Learning Biomarker Models for Progression Estimation of Alzheimer’s Disease

Being able to estimate a patient’s progress in the course of Alzheimer’s disease and predicting future progression based on a number of observed biomarker values is of great interest for patients, clinicians and researchers alike. In this work, an approach for disease progress estimation is presented. Based on a set of subjects that convert to a more severe disease stage during the study, models that describe typical trajectories of biomarker values in the course of disease are learned using quantile regression. A novel probabilistic method is then derived to estimate the current disease progress as well as the rate of progression of an individual by fitting acquired biomarkers to the models. A particular strength of the method is its ability to naturally handle missing data. This means, it is applicable even if individual biomarker measurements are missing for a subject without requiring a retraining of the model. The functionality of the presented method is demonstrated using synthetic and—employing cognitive scores and image-based biomarkers—real data from the ADNI study. Further, three possible applications for progress estimation are demonstrated to underline the versatility of the approach: classification, construction of a spatio-temporal disease progression atlas and prediction of future disease progression.     

Identifying dynamical persistent biomarker structures for rare events using modern integrative machine learning approach

The evolution of omics and computational competency has accelerated discoveries of the underlying biological processes in an unprecedented way. High throughput methodologies, such as flow cytometry, can reveal deeper insights into cell processes, thereby allowing opportunities for scientific discoveries related to health and diseases. However, working with cytometry data often imposes complex computational challenges due to high-dimensionality, large size, and nonlinearity of the data structure. In addition, cytometry data frequently exhibit diverse patterns across biomarkers and suffer from substantial class imbalances which can further complicate the problem. The existing methods of cytometry data analysis either predict cell population or perform feature selection. Through this study, we propose a “wisdom of the crowd” approach to simultaneously predict rare cell populations and perform feature selection by integrating a pool of modern machine learning (ML) algorithms. Given that our approach integrates superior performing ML models across different normalization techniques based on entropy and rank, our method can detect diverse patterns existing across the model features. Furthermore, the method identifies a dynamic biomarker structure that divides the features into persistently selected, unselected, and fluctuating assemblies indicating the role of each biomarker in rare cell prediction, which can subsequently aid in studies of disease progression.     

Partial summary measures of the predictiveness curve

In the evaluation of a biomarker for risk prediction, one can assess the performance of the biomarker in the population of interest by displaying the predictiveness curve. In conjunction with an assessment of the classification accuracy of a biomarker, the predictiveness curve is an important tool for assessing the usefulness of a risk prediction model. Inference for a single biomarker or for multiple biomarkers can be performed using summary measures of the predictiveness curve. We propose two partial summary measures, the partial total gain and the partial proportion of explained variation, that summarize the predictiveness curve over a restricted range of risk. The methods we describe can be used to compare two biomarkers when there are existing thresholds for risk stratification. We describe inferential tools for one and two samples that are shown to have adequate power in a simulation study. The methods are illustrated by assessing the accuracy of a risk score for predicting the onset of Alzheimer's disease.     

Semiparametric Models of Time-Dependent Predictive Values of Prognostic Biomarkers

Summary .  Rigorous statistical evaluation of the predictive values of novel biomarkers is critical prior to applying novel biomarkers into routine standard care. It is important to identify factors that influence the performance of a biomarker in order to determine the optimal conditions for test performance. We propose a covariate-specific time-dependent positive predictive values curve to quantify the predictive accuracy of a prognostic marker measured on a continuous scale and with censored failure time outcome. The covariate effect is accommodated with a semiparametric regression model framework. In particular, we adopt a smoothed survival time regression technique ( Dabrowska, 1997 ,  The Annals of Statistics   25, 1510–1540) to account for the situation where risk for the disease occurrence and progression is likely to change over time. In addition, we provide asymptotic distribution theory and resampling-based procedures for making statistical inference on the covariate-specific positive predictive values. We illustrate our approach with numerical studies and a dataset from a prostate cancer study.     

