Consensus hologram QSAR modeling for the prediction of human intestinal absorption

Consistent in silico models for ADME properties are useful tools in early drug discovery. Here, we report the hologram QSAR modeling of human intestinal absorption using a dataset of 638 compounds with experimental data associated. The final validated models are consistent and robust for the consensus prediction of this important pharmacokinetic property and are suitable for virtual screening applications. (C) 2012 Elsevier Ltd. All rights reserved.

BPROMPT:a consensus server for membrane protein prediction

Protein structure prediction is a cornerstone of bioinformatics research. Membrane proteins require their own prediction methods due to their intrinsically different composition. A variety of tools exist for topology prediction of membrane proteins, many of them available on the Internet. The server described in this paper, BPROMPT (Bayesian PRediction Of Membrane Protein Topology), uses a Bayesian Belief Network to combine the results of other prediction methods, providing a more accurate consensus prediction. Topology predictions with accuracies of 70% for prokaryotes and 53% for eukaryotes were achieved. BPROMPT can be accessed at http://www.jenner.ac.uk/BPROMPT.

She’s a femme fatale: low-density larval development produces good disease vectors

Two hypotheses for how conditions for larval mosquitoes affect vectorial capacity make opposite predictions about the relationship of adult size and frequency of infection with vector-borne pathogens. Competition among larvae produces small adult females. The competition-susceptibility hypothesis postulates that small females are more susceptible to infection and predicts frequency of infection should decrease with size. The competition-longevity hypothesis postulates that small females have lower longevity and lower probability of becoming competent to transmit the pathogen and thus predicts frequency of infection should increase with size. We tested these hypotheses for Aedes aegypti in Rio de Janeiro, Brazil, during a dengue outbreak. In the laboratory, longevity increases with size, then decreases at the largest sizes. For field-collected females, generalised linear mixed model comparisons showed that a model with a linear increase of frequency of dengue with size produced the best Akaike’s information criterion with a correction for small sample sizes (AICc). Consensus prediction of three competing models indicated that frequency of infection increases monotonically with female size, consistent with the competition-longevity hypothesis. Site frequency of infection was not significantly related to site mean size of females. Thus, our data indicate that uncrowded, low competition conditions for larvae produce the females that are most likely to be important vectors of dengue. More generally, ecological conditions, particularly crowding and intraspecific competition among larvae, are likely to affect vector-borne pathogen transmission in nature, in this case via effects on longevity of resulting adults. Heterogeneity among individual vectors in likelihood of infection is a generally important outcome of ecological conditions impacting vectors as larvae.

Prediction of sediments toxicity using consensus-based sediment quality guidelines and benthic foraminifera in the Ria de Aveiro(Portugal)

Ria de Aveiro is a large and shallow lagoon on the west coast of Portugal (40º38’N, 8º45´W), characterized by a complex geometry. It includes large areas of intertidal flats and a network of narrow channels which are connected to the Atlantic by an artificial inlet. Tides are the main forcing of the hydrology and physical processes of the lagoon. The deeper areas near the inlet are characterized by strong marine influence through tidal inflow, with high values of current velocity (>1m/s) and tidal range (2–3 m at spring tides), while in remote shallow areas, the circulation and the sea water inflow are reduced. These remote areas are more influenced by fresh waters received from several rivers and several small streams. The Aveiro lagoon is a very important ecosystem but as been used as recipient for various kinds of anthropogenic wastes resulting from the high population density, urban activities and industrial development. One of the most important Portuguese industrial centre is located in the lagoon margins. Ria de Aveiro is a coastal lagoon under huge direct antropization. This system also suffers strong diffuse antropization. This work is related with diffuse antropization linked with chemical pollution which may lead to biological stress and collapse.

Experimental analysis and computer prediction of CTF/NFI transcription factor DNA binding sites.

Accurate prediction of transcription factor binding sites is needed to unravel the function and regulation of genes discovered in genome sequencing projects. To evaluate current computer prediction tools, we have begun a systematic study of the sequence-specific DNA-binding of a transcription factor belonging to the CTF/NFI family. Using a systematic collection of rationally designed oligonucleotides combined with an in vitro DNA binding assay, we found that the sequence specificity of this protein cannot be represented by a simple consensus sequence or weight matrix. For instance, CTF/NFI uses a flexible DNA binding mode that allows for variations of the binding site length. From the experimental data, we derived a novel prediction method using a generalised profile as a binding site predictor. Experimental evaluation of the generalised profile indicated that it accurately predicts the binding affinity of the transcription factor to natural or synthetic DNA sequences. Furthermore, the in vitro measured binding affinities of a subset of oligonucleotides were found to correlate with their transcriptional activities in transfected cells. The combined computational-experimental approach exemplified in this work thus resulted in an accurate prediction method for CTF/NFI binding sites potentially functioning as regulatory regions in vivo.

