Nandini Raghavan

Sparse learning and stability selection for predicting MCI to AD conversion using baseline ADNI data

BackgroundPatients with Mild Cognitive Impairment (MCI) are at high risk of progression to Alzheimer’s dementia. Identifying MCI individuals with high likelihood of conversion to dementia and the associated biosignatures has recently received increasing attention in AD research. Different biosignatures for AD (neuroimaging, demographic, genetic and cognitive measures) may contain complementary information for diagnosis and prognosis of AD.MethodsWe have conducted a comprehensive study using a large number of samples from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) to test the power of integrating various baseline data for predicting the conversion from MCI to probable AD and identifying a small subset of biosignatures for the prediction and assess the relative importance of different modalities in predicting MCI to AD conversion. We have employed sparse logistic regression with stability selection for the integration and selection of potential predictors. Our study differs from many of the other ones in three important respects: (1) we use a large cohort of MCI samples that are unbiased with respect to age or education status between case and controls (2) we integrate and test various types of baseline data available in ADNI including MRI, demographic, genetic and cognitive measures and (3) we apply sparse logistic regression with stability selection to ADNI data for robust feature selection.ResultsWe have used 319 MCI subjects from ADNI that had MRI measurements at the baseline and passed quality control, including 177 MCI Non-converters and 142 MCI Converters. Conversion was considered over the course of a 4-year follow-up period. A combination of 15 features (predictors) including those from MRI scans, APOE genotyping, and cognitive measures achieves the best prediction with an AUC score of 0.8587.ConclusionsOur results demonstrate the power of integrating various baseline data for prediction of the conversion from MCI to probable AD. Our results also demonstrate the effectiveness of stability selection for feature selection in the context of sparse logistic regression.

Development and evaluation of a genomic signature for the prediction and mechanistic assessment of nongenotoxic hepatocarcinogens in the rat.

Evaluating the risk of chemical carcinogenesis has long been a challenge owing to the protracted nature of the pathology and the limited translatability of animal models. Although numerous short-term in vitro and in vivo assays have been developed, they have failed to reliably predict the carcinogenicity of nongenotoxic compounds. Extending upon previous microarray work (Fielden, M. R., Nie, A., McMillian, M., Elangbam, C. S., Trela, B. A., Yang, Y., Dunn, R. T., II, Dragan, Y., Fransson-Stehen, R., Bogdanffy, M., et al. (2008). Interlaboratory evaluation of genomic signatures for predicting carcinogenicity in the rat. Toxicol. Sci. 103, 28-34), we have developed and extensively evaluated a quantitative PCR-based signature to predict the potential for nongenotoxic compounds to induce liver tumors in the rat as a first step in the safety assessment of potential nongenotoxic carcinogens. The training set was derived from liver RNA from rats treated with 72 compounds and used to develop a 22-gene signature on the TaqMan array platform, providing an economical and standardized assay protocol. Independent testing on over 900 diverse samples (66 compounds) confirmed the interlaboratory precision of the assay and its ability to predict known nongenotoxic hepatocarcinogens (NGHCs). When tested under different experimental designs, strains, time points, dose setting criteria, and other preanalytical processes, the signature sensitivity and specificity was estimated to be 67% (95% confidence interval [CI] = 38-88%) and 59% (95% CI = 44-72%), respectively, with an area under the receiver operating characteristic curve of 0.65 (95% CI = 0.46-0.83%). Compounds were best classified using expression data from short-term repeat dose studies; however, the prognostic expression changes appeared to be preserved after longer term treatment. Exploratory evaluations also revealed that different modes of action for nongenotoxic and genotoxic compounds can be discriminated based on the expression of specific genes. These results support a potential early preclinical testing paradigm to catalyze broader understanding of putative NGHCs.

