case Study using Code Surrogates in Additive Manufacturing

There has been an increasing interest in recent years in the mining of massive data sets whose sizes are measured in terabytes. While it is easy to collect such large data sets in some application domains, there are others where collecting even a single data point can be very expensive, so the resulting data sets have only tens or hundreds of samples. For example, when complex computer simulations are used to understand a scientific phenomenon, we want to run the simulation for many different values of the input parameters and analyze the resulting output. The data set relating the simulation inputs and outputs is typically quite small, especially when each run of the simulation is expensive. However, regression techniques can still be used on such data sets to build an inexpensive \surrogate" that could provide an approximate output for a given set of inputs. A good surrogate can be very useful in sensitivity analysis, uncertainty analysis, and in designing experiments. In this paper, we compare different regression techniques to determine how well they predict melt-pool characteristics in the problem domain of additive manufacturing. Our analysis indicates that some of the commonly used regression methods do perform quite well even on small data sets.

97 MATHEMATICS AND COMPUTING↗

The Effect of Stabilization Heat Treatments on the Tensile and Creep Behavior of an Advanced Nickel-Based Disk Alloy

As part of NASA s Advanced Subsonic Technology Program, a study of stabilization heat treatment options for an advanced nickel-base disk alloy, ME 209, was performed. Using a simple, physically based approach, the effect of stabilization heat treatments on tensile and creep properties was analyzed in this paper. Solutions temperature, solution cooling rate, and stabilization temperature/time were found to have a significant impact on tensile and creep properties. These effects were readily quantified using the following methodology. First, the effect of solution cooling rate was assessed to determine its impact on a given property. The as-cooled property was then modified by using two multiplicative factors which assess the impact of solution temperature and stabilization parameters. Comparison of experimental data with predicted values showed this physically based analysis produced good results that rivaled the statistical analysis employed, which required numerous changes in the form of the regression equation depending on the property and temperature in question. As this physically based analysis uses the data for input, it should be noted that predictions which attempt to extrapolate beyond the bounds of the data must be viewed with skepticism. Future work aimed at expanding the range of the stabilization/aging parameters explored in this study would be highly desirable, especially at the higher solution cooling rates.

Gayda, John↗

SU-D-204-06: Integration of Machine Learning and Bioinformatics Methods to Analyze Genome-Wide Association Study Data for Rectal Bleeding and Erectile Dysfunction Following Radiotherapy in Prostate Cancer

Purpose: We investigated whether integration of machine learning and bioinformatics techniques on genome-wide association study (GWAS) data can improve the performance of predictive models in predicting the risk of developing radiation-induced late rectal bleeding and erectile dysfunction in prostate cancer patients. Methods: We analyzed a GWAS dataset generated from 385 prostate cancer patients treated with radiotherapy. Using genotype information from these patients, we designed a machine learning-based predictive model of late radiation-induced toxicities: rectal bleeding and erectile dysfunction. The model building process was performed using 2/3 of samples (training) and the predictive model was tested with 1/3 of samples (validation). To identify important single nucleotide polymorphisms (SNPs), we computed the SNP importance score, resulting from our random forest regression model. We performed gene ontology (GO) enrichment analysis for nearby genes of the important SNPs. Results: After univariate analysis on the training dataset, we filtered out many SNPs with p>0.001, resulting in 749 and 367 SNPs that were used in the model building process for rectal bleeding and erectile dysfunction, respectively. On the validation dataset, our random forest regression model achieved the area under the curve (AUC)=0.70 and 0.62 for rectal bleeding and erectile dysfunction, respectively. We performed GO enrichment analysis for the top 25%, 50%, 75%, and 100% SNPs out of the select SNPs in the univariate analysis. When we used the top 50% SNPs, more plausible biological processes were obtained for both toxicities. An additional test with the top 50% SNPs improved predictive power with AUC=0.71 and 0.65 for rectal bleeding and erectile dysfunction. A better performance was achieved with AUC=0.67 when age and androgen deprivation therapy were added to the model for erectile dysfunction. Conclusion: Our approach that combines machine learning and bioinformatics techniques enabled designing better models and identifying more plausible biological processes associated with the outcomes.

