Amyotrophic lateral sclerosis (ALS) is characterized by degeneration of motor neurons. We tested the hypothesis that proteomic analysis will identify protein biomarkers that provide insight into disease pathogenesis and are diagnostically useful. To identify ALS specific biomarkers, we compared the proteomic profile of cerebrospinal fluid (CSF) from ALS and control subjects using surface-enhanced laser desorption/ ionization-time of flight mass spectrometry (SELDI-TOF-MS). We identified 30 mass ion peaks with statistically significant (p < 0.01) differences between control and ALS subjects. Initial analysis with a rule-learning algorithm yielded biomarker panels with diagnostic predictive value as subsequently assessed using an independent set of coded test subjects. Three biomarkers were identified that are either decreased (transthyretin, cystatin C) or increased (carboxy-terminal fragment of neuroendocrine protein 7B2) in ALS CSF. We validated the SELDI-TOF-MS results for transthyretin and cystatin C by immunoblot and immunohistochemistry using commercially available antibodies. These findings identify a panel of CSF protein biomarkers for ALS.

Introduction Recent studies using mass spectrometry have discovered candidate biomarkers for amyotrophic lateral sclerosis (ALS). However these studies utilize small numbers of ALS and control subjects. Additional studies using larger subject cohorts are required to verify these candidate biomarkers. Methods Cerebrospinal fluid (CSF) from 100 patients with ALS, 100 disease control and 41 healthy control subjects were examined by mass spectrometry. Results 61 mass spectral peaks exhibited altered levels between ALS and controls. Mass peaks for cystatin C and transthyretin were reduced in ALS, whereas mass peaks for post-translational modified transthyretin and C-reactive protein (CRP) were increased. CRP levels were 5.84±1.01 ng/mL for controls and 11.24±1.52 ng/mL for ALS subjects as determined by ELISA. Discussion This study verified prior mass spectrometry results for cystatin C and transthyretin in ALS. CRP levels were increased in the CSF of ALS patients, and cystatin C level correlated with survival in patients with limb-onset disease. Our biomarker panel predicted ALS with an overall accuracy of 82%.

Aberrant interactions between the host and the intestinal bacteria are thought to contribute to the pathogenesis of many digestive diseases. However, studying the complex ecosystem at the human mucosal-luminal interface (MLI) is challenging and requires an integrative systems biology approach. Therefore, we developed a novel method integrating lavage sampling of the human mucosal surface, high-throughput proteomics, and a unique suite of bioinformatic and statistical analyses. Shotgun proteomic analysis of secreted proteins recovered from the MLI confirmed the presence of both human and bacterial components. To profile the MLI metaproteome, we collected 205 mucosal lavage samples from 38 healthy subjects, and subjected them to high-throughput proteomics. The spectral data were subjected to a rigorous data processing pipeline to optimize suitability for quantitation and analysis, and then were evaluated using a set of biostatistical tools. Compared to the mucosal transcriptome, the MLI metaproteome was enriched for extracellular proteins involved in response to stimulus and immune system processes. Analysis of the metaproteome revealed significant individual-related as well as anatomic region-related (biogeographic) features. Quantitative shotgun proteomics established the identity and confirmed the biogeographic association of 49 proteins (including 3 functional protein networks) demarcating the proximal and distal colon. This robust and integrated proteomic approach is thus effective for identifying functional features of the human mucosal ecosystem, and a fresh understanding of the basic biology and disease processes at the MLI.

No abstract

Deep neural networks are increasingly being used in both supervised learning for classification tasks and unsupervised learning to derive complex patterns from the input data. However, the successful implementation of deep neural networks using neuroimaging datasets requires adequate sample size for training and well-defined signal intensity based structural differentiation. There is a lack of effective automated diagnostic tools for the reliable detection of brain dysmaturation in the neonatal period, related to small sample size and complex undifferentiated brain structures, despite both translational research and clinical importance. Volumetric information alone is insufficient for diagnosis. In this study, we developed a computational framework for the automated classification of brain dysmaturation from neonatal MRI, by combining a specific deep neural network implementation with neonatal structural brain segmentation as a method for both clinical pattern recognition and data-driven inference into the underlying structural morphology. We implemented three-dimensional convolution neural networks (3D-CNNs) to specifically classify dysplastic cerebelli, a subset of surface-based subcortical brain dysmaturation, in term infants born with congenital heart disease. We obtained a 0.985 ± 0. 0241-classification accuracy of subtle cerebellar dysplasia in CHD using 10-fold cross-validation. Furthermore, the hidden layer activations and class activation maps depicted regional vulnerability of the superior surface of the cerebellum, (composed of mostly the posterior lobe and the midline vermis), in regards to differentiating the dysplastic process from normal tissue. The posterior lobe and the midline vermis provide regional differentiation that is relevant to not only to the clinical diagnosis of cerebellar dysplasia, but also genetic mechanisms and neurodevelopmental outcome correlates. These findings not only contribute to the detection and classification of a subset of neonatal brain dysmaturation, but also provide insight to the pathogenesis of cerebellar dysplasia in CHD. In addition, this is one of the first examples of the application of deep learning to a neuroimaging dataset, in which the hidden layer activation revealed diagnostically and biologically relevant features about the clinical pathogenesis. The code developed for this project is open source, published under the BSD License, and designed to be generalizable to applications both within and beyond neonatal brain imaging.