Prediction of Antibacterial Activity from Physicochemical Properties of Antimicrobial Peptides

Consensus is gathering that antimicrobial peptides that exert their antibacterial action at the membrane level must reach a local concentration threshold to become active. Studies of peptide interaction with model membranes do identify such disruptive thresholds but demonstrations of the possible correlation of these with the in vivo onset of activity have only recently been proposed. In addition, such thresholds observed in model membranes occur at local peptide concentrations close to full membrane coverage. In this work we fully develop an interaction model of antimicrobial peptides with biological membranes; by exploring the consequences of the underlying partition formalism we arrive at a relationship that provides antibacterial activity prediction from two biophysical parameters: the affinity of the peptide to the membrane and the critical bound peptide to lipid ratio. A straightforward and robust method to implement this relationship, with potential application to high-throughput screening approaches, is presented and tested. In addition, disruptive thresholds in model membranes and the onset of antibacterial peptide activity are shown to occur over the same range of locally bound peptide concentrations (10 to 100 mM), which conciliates the two types of observations

Prediction of exposed domains of envelope glycoprotein in Indian HIV-1 isolates and experimental confirmation of their immunogenicity in humans

We describe the impact of subtype differences on the seroreactivity of linear antigenic epitopes in envelope glycoprotein of HIV-1 isolates from different geographical locations. By computer analysis, we predicted potential antigenic sites of envelope glycoprotein (gp120 and gp4l) of this virus. For this purpose, after fetching sequences of proteins of interest from data banks, values of hydrophilicity, flexibility, accessibility, inverted hydrophobicity, and secondary structure were considered. We identified several potential antigenic epitopes in a B subtype strain of envelope glycoprotein of HIV-1 (IIIB). Solid- phase peptide synthesis methods of Merrifield and Fmoc chemistry were used for synthesizing peptides. These synthetic peptides corresponded mainly to the C2, V3 and CD4 binding sites of gp120 and some parts of the ectodomain of gp41. The reactivity of these peptides was tested by ELISA against different HIV-1-positive sera from different locations in India. For two of these predicted epitopes, the corresponding Indian consensus sequences (LAIERYLKQQLLGWG and DIIGDIRQAHCNISEDKWNET) (subtype C) were also synthesized and their reactivity was tested by ELISA. These peptides also distinguished HIV-1-positive sera of Indians with C subtype infections from sera from HIV-negative subjects.

Hierarchical Prediction Machines and Big Data Analytics

An emerging consensus in cognitive science views the biological brain as a hierarchically-organized predictive processing system. This is a system in which higher-order regions are continuously attempting to predict the activity of lower-order regions at a variety of (increasingly abstract) spatial and temporal scales. The brain is thus revealed as a hierarchical prediction machine that is constantly engaged in the effort to predict the flow of information originating from the sensory surfaces. Such a view seems to afford a great deal of explanatory leverage when it comes to a broad swathe of seemingly disparate psychological phenomena (e.g., learning, memory, perception, action, emotion, planning, reason, imagination, and conscious experience). In the most positive case, the predictive processing story seems to provide our first glimpse at what a unified (computationally-tractable and neurobiological plausible) account of human psychology might look like. This obviously marks out one reason why such models should be the focus of current empirical and theoretical attention. Another reason, however, is rooted in the potential of such models to advance the current state-of-the-art in machine intelligence and machine learning. Interestingly, the vision of the brain as a hierarchical prediction machine is one that establishes contact with work that goes under the heading of 'deep learning'. Deep learning systems thus often attempt to make use of predictive processing schemes and (increasingly abstract) generative models as a means of supporting the analysis of large data sets. But are such computational systems sufficient (by themselves) to provide a route to general human-level analytic capabilities? I will argue that they are not and that closer attention to a broader range of forces and factors (many of which are not confined to the neural realm) may be required to understand what it is that gives human cognition its distinctive (and largely unique) flavour. The vision that emerges is one of 'homomimetic deep learning systems', systems that situate a hierarchically-organized predictive processing core within a larger nexus of developmental, behavioural, symbolic, technological and social influences. Relative to that vision, I suggest that we should see the Web as a form of 'cognitive ecology', one that is as much involved with the transformation of machine intelligence as it is with the progressive reshaping of our own cognitive capabilities.

Intrinsic disorder prediction from the analysis of multiple protein fold recognition models

Motivation: Intrinsic protein disorder is functionally implicated in numerous biological roles and is, therefore, ubiquitous in proteins from all three kingdoms of life. Determining the disordered regions in proteins presents a challenge for experimental methods and so recently there has been much focus on the development of improved predictive methods. In this article, a novel technique for disorder prediction, called DISOclust, is described, which is based on the analysis of multiple protein fold recognition models. The DISOclust method is rigorously benchmarked against the top.ve methods from the CASP7 experiment. In addition, the optimal consensus of the tested methods is determined and the added value from each method is quantified. Results: The DISOclust method is shown to add the most value to a simple consensus of methods, even in the absence of target sequence homology to known structures. A simple consensus of methods that includes DISOclust can significantly outperform all of the previous individual methods tested.

