Identification of potential CSF biomarkers in ALS.

BACKGROUND: The clinical diagnosis of ALS is based entirely on clinical features. Identification of biomarkers for ALS would be important for diagnosis and might also provide clues to pathogenesis. OBJECTIVE: To determine if there is a specific protein profile in the CSF that distinguishes patients with ALS from those with purely motor peripheral neuropathy (PN) and healthy control subjects. METHODS: CSF obtained from patients with ALS, disease controls (patients with other neurologic disorders), and normal controls were analyzed using the surface-enhanced laser desorption/ionization time-of-flight mass spectrometry proteomics technique. Biomarker sensitivity and specificity was calculated with receiver operating characteristic curve methodology. ALS biomarkers were purified and sequence identified by mass spectrometry-directed peptide sequencing. RESULTS: In initial proteomic discovery studies, three protein species (4.8-, 6.7-, and 13.4-kDa) that were significantly lower in concentration in the CSF from patients with ALS (n = 36) than in normal controls (n = 21) were identified. A combination of three protein species (the "three-protein" model) correctly identified patients with ALS with 95% accuracy, 91% sensitivity, and 97% specificity from the controls. Independent validation studies using separate cohorts of ALS (n = 13), healthy control (n = 25), and PN (n = 7) subjects confirmed the ability of the three CSF protein species to separate patients with ALS from other diseases. Protein sequence analysis identified the 13.4-kDa protein species as cystatin C and the 4.8-kDa protein species as a peptic fragment of the neurosecretory protein VGF. CONCLUSION: Additional application of a "three-protein" biomarker model to current diagnostic criteria may provide an objective biomarker pattern to help identify patients with ALS.

Chloroplast transit peptide prediction: a peek inside the black box.

Previous work in predicting protein localization to the chloroplast organelle in plants led to the development of an artificial neural network-based approach capable of remarkable accuracy in its prediction (ChloroP). A common criticism against such neural network models is that it is difficult to interpret the criteria that are used in making predictions. We address this concern with several new prediction methods that base predictions explicitly on the abundance of different amino acid types in the N-terminal region of the protein. Our successful prediction accuracy suggests that ChloroP uses little positional information in its decision-making; an unexpected result given the elaborate ChloroP input scheme. By removing positional information, our simpler methods allow us to identify those amino acids that are useful for successful prediction. The identification of important sequence features, such as amino acid content, is advantageous if one of the goals of localization predictors is to gain an understanding of the biological process of chloroplast localization. Our most accurate predictor combines principal component analysis and logistic regression. Web-based prediction using this method is available online at http://apicoplast.cis.upenn.edu/pclr/.

SVD-NET: an algorithm that automatically selects network structure.

An algorithm is developed for training feedforward neural networks that uses singular value decomposition (SVD) to identify and eliminate redundant hidden nodes. Minimizing redundancy gives smaller networks, producing models that generalize better and thus eliminate the need of using cross-validation to avoid overfitting. The method is demonstrated by modeling a chemical reactor.

Significance of conductances in Hodgkin-Huxley models.

1. We explore the roles of conductances in Hodgkin-Huxley (HH) models using a method that allows the explicit linking of HH model input-output behavior to parameter values for maximal conductances, voltage shifts, and time constants. The procedure can be used to identify not only the parameter values most critical to supporting a neuronal activity pattern of interest but also the relationships between parameters which may be required, e.g., limited ranges of relative magnitudes. 2. The method is the repeated use of stochastic search to find hundreds or even thousands of different sets of model parameter values that allow a HH model to produce a desired behavior, such as current-frequency transduction, to within a desired tolerance, e.g., frequency match to within 10 Hz. Graphical or other analysis may then be performed to reveal the shape and boundaries of the parameter solution regions that support the desired behavior. 3. The shape of these parameter regions can reveal parameter values and relationships essential to the behavior. For instance, graphical display may reveal covariances between maximal conductance values, or a much wider range of variation in some maximal conductance values than in others. 4. We demonstrate the use of these techniques with simple, representative HH models, primarily that of Connor et al. for crustacean walking leg axons, but also some extensions of the results are explored using the more complex model of McCormick and Huguenard for thalamocortical relay neurons. Both models are single compartment. Behaviors studied include current-to-frequency transduction, the time delay to first action potential in response to current steps, and the timing of action potential occurrences in response to both square-wave current injection and the injection of currents derived from in vitro records of excitatory postsynaptic currents. 5. Using these simple models, we find that relatively general behaviors such as current-frequency (I/F) curves may be supported by very broad, but bounded parameter solution regions, with the shape of the solution regions revealing the relative importance of the maximal conductances of a model in creating the behavior. Furthermore, we find that a focus on increasingly specific behaviors, such as I/F behavior, defined by tolerances of only a few hertz combined with strict requirements for action potential height, inevitably leads to increasingly narrow, and eventually nonphysiologically narrow, regions of acceptable parameter values. 6. We use the Connor et al. model to reproduce the in vitro action potential timing responses of a rat brain stem neuron to various stimuli.(ABSTRACT TRUNCATED AT 400 WORDS)

Using radial basis functions to approximate a function and its error bounds.

A novel network called the validity index network (VI net) is presented. The VI net, derived from radial basis function networks, fits functions and calculates confidence intervals for its predictions, indicating local regions of poor fit and extrapolation.