Motivation: Disease state prediction from biomarker profiling studies is an important problem because more accurate classification models will potentially lead to the discovery of better, more discriminative markers. Data mining methods are routinely applied to such analyses of biomedical datasets generated from highthroughput 'omic' technologies applied to clinical samples from tissues or bodily fluids. Past work has demonstrated that rule models can be successfully applied to this problem, since they can produce understandable models that facilitate review of discriminative biomarkers by biomedical scientists. While many rule-based methods produce rules that make predictions under uncertainty, they typically do not quantify the uncertainty in the validity of the rule itself. This article describes an approach that uses a Bayesian score to evaluate rule models. Results: We have combined the expressiveness of rules with the mathematical rigor of Bayesian networks (BNs) to develop and evaluate a Bayesian rule learning (BRL) system. This system utilizes a novel variant of the K2 algorithm for building BNs from the training data to provide probabilistic scores for IF-antecedent-THENconsequent rules using heuristic best-first search. We then apply rule-based inference to evaluate the learned models during 10-fold cross-validation performed two times. The BRL system is evaluated on 24 published 'omic' datasets, and on average it performs on par or better than other readily available rule learning methods. Moreover, BRL produces models that contain on average 70% fewer variables, which means that the biomarker panels for disease prediction contain fewer markers for further verification and validation by bench scientists.

Many clinical research datasets have a large percentage of missing values that directly impacts their usefulness in yielding high accuracy classifiers when used for training in supervised machine learning. While missing value imputation methods have been shown to work well with smaller percentages of missing values, their ability to impute sparse clinical research data can be problem specific. We previously attempted to learn quantitative guidelines for ordering cardiac magnetic resonance imaging during the evaluation for pediatric cardiomyopathy, but missing data significantly reduced our usable sample size. In this work, we sought to determine if increasing the usable sample size through imputation would allow us to learn better guidelines. We first review several machine learning methods for estimating missing data. Then, we apply four popular methods (mean imputation, decision tree, k-nearest neighbors, and self-organizing maps) to a clinical research dataset of pediatric patients undergoing evaluation for cardiomyopathy. Using Bayesian Rule Learning (BRL) to learn ruleset models, we compared the performance of imputation-augmented models versus unaugmented models. We found that all four imputation-augmented models performed similarly to unaugmented models. While imputation did not improve performance, it did provide evidence for the robustness of our learned models.

BackgroundSeveral data mining methods require data that are discrete, and other methods often perform better with discrete data. We introduce an efficient Bayesian discretization (EBD) method for optimal discretization of variables that runs efficiently on high-dimensional biomedical datasets. The EBD method consists of two components, namely, a Bayesian score to evaluate discretizations and a dynamic programming search procedure to efficiently search the space of possible discretizations. We compared the performance of EBD to Fayyad and Irani's (FI) discretization method, which is commonly used for discretization.ResultsOn 24 biomedical datasets obtained from high-throughput transcriptomic and proteomic studies, the classification performances of the C4.5 classifier and the naïve Bayes classifier were statistically significantly better when the predictor variables were discretized using EBD over FI. EBD was statistically significantly more stable to the variability of the datasets than FI. However, EBD was less robust, though not statistically significantly so, than FI and produced slightly more complex discretizations than FI.ConclusionsOn a range of biomedical datasets, a Bayesian discretization method (EBD) yielded better classification performance and stability but was less robust than the widely used FI discretization method. The EBD discretization method is easy to implement, permits the incorporation of prior knowledge and belief, and is sufficiently fast for application to high-dimensional data.