Cellular and molecular mechanisms implicated in pathogenesis of selective neurodegeneration in Huntington’s disease

Huntington??s disease (HD) is one of the most common dominantly-inherited neurodegenerative disorders and is caused by a CAG repeat expansion in the huntingtin gene. HD is characterized by selective degeneration of subpopulations of neurons in the brain, however the precise underlying mechanisms how a ubiquitously expressed disease protein could target specific types of neurons for degeneration remains a critical, yet unanswered question for HD and other major neurodegenerative disorders. In this review, we describe the expanding view of selective neuronal vulnerability in HD, based on recent neuropathological and neuroimaging studies. We will also summarize the systematic effort to define the cell types in which mutant Huntingtin expression is critical for pathogenesis of vulnerable neurons in the striatum and cortex. Finally, we will describe selected, emerging molecular mechanisms that are implicated in selective disease processes in HD. Together, the field has begun to appreciate the distinct molecular pathogenic roles of mutant huntingtin in different cell types that may contribute to the selective neuronal vulnerability, with dissection of such mechanisms likely to yield novel molecular targets for HD therapy.     

Application of biomarkers in cancer risk management: evaluation from stochastic clonal evolutionary and dynamic system optimization points of view

Aside from primary prevention, early detection remains the most effective way to decrease mortality associated with the majority of solid cancers. Previous cancer screening models are largely based on classification of at-risk populations into three conceptually defined groups (normal, cancer without symptoms, and cancer with symptoms). Unfortunately, this approach has achieved limited successes in reducing cancer mortality. With advances in molecular biology and genomic technologies, many candidate somatic genetic and epigenetic "biomarkers" have been identified as potential predictors of cancer risk. However, none have yet been validated as robust predictors of progression to cancer or shown to reduce cancer mortality. In this Perspective, we first define the necessary and sufficient conditions for precise prediction of future cancer development and early cancer detection within a simple physical model framework. We then evaluate cancer risk prediction and early detection from a dynamic clonal evolution point of view, examining the implications of dynamic clonal evolution of biomarkers and the application of clonal evolution for cancer risk management in clinical practice. Finally, we propose a framework to guide future collaborative research between mathematical modelers and biomarker researchers to design studies to investigate and model dynamic clonal evolution. This approach will allow optimization of available resources for cancer control and intervention timing based on molecular biomarkers in predicting cancer among various risk subsets that dynamically evolve over time.     

Early energy deficit in Huntington disease: identification of a plasma biomarker traceable during disease progression

Huntington disease (HD) is a fatal neurodegenerative disorder, with no effective treatment. The pathogenic mechanisms underlying HD has not been elucidated, but weight loss, associated with chorea and cognitive decline, is a characteristic feature of the disease that is accessible to investigation. We, therefore, performed a multiparametric study exploring body weight and the mechanisms of its loss in 32 presymptomatic carriers and HD patients in the early stages of the disease, compared to 21 controls. We combined this study with a multivariate statistical analysis of plasma components quantified by proton nuclear magnetic resonance ((1)H NMR) spectroscopy. We report evidence of an early hypermetabolic state in HD. Weight loss was observed in the HD group even in presymptomatic carriers, although their caloric intake was higher than that of controls. Inflammatory processes and primary hormonal dysfunction were excluded. (1)H NMR spectroscopy on plasma did, however, distinguish HD patients at different stages of the disease and presymptomatic carriers from controls. This distinction was attributable to low levels of the branched chain amino acids (BCAA), valine, leucine and isoleucine. BCAA levels were correlated with weight loss and, importantly, with disease progression and abnormal triplet repeat expansion size in the HD1 gene. Levels of IGF1, which is regulated by BCAA, were also significantly lower in the HD group. Therefore, early weight loss in HD is associated with a systemic metabolic defect, and BCAA levels may be used as a biomarker, indicative of disease onset and early progression. The decreased plasma levels of BCAA may correspond to a critical need for Krebs cycle energy substrates in the brain that increased metabolism in the periphery is trying to provide.     

