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.

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.

Introduction Clinical decision making in the setting of computed tomography (CT) screening could benefit from accessible biomarkers that help predict the level of lung cancer risk in high-risk individuals with indeterminate pulmonary nodules. Methods To identify candidate serum biomarkers, we measured 70 cancer-related proteins by Luminex xMAP (Luminex Corporation) multiplexed immunoassays in a training set of sera from 56 patients with biopsy-proven primary non–small-cell lung cancer and 56 age-, sex-, and smoking-matched CT-screened controls. Results We identified a panel of 10 serum biomarkers—prolactin, transthyretin, thrombospondin-1, E-selectin, C-C motif chemokine 5, macrophage migration inhibitory factor, plasminogen activator inhibitor, receptor tyrosine-protein kinase, erbb-2, cytokeratin fragment 21.1, and serum amyloid A—that distinguished lung cancer patients from controls with an estimated balanced accuracy (average of sensitivity and specificity) of 76.0 ± 3.8% from 20-fold internal cross-validation. We then iteratively evaluated this model in an independent test and verification case/control studies confirming the initial classification performance of the panel. The classification performance of the 10-biomarker panel was also analytically validated using enzyme-linked immunosorbent assays in a second independent case/control population, further validating the robustness of the panel. Conclusions The performance of this 10-biomarker panel–based model was 77.1% sensitivity/76.2% specificity in cross-validation in the expanded training set, 73.3% sensitivity/93.3% specificity (balanced accuracy 83.3%) in the blinded verification set with the best discriminative performance in stage I/II cases: 85% sensitivity (balanced accuracy 89.2%). Importantly, the rate of misclassification of CT-screened controls was not different in most control subgroups with or without airflow obstruction or emphysema or pulmonary nodules. These biomarkers have potential to aid in the early detection of lung cancer and more accurate interpretation of indeterminate pulmonary nodules detected by CT screening.

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.