Search

Online health communities constitute a useful source of information and social support for patients. American Cancer Society's Cancer Survivor Network (CSN), a 173,000-member community, is the largest online network for cancer patients, survivors, and caregivers. A discussion thread in CSN is often initiated by a cancer survivor seeking support from other members of CSN. Discussion threads are multi-party conversations that often provide a source of social support e.g., by bringing about a change of sentiment from negative to positive on the part of the thread originator. While previous studies regarding cancer survivors have shown that members of an online health community derive benefits from their participation in such communities, causal accounts of the factors that contribute to the observed benefits have been lacking. We introduce a novel framework to examine the temporal causality of sentiment dynamics in the CSN. We construct a Probabilistic Computation Tree Logic representation and a corresponding probabilistic Kripke structure to represent and reason about the changes in sentiments of posts in a thread over time. We use a sentiment classifier trained using machine learning on a set of posts manually tagged with sentiment labels to classify posts as expressing either positive or negative sentiment. We analyze the probabilistic Kripke structure to identify the prima facie causes of sentiment change on the part of the thread originators in the CSN forum and their significance. We find that the sentiment of replies appears to causally influence the sentiment of the thread originator. Our experiments also show that the conclusions are robust with respect to the choice of the (i) classification threshold of the sentiment classifier; (ii) and the choice of the specific sentiment classifier used. We also extend the basic framework for temporal causality analysis to incorporate the uncertainty in the states of the probabilistic Kripke structure resulting from the use of an imperfect state transducer (in our case, the sentiment classifier). Our analysis of temporal causality of CSN sentiment dynamics offers new insights that the designers, managers and moderators of an online community such as CSN can utilize to facilitate and enhance the interactions so as to better meet the social support needs of the CSN participants. The proposed methodology for analysis of temporal causality has broad applicability in a variety of settings where the dynamics of the underlying system can be modeled in terms of state variables that change in response to internal or external inputs.

Identification of B-cell epitopes in target antigens is a critical step in epitope-driven vaccine design, immunodiagnostic tests, and antibody production. B-cell epitopes could be linear, i.e., a contiguous amino acid sequence fragment of an antigen, or conformational, i.e., amino acids that are often not contiguous in the primary sequence but appear in close proximity within the folded 3D antigen structure. Numerous computational methods have been proposed for predicting both types of B-cell epitopes. However, the development of tools for reliably predicting B-cell epitopes remains a major challenge in immunoinformatics.Classifier ensembles a promising approach for combining a set of classifiers such that the overall performance of the resulting ensemble is better than the predictive performance of the best individual classifier. In this chapter, we show how to build a classifier ensemble for improved prediction of linear B-cell epitopes. The method can be easily adapted to build classifier ensembles for predicting conformational epitopes.

Background: Protein-protein interactions are critical to elucidating the role played by individual proteins in important biological pathways. Of particular interest are hub proteins that can interact with large numbers of partners and often play essential roles in cellular control. Depending on the number of binding sites, protein hubs can be classified at a structural level as singlish-interface hubs (SIH) with one or two binding sites, or multiple-interface hubs (MIH) with three or more binding sites. In terms of kinetics, hub proteins can be classified as date hubs (i.e., interact with different partners at different times or locations) or party hubs (i.e., simultaneously interact with multiple partners)., Methodology: Our approach works in 3 phases: Phase I classifies if a protein is likely to bind with another protein. Phase II determines if a protein-binding (PB) protein is a hub. Phase III classifies PB proteins as singlish-interface versus multiple-interface hubs and date versus party hubs. At each stage, we use sequence-based predictors trained using several standard machine learning techniques., Conclusions: Our method is able to predict whether a protein is a protein-binding protein with an accuracy of 94% and a correlation coefficient of 0.87; identify hubs from non-hubs with 100% accuracy for 30% of the data; distinguish date hubs/party hubs with 69% accuracy and area under ROC curve of 0.68; and SIH/MIH with 89% accuracy and area under ROC curve of 0.84. Because our method is based on sequence information alone, it can be used even in settings where reliable protein-protein interaction data or structures of protein-protein complexes are unavailable to obtain useful insights into the functional and evolutionary characteristics of proteins and their interactions., Availability: We provide a web server for our three-phase approach: http://hybsvm.gdcb.iastate.edu.