An Improved Model for Disease Progression in Patients From the Alzheimer's Disease Neuroimaging Initiative

The objective of this analysis was to develop a semi‐mechanistic nonlinear disease progression model using an expanded set of covariates that captures the longitudinal change of Alzheimers Disease Assessment Scale (ADAS‐cog) scores from the Alzheimers Disease Neuroimaging Initiative study that consisted of 191 Alzheimer disease patients who were followed for 2 years. The model describes the rate of progression and baseline disease severity as a function of influential covariates. The covariates that were tested fell into 4 categories: (1) imaging volumetric measures, (2) serum biomarkers, (3) demographic and genetic factors, and (4) baseline cognitive tests. Covariates found to affect baseline disease status were years since disease onset, hippocampal volume, and ventricular volume. Disease progression rate in the model was influenced by age, total cholesterol, APOE ε4 genotype, Trail Making Test (part B) score, and current levels of impairment as measured by ADAS‐cog. Rate of progression was slower for mild and severe Alzheimer patients compared with moderate Alzheimer patients who exhibited faster rates of deterioration. In conclusion, this model describes disease progression in Alzheimer patients using novel covariates that are important for understanding the worsening of ADAS‐cog scores over time and may be useful in the future for optimizing study designs through clinical trial simulations.

Genome-wide copy number alterations detection in fresh frozen and matched FFPE samples using SNP 6.0 arrays

SNP arrays offer the opportunity to get a genome‐wide view on copy number alterations and are increasingly used in oncology. DNA from formalin‐fixed paraffin‐embedded material (FFPE) is partially degraded which limits the application of those technologies for retrospective studies. We present the use of Affymetrix GeneChip SNP6.0 for identification of copy number alterations in fresh frozen (FF) and matched FFPE samples. Fifteen pairs of adenocarcinomas with both frozen and FFPE embedded material were analyzed. We present an optimization of the sample preparation and show the importance of correcting the measured intensities for fragment length and GC‐content when using FFPE samples. The absence of GC content correction results in a chromosome specific “wave pattern” which may lead to the misclassification of genomic regions as being altered. The highest concordance between FFPE and matched FF were found in samples with the highest call rates. Nineteen of the 23 high level amplifications (83%) seen using FF samples were also detected in the corresponding FFPE material. For limiting the rate of “false positive” alterations, we have chosen a conservative False Discovery Rate (FDR). We observed better results using SNP probes than CNV probes for copy number analysis of FFPE material. This is the first report on the detection of copy number alterations in FFPE samples using Affymetrix GeneChip SNP6.0.

Disease progression model in subjects with mild cognitive impairment from the Alzheimer's disease neuroimaging initiative: CSF biomarkers predict population subtypes

AIM The objective is to develop a semi-mechanistic disease progression model for mild cognitive impairment (MCI) subjects. The model aims to describe the longitudinal progression of ADAS-cog scores from the Alzheimers disease neuroimaging initiative trial that had data from 198 MCI subjects with cerebrospinal fluid (CSF) information who were followed for 3 years. METHOD Various covariates were tested on disease progression parameters and these variables fell into six categories: imaging volumetrics, biochemical, genetic, demographic, cognitive tests and CSF biomarkers. RESULTS CSF biomarkers were associated with both baseline disease score and disease progression rate in subjects with MCI. Baseline disease score was also correlated with atrophy measured using hippocampal volume. Progression rate was also predicted by executive functioning as measured by the Trail B-test. CONCLUSION CSF biomarkers have the ability to discriminate MCI subjects into sub-populations that exhibit markedly different rates of disease progression on the ADAS-cog scale. These biomarkers can therefore be utilized for designing clinical trials enriched with subjects that carry the underlying disease pathology.

Development and evaluation of a multiplexed mass spectrometry based assay for measuring candidate peptide biomarkers in Alzheimer's Disease Neuroimaging Initiative (ADNI) CSF

We describe the outcome of the Biomarkers Consortium CSF Proteomics Project (where CSF is cerebral spinal fluid), a public–private partnership of government, academia, nonprofit, and industry. The goal of this study was to evaluate a multiplexed MS‐based approach for the qualification of candidate Alzheimers disease (AD) biomarkers using CSF samples from the AD Neuroimaging Initiative.

Class prediction in toxicogenomics.