Mass spectrometry-based expression profiling of clinical prostate cancer

The maturation of MS technologies has provided a rich opportunity to interrogate protein expression patterns in normal and disease states by applying expression protein profiling methods. Major goals of this research strategy include the identification of protein biomarkers that demarcate normal and disease populations, and the identification of therapeutic biomarkers for the treatment of diseases such as cancer (Celis, J. E., and Gromov, P. (2003) Proteomics in translational cancer research: Toward an integrated approach. Cancer Cell 3, 9-151). Prostate cancer is one disease that would greatly benefit from implementing MS-based expression profiling methods because of the need to stratify the disease based on molecular markers. In this review, we will summarize the current MS-based methods to identify and validate biomarkers in human prostate cancer. Lastly, we propose a reverse proteomic approach implementing a quantitative MS research strategy to identify and quantify biomarkers implicated in prostate cancer development. With this approach, the absolute levels of prostate cancer biomarkers will be identified and quantified in normal and diseased samples by measuring the levels of native peptide biomarkers in relation to a chemically identical but isotopically labeled reference peptide. Ultimately, a centralized prostate cancer peptide biomarker expression database could function as a repository for the identification, quantification, and validation of protein biomarker(s) during prostate cancer progression in men.     

Candidate biomarkers in psychiatric disorders: state of the field

The field of psychiatry is hampered by a lack of robust, reliable and valid biomarkers that can aid in objectively diagnosing patients and providing individualized treatment recommendations. Here we review and critically evaluate the evidence for the most promising biomarkers in the psychiatric neuroscience literature for autism spectrum disorder, schizophrenia, anxiety disorders and post-traumatic stress disorder, major depression and bipolar disorder, and substance use disorders. Candidate biomarkers reviewed include various neuroimaging, genetic, molecular and peripheral assays, for the purposes of determining susceptibility or presence of illness, and predicting treatment response or safety. This review highlights a critical gap in the biomarker validation process. An enormous societal investment over the past 50 years has identified numerous candidate biomarkers. However, to date, the overwhelming majority of these measures have not been proven sufficiently reliable, valid and useful to be adopted clinically. It is time to consider whether strategic investments might break this impasse, focusing on a limited number of promising candidates to advance through a process of definitive testing for a specific indication. Some promising candidates for definitive testing include the N170 signal, an event-related brain potential measured using electroencephalography, for subgroup identification within autism spectrum disorder; striatal resting-state functional magnetic resonance imaging (fMRI) measures, such as the striatal connectivity index (SCI) and the functional striatal abnormalities (FSA) index, for prediction of treatment response in schizophrenia; error-related negativity (ERN), an electrophysiological index, for prediction of first onset of generalized anxiety disorder, and resting-state and structural brain connectomic measures for prediction of treatment response in social anxiety disorder. Alternate forms of classification may be useful for conceptualizing and testing potential biomarkers. Collaborative efforts allowing the inclusion of biosystems beyond genetics and neuroimaging are needed, and online remote acquisition of selected measures in a naturalistic setting using mobile health tools may significantly advance the field. Setting specific benchmarks for well-defined target application, along with development of appropriate funding and partnership mechanisms, would also be crucial. Finally, it should never be forgotten that, for a biomarker to be actionable, it will need to be clinically predictive at the individual level and viable in clinical settings.     

Identifying disease-associated biomarker network features through conditional graphical model

Biomarkers are often organized into networks, in which the strengths of network connections vary across subjects depending on subject-specific covariates (eg, genetic variants). Variation of network connections, as subject-specific feature variables, has been found to predict disease clinical outcome. In this work, we develop a two-stage method to estimate biomarker networks that account for heterogeneity among subjects and evaluate network's association with disease clinical outcome. In the first stage, we propose a conditional Gaussian graphical model with mean and precision matrix depending on covariates to obtain covariate-dependent networks with connection strengths varying across subjects while assuming homogeneous network structure. In the second stage, we evaluate clinical utility of network measures (connection strengths) estimated from the first stage. The second-stage analysis provides the relative predictive power of between-region network measures on clinical impairment in the context of regional biomarkers and existing disease risk factors. We assess the performance of proposed method by extensive simulation studies and application to a Huntington's disease (HD) study to investigate the effect of HD causal gene on the rate of change in motor symptom through affecting brain subcortical and cortical gray matter atrophy connections. We show that cortical network connections and subcortical volumes, but not subcortical connections are identified to be predictive of clinical motor function deterioration. We validate these findings in an independent HD study. Lastly, highly similar patterns seen in the gray matter connections and a previous white matter connectivity study suggest a shared biological mechanism for HD and support the hypothesis that white matter loss is a direct result of neuronal loss as opposed to the loss of myelin or dysmyelination.     