The initiation of B-cell ligand recognition is a critical step for the generation of an immune response against foreign bodies. We sought to identify the biochemical pathways involved in the B-cell ligand recognition cascade and sets of ligands that trigger similar immunological responses. We utilized several comparative approaches to analyze the gene coexpression networks generated from a set of microarray experiments spanning 33 different ligands. First, we compared the degree distributions of the generated networks. Second, we utilized a pairwise network alignment algorithm, BiNA, to align the networks based on the hubs in the networks. Third, we aligned the networks based on a set of KEGG pathways. We summarized our results by constructing a consensus hierarchy of pathways that are involved in B cell ligand recognition. The resulting pathways were further validated through literature for their common physiological responses. Collectively, the results based on our comparative analyses of degree distributions, alignment of hubs, and alignment based on KEGG pathways provide a basis for molecular characterization of the immune response states of B-cells and demonstrate the power of comparative approaches (e.g., gene coexpression network alignment algorithms) in elucidating biochemical pathways involved in complex signaling events in cells., (Copyright © 2012. Published by Elsevier Ltd.)

Background: Identification of the residues in protein-protein interaction sites has a significant impact in problems such as drug discovery. Motivated by the observation that the set of interface residues of a protein tend to be conserved even among remote structural homologs, we introduce PrISE, a family of local structural similarity-based computational methods for predicting protein-protein interface residues., Results: We present a novel representation of the surface residues of a protein in the form of structural elements. Each structural element consists of a central residue and its surface neighbors. The PrISE family of interface prediction methods uses a representation of structural elements that captures the atomic composition and accessible surface area of the residues that make up each structural element. Each of the members of the PrISE methods identifies for each structural element in the query protein, a collection of similar structural elements in its repository of structural elements and weights them according to their similarity with the structural element of the query protein. PrISEL relies on the similarity between structural elements (i.e. local structural similarity). PrISEG relies on the similarity between protein surfaces (i.e. general structural similarity). PrISEC, combines local structural similarity and general structural similarity to predict interface residues. These predictors label the central residue of a structural element in a query protein as an interface residue if a weighted majority of the structural elements that are similar to it are interface residues, and as a non-interface residue otherwise. The results of our experiments using three representative benchmark datasets show that the PrISEC outperforms PrISEL and PrISEG; and that PrISEC is highly competitive with state-of-the-art structure-based methods for predicting protein-protein interface residues. Our comparison of PrISEC with PredUs, a recently developed method for predicting interface residues of a query protein based on the known interface residues of its (global) structural homologs, shows that performance superior or comparable to that of PredUs can be obtained using only local surface structural similarity. PrISEC is available as a Web server at http://prise.cs.iastate.edu/, Conclusions: Local surface structural similarity based methods offer a simple, efficient, and effective approach to predict protein-protein interface residues.

Background: RNA-protein interactions (RPIs) play important roles in a wide variety of cellular processes, ranging from transcriptional and post-transcriptional regulation of gene expression to host defense against pathogens. High throughput experiments to identify RNA-protein interactions are beginning to provide valuable information about the complexity of RNA-protein interaction networks, but are expensive and time consuming. Hence, there is a need for reliable computational methods for predicting RNA-protein interactions., Results: We propose RPISeq, a family of classifiers for predicting RNA-protein interactions using only sequence information. Given the sequences of an RNA and a protein as input, RPIseq predicts whether or not the RNA-protein pair interact. The RNA sequence is encoded as a normalized vector of its ribonucleotide 4-mer composition, and the protein sequence is encoded as a normalized vector of its 3-mer composition, based on a 7-letter reduced alphabet representation. Two variants of RPISeq are presented: RPISeq-SVM, which uses a Support Vector Machine (SVM) classifier and RPISeq-RF, which uses a Random Forest classifier. On two non-redundant benchmark datasets extracted from the Protein-RNA Interface Database (PRIDB), RPISeq achieved an AUC (Area Under the Receiver Operating Characteristic (ROC) curve) of 0.96 and 0.92. On a third dataset containing only mRNA-protein interactions, the performance of RPISeq was competitive with that of a published method that requires information regarding many different features (e.g., mRNA half-life, GO annotations) of the putative RNA and protein partners. In addition, RPISeq classifiers trained using the PRIDB data correctly predicted the majority (57-99%) of non-coding RNA-protein interactions in NPInter-derived networks from E. coli, S. cerevisiae, D. melanogaster, M. musculus, and H. sapiens., Conclusions: Our experiments with RPISeq demonstrate that RNA-protein interactions can be reliably predicted using only sequence-derived information. RPISeq offers an inexpensive method for computational construction of RNA-protein interaction networks, and should provide useful insights into the function of non-coding RNAs. RPISeq is freely available as a web-based server at http://pridb.gdcb.iastate.edu/RPISeq/.