Secondary structure prediction with support vector machines

Motivation: A new method that uses support vector machines (SVMs) to predict protein secondary structure is described and evaluated. The study is designed to develop a reliable prediction method using an alternative technique and to investigate the applicability of SVMs to this type of bioinformatics problem. Methods: Binary SVMs are trained to discriminate between two structural classes. The binary classifiers are combined in several ways to predict multi-class secondary structure. Results: The average three-state prediction accuracy per protein (Q3) is estimated by cross-validation to be 77.07 ± 0.26% with a segment overlap (Sov) score of 73.32 ± 0.39%. The SVM performs similarly to the 'state-of-the-art' PSIPRED prediction method on a non-homologous test set of 121 proteins despite being trained on substantially fewer examples. A simple consensus of the SVM, PSIPRED and PROFsec achieves significantly higher prediction accuracy than the individual methods. Availability: The SVM classifier is available from the authors. Work is in progress to make the method available on-line and to integrate the SVM predictions into the PSIPRED server.

Allergen motifs and the prediction of allergenicity

We have recently shown that the majority of allergens can be represented by allergen motifs. This observation prompted us to experimentally investigate the synthesized peptides corresponding to the in silico motifs with regard to potential IgE binding and cross-reactions with allergens. Two motifs were selected as examples to conduct in vitro studies. From the first motif, derived from allergenic MnSOD sequences, the motif stretch of the allergen Asp f 6 was selected and synthesized as a peptide (MnSOD Mot). The corresponding full-length MnSOD was also expressed in Escherichia coli and both were compared for IgE reactivity with sera of patients reacting to the MnSOD of Aspergillus fumigatus or Malassezia sympodialis. For the second motif, the invertebrate tropomyosin sequences were aligned and a motif consensus sequence was expressed as a recombinant protein (Trop Mot). The IgE reactivity of Trop Mot was analyzed in ELISA and compared to that of recombinant tropomyosin from the shrimp Penaeus aztecus (rPen a 1) in ImmunoCAP. MnSOD Mot was weakly recognized by some of the tested sera, suggesting that the IgE binding epitopes of a multimeric globular protein such as MnSOD cannot be fully represented by a motif peptide. In contrast, the motif Trop Mot showed the same IgE reactivity as shrimp full-length tropomyosin, indicating that the major allergenic reactivity of a repetitive structure such as tropomyosin can be covered by a motif peptide. Our results suggest that the motif-generating algorithm may be used for identifying major IgE binding structures of coiled-coil proteins.

Interval Prediction Based on Experts’ Statements

In the work [1] we proposed an approach of forming a consensus of experts’ statements in pattern recognition. In this paper, we present a method of aggregating sets of individual statements into a collective one for the case of forecasting of quantitative variable.

Multidimensional Heterogeneous Variable Prediction Based on Experts’ Statements

* The work was supported by the RFBR under Grant N07-01-00331a.

ArrayMining: a modular web-application for microarray analysis combining ensemble and consensus methods with cross-study normalization

Background: Statistical analysis of DNA microarray data provides a valuable diagnostic tool for the investigation of genetic components of diseases. To take advantage of the multitude of available data sets and analysis methods, it is desirable to combine both different algorithms and data from different studies. Applying ensemble learning, consensus clustering and cross-study normalization methods for this purpose in an almost fully automated process and linking different analysis modules together under a single interface would simplify many microarray analysis tasks. Results: We present ArrayMining.net, a web-application for microarray analysis that provides easy access to a wide choice of feature selection, clustering, prediction, gene set analysis and cross-study normalization methods. In contrast to other microarray-related web-tools, multiple algorithms and data sets for an analysis task can be combined using ensemble feature selection, ensemble prediction, consensus clustering and cross-platform data integration. By interlinking different analysis tools in a modular fashion, new exploratory routes become available, e.g. ensemble sample classification using features obtained from a gene set analysis and data from multiple studies. The analysis is further simplified by automatic parameter selection mechanisms and linkage to web tools and databases for functional annotation and literature mining. Conclusion: ArrayMining.net is a free web-application for microarray analysis combining a broad choice of algorithms based on ensemble and consensus methods, using automatic parameter selection and integration with annotation databases.

Exploring Iris Colour Prediction And Ancestry Inference In Admixed Populations Of South America.

New DNA-based predictive tests for physical characteristics and inference of ancestry are highly informative tools that are being increasingly used in forensic genetic analysis. Two eye colour prediction models: a Bayesian classifier - Snipper and a multinomial logistic regression (MLR) system for the Irisplex assay, have been described for the analysis of unadmixed European populations. Since multiple SNPs in combination contribute in varying degrees to eye colour predictability in Europeans, it is likely that these predictive tests will perform in different ways amongst admixed populations that have European co-ancestry, compared to unadmixed Europeans. In this study we examined 99 individuals from two admixed South American populations comparing eye colour versus ancestry in order to reveal a direct correlation of light eye colour phenotypes with European co-ancestry in admixed individuals. Additionally, eye colour prediction following six prediction models, using varying numbers of SNPs and based on Snipper and MLR, were applied to the study populations. Furthermore, patterns of eye colour prediction have been inferred for a set of publicly available admixed and globally distributed populations from the HGDP-CEPH panel and 1000 Genomes databases with a special emphasis on admixed American populations similar to those of the study samples.