60 APPLIED LIFE SCIENCES↗

Analysis of slags using laser-induced breakdown spectroscopy

The feasibility of laser-induced breakdown spectroscopy (LIBS) for the analysis of gasification slags was investigated by comparing LIBS results to the results of an ICP-OES analyzer. A small amount of slag sample was placed on a piece of double sided adhesive tape attached to a glass microscope slide and analyzed for Al, Ca, Fe, Si, and V which are major elements found in slags. The partial least squares regression (PLS-R) and univariate simple linear regression (SLR) calibration methods indicated that apart from V (accuracy up to + 20%) the accuracy of analysis varies within 0.35–6.5% for SLR and 0.06–10% for PLS-R. A paired-sample t-test within the 95% confidence level yielded p-values greater than 0.05, meaning no appreciable statistical difference was observed between the univariate SLR with internal standardization and the multivariate PLS-R for most of the analytes. From the results obtained in this work, LIBS response varies depending on the element and the technique used for quantitative analysis. Simultaneous use of the univariate calibration curves with internal standard (intensity ratio) and PLS regression in multi-elemental analysis can help reduce the matrix effect of slags associated to their high variation in concentration. Overall, these results demonstrate the capability of LIBS as an alternative technique for analyzing gasification slags. Estimated limits of detection for Al, Ca, Fe, Si and V were 0.167, 0.78, 0.171, 0.243 and 0.01 wt.%, respectively.

36 MATERIALS SCIENCE↗

A Multi-institutional Study of Factors Influencing the Use of Stereotactic Radiosurgery for Brain Metastases

Purpose: Stereotactic radiosurgery (SRS) for brain metastases is a relatively well-studied technology with established guidelines regarding patient selection, although its implementation is technically complex. We evaluated the extent to which local availability of SRS affected the treatment of patients with brain metastases. Methods and Materials: We identified 3030 patients who received whole-brain radiation therapy (WBRT) for brain metastases in 1 of 7 cancer centers in Ontario. Clinical data were abstracted for a random sample of 973 patients. Logistic regression analyses were performed to identify factors associated with the use of SRS as a boost within 4 months following WBRT or at any time following WBRT. Results: Of 898 patients eligible for analysis, SRS was provided to 70 (7.8%) patients at some time during the course of their disease and to 34 (3.8%) patients as a boost following WBRT. In multivariable analyses, factors significantly associated with the use of SRS boost following WBRT were fewer brain metastases (odds ratio [OR] = 6.50), controlled extracranial disease (OR = 3.49), age (OR = 0.97 per year of advancing age), and the presence of an on-site SRS program at the hospital where WBRT was given (OR = 12.34; all P values were <.05). Similarly, availability of on-site SRS was the factor most predictive of the use of SRS at any time following WBRT (OR = 5.98). Among patients with 1-3 brain metastases, good/fair performance status, and no evidence of active extracranial disease, SRS was provided to 40.3% of patients who received WBRT in a hospital that had an on-site SRS program vs 3.0% of patients who received WBRT at a hospital without SRS (P<.01). Conclusions: The availability of on-site SRS is the factor most strongly associated with the provision of this treatment to patients with brain metastases and appears to be more influential than accepted clinical eligibility factors.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

A Comparative Analysis between GIMSS NDVIg and NDVI3g for Monitoring Vegetation Activity Change in the Northern Hemisphere during 1982-2008