Computational protein-protein docking is a valuable tool for determining the conformation of complexes formed by interacting proteins. Selecting near-native conformations from the large number of possible models generated by docking software presents a significant challenge in practice. We introduce a novel method for ranking docked conformations based on the degree of overlap between the interface residues of a docked conformation formed by a pair of proteins with the set of predicted interface residues between them. Our approach relies on a method, called PS-HomPPI, for reliably predicting protein-protein interface residues by taking into account information derived from both interacting proteins. PS-HomPPI infers the residues of a query protein that are likely to interact with a partner protein based on known interface residues of the homo-interologs of the query-partner protein pair, i.e., pairs of interacting proteins that are homologous to the query protein and partner protein. Our results on Docking Benchmark 3.0 show that the quality of the ranking of docked conformations using our method is consistently superior to that produced using ClusPro cluster-size-based and energy-based criteria for 61 out of the 64 docking complexes for which PS-HomPPI produces interface predictions. An implementation of our method for ranking docked models is freely available at: http://einstein.cs.iastate.edu/DockRank/.

High accuracy sequence classification often requires the use of higher order Markov models (MMs). However, the number of MM parameters increases exponentially with the range of direct dependencies between sequence elements, thereby increasing the risk of overfitting when the data set is limited in size. We present abstraction augmented Markov models (AAMMs) that effectively reduce the number of numeric parameters of k(th) order MMs by successively grouping strings of length k (i.e., k-grams) into abstraction hierarchies. We evaluate AAMMs on three protein subcellular localization prediction tasks. The results of our experiments show that abstraction makes it possible to construct predictive models that use significantly smaller number of features (by one to three orders of magnitude) as compared to MMs. AAMMs are competitive with and, in some cases, significantly outperform MMs. Moreover, the results show that AAMMs often perform significantly better than variable order Markov models, such as decomposed context tree weighting, prediction by partial match, and probabilistic suffix trees.

Identification of epitopes that invoke strong responses from B-cells is one of the key steps in designing effective vaccines against pathogens. Because experimental determination of epitopes is expensive in terms of cost, time, and effort involved, there is an urgent need for computational methods for reliable identification of B-cell epitopes. Although several computational tools for predicting B-cell epitopes have become available in recent years, the predictive performance of existing tools remains far from ideal. We review recent advances in computational methods for B-cell epitope prediction, identify some gaps in the current state of the art, and outline some promising directions for improving the reliability of such methods.

We analyse sequence and structural features of protein-RNA interfaces using RB-147, a non-redundant dataset of protein-RNA complexes extracted from the PDB. We train classifiers using machine learning algorithms to predict protein-RNA interfaces from sequence and structure-derived features of proteins. Our experiments show that Struct-NB, a Naive Bayes classifier that exploits structural features, outperforms its counterparts that use only sequence features to predict protein-RNA binding residues.

Background: By using a standard Support Vector Machine (SVM) with a Sequential Minimal Optimization (SMO) method of training, Naïve Bayes and other machine learning algorithms we are able to distinguish between two classes of protein sequences: those folding to highly-designable conformations, or those folding to poorly- or non-designable conformations., Results: First, we generate all possible compact lattice conformations for the specified shape (a hexagon or a triangle) on the 2D triangular lattice. Then we generate all possible binary hydrophobic/polar (H/P) sequences and by using a specified energy function, thread them through all of these compact conformations. If for a given sequence the lowest energy is obtained for a particular lattice conformation we assume that this sequence folds to that conformation. Highly-designable conformations have many H/P sequences folding to them, while poorly-designable conformations have few or no H/P sequences. We classify sequences as folding to either highly- or poorly-designable conformations. We have randomly selected subsets of the sequences belonging to highly-designable and poorly-designable conformations and used them to train several different standard machine learning algorithms., Conclusion: By using these machine learning algorithms with ten-fold cross-validation we are able to classify the two classes of sequences with high accuracy -- in some cases exceeding 95%.