Heterogeneous multimodal biomarkers analysis for Alzheimer’s disease via Bayesian network

By 2050, it is estimated that the number of worldwide Alzheimer’s disease (AD) patients will quadruple from the current number of 36 million, while no proven disease-modifying treatments are available. At present, the underlying disease mechanisms remain under investigation, and recent studies suggest that the disease involves multiple etiological pathways. To better understand the disease and develop treatment strategies, a number of ongoing studies including the Alzheimer’s Disease Neuroimaging Initiative (ADNI) enroll many study participants and acquire a large number of biomarkers from various modalities including demographic, genotyping, fluid biomarkers, neuroimaging, neuropsychometric test, and clinical assessments. However, a systematic approach that can integrate all the collected data is lacking. The overarching goal of our study is to use machine learning techniques to understand the relationships among different biomarkers and to establish a system-level model that can better describe the interactions among biomarkers and provide superior diagnostic and prognostic information. In this pilot study, we use Bayesian network (BN) to analyze multimodal data from ADNI, including demographics, volumetric MRI, PET, genotypes, and neuropsychometric measurements and demonstrate our approach to have superior prediction accuracy.     

Exploring metabolic pathway disruption in the subchronic phencyclidine model of schizophrenia with the Generalized Singular Value Decomposition

Background

One of the major goals in gene and protein expression profiling of cancer is to identify biomarkers and build classification models for prediction of disease prognosis or treatment response. Many traditional statistical methods, based on microarray gene expression data alone and individual genes' discriminatory power, often fail to identify biologically meaningful biomarkers thus resulting in poor prediction performance across data sets. Nonetheless, the variables in multivariable classifiers should synergistically interact to produce more effective classifiers than individual biomarkers.

Results

We developed an integrated approach, namely network-constrained support vector machine (netSVM), for cancer biomarker identification with an improved prediction performance. The netSVM approach is specifically designed for network biomarker identification by integrating gene expression data and protein-protein interaction data. We first evaluated the effectiveness of netSVM using simulation studies, demonstrating its improved performance over state-of-the-art network-based methods and gene-based methods for network biomarker identification. We then applied the netSVM approach to two breast cancer data sets to identify prognostic signatures for prediction of breast cancer metastasis. The experimental results show that: (1) network biomarkers identified by netSVM are highly enriched in biological pathways associated with cancer progression; (2) prediction performance is much improved when tested across different data sets. Specifically, many genes related to apoptosis, cell cycle, and cell proliferation, which are hallmark signatures of breast cancer metastasis, were identified by the netSVM approach. More importantly, several novel hub genes, biologically important with many interactions in PPI network but often showing little change in expression as compared with their downstream genes, were also identified as network biomarkers; the genes were enriched in signaling pathways such as TGF-beta signaling pathway, MAPK signaling pathway, and JAK-STAT signaling pathway. These signaling pathways may provide new insight to the underlying mechanism of breast cancer metastasis.

Conclusions

We have developed a network-based approach for cancer biomarker identification, netSVM, resulting in an improved prediction performance with network biomarkers. We have applied the netSVM approach to breast cancer gene expression data to predict metastasis in patients. Network biomarkers identified by netSVM reveal potential signaling pathways associated with breast cancer metastasis, and help improve the prediction performance across independent data sets.     