The long-term Normalized Difference Vegetation Index (NDVI) time-series data set generated from the Advanced Very High Resolution Radiometers (AVHRR) has been widely used to monitor vegetation activity change. The third version of NDVI (NDVI3g) produced by the Global Inventory Modeling and Mapping Studies (GIMMS) group was released recently. The comparisons between the new and old versions should be conducted for linking existing studies with future applications of NDVI3g in monitoring vegetation activity change. Based on simple and piecewise linear regression methods, this research made a comparative analysis between NDVIg and NDVI3g for monitoring vegetation activity change and its responses to climate change in the middle and high latitudes of the Northern Hemisphere during 1982–2008. Our results indicated that there were large differences between NDVIg and NDVI3g in the spatial patterns for both the overall changing trends and the timing of Turning Points (TP) in NDVI time series, which spread over almost the entire study region. The average NDVI trend from NDVI3g was almost twice as great as that from NDVIg and the detected average timing of TP from NDVI3g was about one year later. Although the general spatial patterns were consistent between two data sets for detecting the responses of growing-season NDVI to temperature and precipitation changes, there were large differences in the response magnitude, with a higher response magnitude to temperature in NDVI3g and an opposite response to precipitation change for the two data sets. Finally, these results demonstrated that the NDVIg data set may underestimate the vegetation activity change trend and its response to climate change in the middle and high latitudes of the Northern Hemisphere during the past three decades.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Satellite/radiosonde comparison

Collocated measurements of radiosonde and TIROS Operational Vertical Sounder (TOVS) data are compared to determine whether significant latitudinal, seasonal, or instrumental biases exist. Long-wave structure determined by each system is being examined for correlation. Because U.S. radiosonde data are archived uncorrected, an effort to correct the measurements is being considered. These corrections will be applied to 7 years of measurements. New comparisons will then be made using corrected radiosonde and TOVS data. A regression method is used to retrieve temperatures, and radiosonde zonal means are used to update the regression coefficients. Preliminary results of auto-correlation analysis indicate that detection of long-wave structure in each set of data is slightly different with some levels and locations experiencing different wave periods or amplitudes. Scatter diagrams and linear regression for each layer show bias in the mean temperatures. Winter-time measurements show poorer correlations due to noisy measurements.

Schmidlin, F. J.↗

Aircrew coordination and decisionmaking: Peer ratings of video tapes made during a full mission simulation

Six professionally active, retired captains rated the coordination and decisionmaking performances of sixteen aircrews while viewing videotapes of a simulated commercial air transport operation. The scenario featured a required diversion and a probable minimum fuel situation. Seven point Likert-type scales were used in rating variables on the basis of a model of crew coordination and decisionmaking. The variables were based on concepts of, for example, decision difficulty, efficiency, and outcome quality; and leader-subordin ate concepts such as person and task-oriented leader behavior, and competency motivation of subordinate crewmembers. Five-front-end variables of the model were in turn dependent variables for a hierarchical regression procedure. The variance in safety performance was explained 46%, by decision efficiency, command reversal, and decision quality. The variance of decision quality, an alternative substantive dependent variable to safety performance, was explained 60% by decision efficiency and the captain's quality of within-crew communications. The variance of decision efficiency, crew coordination, and command reversal were in turn explained 78%, 80%, and 60% by small numbers of preceding independent variables. A principle component, varimax factor analysis supported the model structure suggested by regression analyses.

Murphy, M. R.↗

A temperature threshold to identify the driving climate forces of the respiratory process in terrestrial ecosystems

Terrestrial ecosystem respiration (R e ) is the second largest carbon flux between the biosphere and atmosphere. Therefore, climate-driven changes of Re greatly impact on future atmospheric CO 2 concentration. The aim of this study was to derive an air temperature threshold to identify the driving climate forces of the respiratory process in terrestrial ecosystems within different temperature zones. A global dataset of 647 site-years of ecosystem flux data and related variables were collected at 152 sites. The quantile regression was applied to evaluate relationships between the maximum realizable Re rates and mean annual air temperature (MAT) as well as other micrometeorological factors (i.e., atmospheric CO 2 concentration, atmospheric water content, soil heat flux, sensible heat flux, latent heat flux, precipitation, relative humidity, and soil water content). Our analysis revealed an ecosystem threshold of MAT of 11 ± 2.3 °C. In ecosystems with MATs lower than the threshold, the maximum R e rates were primarily dependent on temperature and respiration was mainly a temperature-driven process. In ecosystems with MATs higher than the threshold, besides MAT, other factors, such as water availability and surface heat flux, became significant driving forces of the maximum Re rates and respiration was a multi-factor-driven process. Temperature played the key role in generation of the maximum R e rates in the terrestrial ecosystems, while other driving forces reduce the maximum R e rates and the temperature sensitivity of the respiratory process. According to a regression tree analysis, MAT was also the most influencing factor of mean R e rates among the climate forces. The information from this study should be useful to predict the respiratory process in terrestrial ecosystems with different temperatures under the climate change.