Understanding the gene networks that orchestrate the differentiation of retinal progenitors into photoreceptors in the developing retina is important not only due to its therapeutic applications in treating retinal degeneration but also because the developing retina provides an excellent model for studying CNS development. Although several studies have profiled changes in gene expression during normal retinal development, these studies offer at best only a starting point for functional studies focused on a smaller subset of genes. The large number of genes profiled at comparatively few time points makes it extremely difficult to reliably infer gene networks from a gene expression dataset. We describe a novel approach to identify and prioritize from multiple gene expression datasets, a small subset of the genes that are likely to be good candidates for further experimental investigation. We report progress on addressing this problem using a novel approach to querying multiple large-scale expression datasets using a 'seed network' consisting of a small set of genes that are implicated by published studies in rod photoreceptor differentiation. We use the seed network to identify and sort a list of genes whose expression levels are highly correlated with those of multiple seed network genes in at least two of the five gene expression datasets. The fact that several of the genes in this list have been demonstrated, through experimental studies reported in the literature, to be important in rod photoreceptor function provides support for the utility of this approach in prioritizing experimental targets for further experimental investigation. Based on Gene Ontology and KEGG pathway annotations for the list of genes obtained in the context of other information available in the literature, we identified seven genes or groups of genes for possible inclusion in the gene network involved in differentiation of retinal progenitor cells into rod photoreceptors. Our approach to querying multiple gene expression datasets using a seed network constructed from known interactions between specific genes of interest provides a promising strategy for focusing hypothesis-driven experiments using large-scale 'omics' data.

We analyze the characteristics of protein-protein interfaces using the largest datasets available from the Protein Data Bank (PDB). We start with a comparison of interfaces with protein cores and non-interface surfaces. The results show that interfaces differ from protein cores and non-interface surfaces in residue composition, sequence entropy, and secondary structure. Since interfaces, protein cores, and non-interface surfaces have different solvent accessibilities, it is important to investigate whether the observed differences are due to the differences in solvent accessibility or differences in functionality. We separate out the effect of solvent accessibility by comparing interfaces with a set of residues having the same solvent accessibility as the interfaces. This strategy reveals residue distribution propensities that are not observable by comparing interfaces with protein cores and non-interface surfaces. Our conclusions are that there are larger numbers of hydrophobic residues, particularly aromatic residues, in interfaces, and the interactions apparently favored in interfaces include the opposite charge pairs and hydrophobic pairs. Surprisingly, Pro-Trp pairs are over represented in interfaces, presumably because of favorable geometries. The analysis is repeated using three datasets having different constraints on sequence similarity and structure quality. Consistent results are obtained across these datasets. We have also investigated separately the characteristics of heteromeric interfaces and homomeric interfaces.

Identifying B-cell epitopes play an important role in vaccine design, immunodiagnostic tests, and antibody production. Therefore, computational tools for reliably predicting B-cell epitopes are highly desirable. We explore two machine learning approaches for predicting flexible length linear B-cell epitopes. The first approach utilizes four sequence kernels for determining a similarity score between any arbitrary pair of variable length sequences. The second approach utilizes four different methods of mapping a variable length sequence into a fixed length feature vector. Based on our empirical comparisons, we propose FBCPred, a novel method for predicting flexible length linear B-cell epitopes using the subsequence kernel. Our results demonstrate that FBCPred significantly outperforms all other classifiers evaluated in this study. An implementation of FBCPred and the datasets used in this study are publicly available through our linear B-cell epitope prediction server, BCPREDS, at: http://ailab.cs.iastate.edu/bcpreds/.

Telomerase is a ribonucleoprotein enzyme that adds telomeric DNA repeat sequences to the ends of linear chromosomes. The enzyme plays pivotal roles in cellular senescence and aging, and because it provides a telomere maintenance mechanism for approximately 90% of human cancers, it is a promising target for cancer therapy. Despite its importance, a high-resolution structure of the telomerase enzyme has been elusive, although a crystal structure of an N-terminal domain (TEN) of the telomerase reverse transcriptase subunit (TERT) from Tetrahymena has been reported. In this study, we used a comparative strategy, in which sequence-based machine learning approaches were integrated with computational structural modeling, to explore the potential conservation of structural and functional features of TERT in phylogenetically diverse species. We generated structural models of the N-terminal domains from human and yeast TERT using a combination of threading and homology modeling with the Tetrahymena TEN structure as a template. Comparative analysis of predicted and experimentally verified DNA and RNA binding residues, in the context of these structures, revealed significant similarities in nucleic acid binding surfaces of Tetrahymena and human TEN domains. In addition, the combined evidence from machine learning and structural modeling identified several specific amino acids that are likely to play a role in binding DNA or RNA, but for which no experimental evidence is currently available.