ABSTRACT The intent of this article is to discuss some of the complexities of toxicogenomics data and the statistical design and analysis issues that arise in the course of conducting a toxicogenomics study. We also describe a procedure for classifying compounds into various hepatotoxicity classes based on gene expression data. The methodology involves first classifying a compound as toxic or nontoxic and subsequently classifying the toxic compounds into the hepatotoxicity classes, based on votes by binary classifiers. The binary classifiers are constructed by using genes selected to best elicit differences between the two classes. We show that the gene selection strategy improves the misclassification error rates and also delivers gene pathways that exhibit biological relevance.

The high-level similarity of some disparate gene expression measures

Probe-level data from Affymetrix GeneChips can be summarized in many ways to produce probe-set level gene expression measures (GEMs). Disturbingly, the different approaches not only generate quite different measures but they could also yield very different analysis results. Here, we explore the question of how much the analysis results really do differ, first at the gene level, then at the biological process level. We demonstrate that, even though the gene level results may not necessarily match each other particularly well, as long as there is reasonably strong differentiation between the groups in the data, the various GEMs do in fact produce results that are similar to one another at the biological process level. Not only that the results are biologically relevant. As the extent of differentiation drops, the degree of concurrence weakens, although the biological relevance of findings at the biological process level may yet remain.

Optimal composite scores for longitudinal clinical trials under the linear mixed effects model

Clinical trials of chronic, progressive conditions use rate of change on continuous measures as the primary outcome measure, with slowing of progression on the measure as evidence of clinical efficacy. For clinical trials with a single prespecified primary endpoint, it is important to choose an endpoint with the best signal‐to‐noise properties to optimize statistical power to detect a treatment effect. Composite endpoints composed of a linear weighted average of candidate outcome measures have also been proposed. Composites constructed as simple sums or averages of component tests, as well as composites constructed using weights derived from more sophisticated approaches, can be suboptimal, in some cases performing worse than individual outcome measures. We extend recent research on the construction of efficient linearly weighted composites by establishing the often overlooked connection between trial design and composite performance under linear mixed effects model assumptions and derive a formula for calculating composites that are optimal for longitudinal clinical trials of known, arbitrary design. Using data from a completed trial, we provide example calculations showing that the optimally weighted linear combination of scales can improve the efficiency of trials by almost 20% compared with the most efficient of the individual component scales. Additional simulations and analytical results demonstrate the potential losses in efficiency that can result from alternative published approaches to composite construction and explore the impact of weight estimation on composite performance. Copyright

Novel Statistically-Derived Composite Measures for Assessing the Efficacy of Disease-Modifying Therapies in Prodromal Alzheimer’s Disease Trials: An AIBL Study

BACKGROUND There is a growing consensus that disease-modifying therapies must be given at the prodromal or preclinical stages of Alzheimers disease (AD) to be effective. A major unmet need is to develop and validate sensitive measures to track disease progression in these populations. OBJECTIVE To generate novel statistically-derived composites from standard scores, which have increased sensitivity in the assessment of change from baseline in prodromal AD. METHODS An empirically based method was employed to generate domain specific, global, and cognitive-functional novel composites. The novel composites were compared and contrasted with each other, as well as standard scores for their ability to track change from baseline. The longitudinal characteristics and power to detect decline of the measures were evaluated. Data from participants in the Australian Imaging, Biomarkers and Lifestyle (AIBL) Study characterized as mild cognitively impaired with high neocortical amyloid-β burden were utilized for the study. RESULTS The best performing standard scores were CDR Sum-of-Boxes and MMSE. The statistically-derived novel composites performed better than the standard scores from which they were derived. The domain-specific composites generally did not perform as well as the global composites or the cognitive-functional composites. CONCLUSION A systematic method was employed to generate novel statistically-derived composite measures from standard scores. Composites comprised of measures including function and multiple cognitive domains appeared to best capture change from baseline. These composites may be useful to assess progression or lack thereof in prodromal AD. However, the results should be replicated and validated using an independent clinical sample before implementation in a clinical trial.