54 ENVIRONMENTAL SCIENCES↗

Neural Density Estimation and Uncertainty Quantification for ChemCam Spectra [Slides]

The ChemCam instrument of Curiosity uses laser-induced breakdown spectroscopy (LIBS). It fires a laser at target and vaporizes rock surfaces, creating a plasma. Three spectrographs divide the plasma light into wavelengths for chemical analysis: ultraviolet, violet, and visible near-infrared. Regression methods (SVR, PCR, CNN) have been employed for calibration (prediction of the elemental composition of samples); however, labeled ChemCam samples are limited. Here, we focus on unsupervised learning and employ generative models from ChemCam analysis. Further, we use labels (supervised) in combination to the generative model to compute uncertainties related to predictions. We report generative modeling can be successfully applied to model real-world data. Normalizing flow models can be efficiently constructed on latent spaces for fast downstream inference. Unsupervised and supervised learning can be combined to form an uncertainty quantification framework.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Analyzing the Impact of Residential Building Attributes, Demographic and Behavioral Factors on Natural Gas Usage

This analysis examines the relationship between energy demand and residential building attributes, demographic characteristics, and behavioral variables using the U.S. Department of Energy’s Residential Energy Consumption Survey 2005 microdata. This study investigates the applicability of the smooth backfitting estimator to statistical analysis of residential energy consumption via nonparametric regression. The methodology utilized in the study extends nonparametric additive regression via local linear smooth backfitting to categorical variables. The conventional methods used for analyzing residential energy consumption are econometric modeling and engineering simulations. This study suggests an econometric approach that can be utilized in combination with simulation results. A common weakness of previously used econometric models is a very high likelihood that any suggested parametric relationships will be misspecified. Nonparametric modeling does not have this drawback. Its flexibility allows for uncovering more complex relationships between energy use and the explanatory variables than can possibly be achieved by parametric models. Traditionally, building simulation models overestimated the effects of energy efficiency measures when compared to actual "as-built" observed savings. While focusing on technical efficiency, they do not account for behavioral or market effects. The magnitude of behavioral or market effects may have a substantial influence on the final energy savings resulting from implementation of various energy conservation measures and programs. Moreover, variability in behavioral aspects and user characteristics appears to have a significant impact on total energy consumption. Inaccurate estimates of energy consumption and potential savings also impact investment decisions. The existing modeling literature, whether it relies on parametric specifications or engineering simulation, does not accommodate inclusion of a behavioral component. This study attempts to bridge that gap by analyzing behavioral data and investigate the applicability of additive nonparametric regression to this task. This study evaluates the impact of 31 regressors on residential natural gas usage. The regressors include weather, economic variables, demographic and behavioral characteristics, and building attributes related to energy use. In general, most of the regression results were in line with previous engineering and economic studies in this area. There were, however, some counterintuitive results, particularly with regard to thermostat controls and behaviors. There are a number of possible reasons for these counterintuitive results including the inability to control for regional climate variability due to the data sanitization (to prevent identification of respondents), inaccurate data caused by to self-reporting, and the fact that not all relevant behavioral variables were included in the data set, so we were not able to control for them in the study. The results of this analysis could be used as an in-sample prediction for approximating energy demand of a residential building whose characteristics are described by the regressors in this analysis, but a certain combination of their particular values does not exist in the real world. In addition, this study has potential applications for benefit-cost analysis of residential upgrades and retrofits under a fixed budget, because the results of this study contain information on how natural gas consumption might change once a particular characteristic or attribute is altered. Finally, the results of this study can help establish a relationship between natural gas consumption and changes in behavior of occupants.