RNA-protein interactions are vitally important in a wide range of biological processes, including regulation of gene expression, protein synthesis, and replication and assembly of many viruses. We have developed a computational tool for predicting which amino acids of an RNA binding protein participate in RNA-protein interactions, using only the protein sequence as input. RNABindR was developed using machine learning on a validated nonredundant data set of interfaces from known RNA-protein complexes in the Protein Data Bank. It generates a classifier that captures primary sequence signals sufficient for predicting which amino acids in a given protein are located in the RNA-protein interface. In leave-one-out cross-validation experiments, RNABindR identifies interface residues with >85% overall accuracy. It can be calibrated by the user to obtain either high specificity or high sensitivity for interface residues. RNABindR, implementing a Naive Bayes classifier, performs as well as a more complex neural network classifier (to our knowledge, the only previously published sequence-based method for RNA binding site prediction) and offers the advantages of speed, simplicity and interpretability of results. RNABindR predictions on the human telomerase protein hTERT are in good agreement with experimental data. The availability of computational tools for predicting which residues in an RNA binding protein are likely to contact RNA should facilitate design of experiments to directly test RNA binding function and contribute to our understanding of the diversity, mechanisms, and regulation of RNA-protein complexes in biological systems. (RNABindR is available as a Web tool from http://bindr.gdcb.iastate.edu.).

Protein-protein and protein nucleic acid interactions are vitally important for a wide range of biological processes, including regulation of gene expression, protein synthesis, and replication and assembly of many viruses. We have developed machine learning approaches for predicting which amino acids of a protein participate in its interactions with other proteins and/or nucleic acids, using only the protein sequence as input. In this paper, we describe an application of classifiers trained on datasets of well-characterized protein-protein and protein-RNA complexes for which experimental structures are available. We apply these classifiers to the problem of predicting protein and RNA binding sites in the sequence of a clinically important protein for which the structure is not known: the regulatory protein Rev, essential for the replication of HIV-1 and other lentiviruses. We compare our predictions with published biochemical, genetic and partial structural information for HIV-1 and EIAV Rev and with our own published experimental mapping of RNA binding sites in EIAV Rev. The predicted and experimentally determined binding sites are in very good agreement. The ability to predict reliably the residues of a protein that directly contribute to specific binding events--without the requirement for structural information regarding either the protein or complexes in which it participates--can potentially generate new disease intervention strategies.

We present the first prototype of INDUS (Intelligent Data Understanding System), a federated, query-centric system for information integration and knowledge acquisition from distributed, semantically heterogeneous data sources that can be viewed (conceptually) as tables. INDUS employs ontologies and inter-ontology mappings, to enable a user to view a collection of such data sources (regardless of location, internal structure and query interfaces) as though they were a collection of tables structured according to an ontology supplied by the user. This allows INDUS to answer user queries against distributed, semantically heterogeneous data sources without the need for a centralized data warehouse or a common global ontology.

In this paper, we describe a machine learning approach for sequence-based prediction of protein-protein interaction sites. A support vector machine (SVM) classifier was trained to predict whether or not a surface residue is an interface residue (i.e., is located in the protein-protein interaction surface), based on the identity of the target residue and its ten sequence neighbors. Separate classifiers were trained on proteins from two categories of complexes, antibody-antigen and protease-inhibitor. The effectiveness of each classifier was evaluated using leave-one-out (jack-knife) cross-validation. Interface and non-interface residues were classified with relatively high sensitivity (82.3% and 78.5%) and specificity (81.0% and 77.6%) for proteins in the antigen-antibody and protease-inhibitor complexes, respectively. The correlation between predicted and actual labels was 0.430 and 0.462, indicating that the method performs substantially better than chance (zero correlation). Combined with recently developed methods for identification of surface residues from sequence information, this offers a promising approach to predict residues involved in protein-protein interactions from sequence information alone.