Evaluating the Predictive Value of Biomarkers with Stratified Case‐Cohort Design

Summary Identification of novel biomarkers for risk assessment is important for both effective disease prevention and optimal treatment recommendation. Discovery relies on the precious yet limited resource of stored biological samples from large prospective cohort studies. Case‐cohort sampling design provides a cost‐effective tool in the context of biomarker evaluation, especially when the clinical condition of interest is rare. Existing statistical methods focus on making efficient inference on relative hazard parameters from the Cox regression model. Drawing on recent theoretical development on the weighted likelihood for semiparametric models under two‐phase studies ( Breslow and Wellner, 2007 ), we propose statistical methods to evaluate accuracy and predictiveness of a risk prediction biomarker, with censored time‐to‐event outcome under stratified case‐cohort sampling. We consider nonparametric methods and a semiparametric method. We derive large sample properties of proposed estimators and evaluate their finite sample performance using numerical studies. We illustrate new procedures using data from Framingham Offspring Study to evaluate the accuracy of a recently developed risk score incorporating biomarker information for predicting cardiovascular disease.     

Use of biomarkers in clinical trials of Alzheimer disease: from concept to application

Research progress during the last decades has resulted in an unprecedented accumulation of knowledge regarding the molecular pathogenesis of Alzheimer disease (AD). These important achievements toward clarifying the mechanistic processes underlying AD are being translated into ongoing development of biomarkers and their use in clinical trials. AD biomarkers are biochemical and anatomical variables (e.g. cerebrospinal fluid, positron emission tomography, and structural MRI) that measure AD-related pathologic features (i.e. amyloid deposition and neurodegeneration) in vivo. Biomarkers are utilized as 'diagnostic biomarkers' and/or 'endpoint biomarkers' in symptomatic or disease-modifying clinical trials. Diagnostic biomarkers play an important role in population enrichment by refining selection criteria, stratifying populations, and increasing the statistical power of trials. Endpoint biomarkers may be used as outcome measures to monitor the rate of disease progression and detect treatment effects. AD biomarkers do not reach abnormal levels or peak simultaneously, but do so in a time-dependent order. The choice of biomarkers for a clinical trial must take into consideration the type of therapeutic intervention, the clinical stage of AD, and the time dependence of biomarker changes during disease progression. The combination of amyloid and neurodegeneration biomarkers is highly desirable since they capture different aspects of the disease. Clinical trials for every clinical stage of AD would benefit from quantification and standardization of biomarkers. However, this is still a work in progress.     

An in vivo platform for tumor biomarker assessment

Tumor biomarkers provide a quantitative tool for following tumor progression and response to therapy. However, investigations of clinically useful tumor biomarkers are time-consuming, costly, and limited by patient and tumor heterogeneity. In addition, assessment of biomarkers as indicators of therapy response is confounded by the concomitant use of multiple therapeutic interventions. Herein we report our use of a clinically relevant orthotopic animal model of malignant pleural mesothelioma for investigating tumor biomarkers. Utilizing multi-modality imaging with correlative histopathology, we demonstrate the utility and accuracy of the mouse model in investigating tumor biomarkers--serum soluble mesothelin-related peptide (SMRP) and osteopontin (OPN). This model revealed percentage change in SMRP level to be an accurate biomarker of tumor progression and therapeutic response--a finding consistent with recent clinical studies. This in vivo platform demonstrates the advantages of a validated mouse model for the timely and cost-effective acceleration of human biomarker translational research.     

Progressive Cognitive Deficit,Motor Impairment and Striatal Pathology in a Transgenic Huntington Disease Monkey Model from Infancy to Adulthood

One of the roadblocks to developing effective therapeutics for Huntington disease (HD) is the lack of animal models that develop progressive clinical traits comparable to those seen in patients. Here we report a longitudinal study that encompasses cognitive and motor assessment, and neuroimaging of a group of transgenic HD and control monkeys from infancy to adulthood. Along with progressive cognitive and motor impairment, neuroimaging revealed a progressive reduction in striatal volume. Magnetic resonance spectroscopy at 48 months of age revealed a decrease of N-acetylaspartate (NAA), further suggesting neuronal damage/loss in the striatum. Postmortem neuropathological analyses revealed significant neuronal loss in the striatum. Our results indicate that HD monkeys share similar disease patterns with HD patients, making them potentially suitable as a preclinical HD animal model.