03 NATURAL GAS↗

Determining the response of sea level to atmospheric pressure forcing using TOPEX/POSEIDON data

The static response of sea level to the forcing of atmospheric pressure, the so-called inverted barometer (IB) effect, is investigated using TOPEX/POSEIDON data. This response, characterized by the rise and fall of sea level to compensate for the change of atmospheric pressure at a rate of -1 cm/mbar, is not associated with any ocean currents and hence is normally treated as an error to be removed from sea level observation. Linear regression and spectral transfer function analyses are applied to sea level and pressure to examine the validity of the IB effect. In regions outside the tropics, the regression coefficient is found to be consistently close to the theoretical value except for the regions of western boundary currents, where the mesoscale variability interferes with the IB effect. The spectral transfer function shows near IB response at periods of 30 degrees is -0.84 +/- 0.29 cm/mbar (1 standard deviation). The deviation from = 1 cm /mbar is shown to be caused primarily by the effect of wind forcing on sea level, based on multivariate linear regression model involving both pressure and wind forcing. The regression coefficient for pressure resulting from the multivariate analysis is -0.96 +/- 0.32 cm/mbar. In the tropics the multivariate analysis fails because sea level in the tropics is primarily responding to remote wind forcing. However, after removing from the data the wind-forced sea level estimated by a dynamic model of the tropical Pacific, the pressure regression coefficient improves from -1.22 +/- 0.69 cm/mbar to -0.99 +/- 0.46 cm/mbar, clearly revealing an IB response. The result of the study suggests that with a proper removal of the effect of wind forcing the IB effect is valid in most of the open ocean at periods longer than 20 days and spatial scales larger than 500 km.

Fu, Lee-Lueng↗

Prediction of epigenetically regulated genes in breast cancer cell lines

Methylation of CpG islands within the DNA promoter regions is one mechanism that leads to aberrant gene expression in cancer. In particular, the abnormal methylation of CpG islands may silence associated genes. Therefore, using high-throughput microarrays to measure CpG island methylation will lead to better understanding of tumor pathobiology and progression, while revealing potentially new biomarkers. We have examined a recently developed high-throughput technology for measuring genome-wide methylation patterns called mTACL. Here, we propose a computational pipeline for integrating gene expression and CpG island methylation profles to identify epigenetically regulated genes for a panel of 45 breast cancer cell lines, which is widely used in the Integrative Cancer Biology Program (ICBP). The pipeline (i) reduces the dimensionality of the methylation data, (ii) associates the reduced methylation data with gene expression data, and (iii) ranks methylation-expression associations according to their epigenetic regulation. Dimensionality reduction is performed in two steps: (i) methylation sites are grouped across the genome to identify regions of interest, and (ii) methylation profles are clustered within each region. Associations between the clustered methylation and the gene expression data sets generate candidate matches within a fxed neighborhood around each gene. Finally, the methylation-expression associations are ranked through a logistic regression, and their significance is quantified through permutation analysis. Our two-step dimensionality reduction compressed 90% of the original data, reducing 137,688 methylation sites to 14,505 clusters. Methylation-expression associations produced 18,312 correspondences, which were used to further analyze epigenetic regulation. Logistic regression was used to identify 58 genes from these correspondences that showed a statistically signifcant negative correlation between methylation profles and gene expression in the panel of breast cancer cell lines. Subnetwork enrichment of these genes has identifed 35 common regulators with 6 or more predicted markers. In addition to identifying epigenetically regulated genes, we show evidence of differentially expressed methylation patterns between the basal and luminal subtypes. Our results indicate that the proposed computational protocol is a viable platform for identifying epigenetically regulated genes. Our protocol has generated a list of predictors including COL1A2, TOP2A, TFF1, and VAV3, genes whose key roles in epigenetic regulation is documented in the literature. Subnetwork enrichment of these predicted markers further suggests that epigenetic regulation of individual genes occurs in a coordinated fashion and through common regulators.

59 BASIC BIOLOGICAL SCIENCES↗