Ashish V. Tendulkar

The Protein-Protein Interaction tasks of BioCreative III: classification/ranking of articles and linking bio-ontology concepts to full text

BackgroundDetermining usefulness of biomedical text mining systems requires realistic task definition and data selection criteria without artificial constraints, measuring performance aspects that go beyond traditional metrics. The BioCreative III Protein-Protein Interaction (PPI) tasks were motivated by such considerations, trying to address aspects including how the end user would oversee the generated output, for instance by providing ranked results, textual evidence for human interpretation or measuring time savings by using automated systems. Detecting articles describing complex biological events like PPIs was addressed in the Article Classification Task (ACT), where participants were asked to implement tools for detecting PPI-describing abstracts. Therefore the BCIII-ACT corpus was provided, which includes a training, development and test set of over 12,000 PPI relevant and non-relevant PubMed abstracts labeled manually by domain experts and recording also the human classification times. The Interaction Method Task (IMT) went beyond abstracts and required mining for associations between more than 3,500 full text articles and interaction detection method ontology concepts that had been applied to detect the PPIs reported in them.ResultsA total of 11 teams participated in at least one of the two PPI tasks (10 in ACT and 8 in the IMT) and a total of 62 persons were involved either as participants or in preparing data sets/evaluating these tasks. Per task, each team was allowed to submit five runs offline and another five online via the BioCreative Meta-Server. From the 52 runs submitted for the ACT, the highest Matthews Correlation Coefficient (MCC) score measured was 0.55 at an accuracy of 89% and the best AUC iP/R was 68%. Most ACT teams explored machine learning methods, some of them also used lexical resources like MeSH terms, PSI-MI concepts or particular lists of verbs and nouns, some integrated NER approaches. For the IMT, a total of 42 runs were evaluated by comparing systems against manually generated annotations done by curators from the BioGRID and MINT databases. The highest AUC iP/R achieved by any run was 53%, the best MCC score 0.55. In case of competitive systems with an acceptable recall (above 35%) the macro-averaged precision ranged between 50% and 80%, with a maximum F-Score of 55%.ConclusionsThe results of the ACT task of BioCreative III indicate that classification of large unbalanced article collections reflecting the real class imbalance is still challenging. Nevertheless, text-mining tools that report ranked lists of relevant articles for manual selection can potentially reduce the time needed to identify half of the relevant articles to less than 1/4 of the time when compared to unranked results. Detecting associations between full text articles and interaction detection method PSI-MI terms (IMT) is more difficult than might be anticipated. This is due to the variability of method term mentions, errors resulting from pre-processing of articles provided as PDF files, and the heterogeneity and different granularity of method term concepts encountered in the ontology. However, combining the sophisticated techniques developed by the participants with supporting evidence strings derived from the articles for human interpretation could result in practical modules for biological annotation workflows.

Functional Sites in Protein Families Uncovered via an Objective and Automated Graph Theoretic Approach

We report a method for detection of recurring side-chain patterns (DRESPAT) using an unbiased and automated graph theoretic approach. We first list all structural patterns as sub-graphs where the protein is represented as a graph. The patterns from proteins are compared pair-wise to detect patterns common to a protein pair based on content and geometry criteria. The recurring pattern is then detected using an automated search algorithm from the all-against-all pair-wise comparison data of proteins. Intra-protein pattern comparison data are used to enable detection of patterns recurring within a protein. A method has been proposed for empirical calculation of statistical significance of recurring pattern. The method was tested on 17 protein sets of varying size, composed of non-redundant representatives from SCOP superfamilies. Recurring patterns in serine proteases, cysteine proteases, lipases, cupredoxin, ferredoxin, ferritin, cytochrome c, aspartoyl proteases, peroxidases, phospholipase A2, endonuclease, SH3 domain, EF-hand and lectins show additional residues conserved in the vicinity of the known functional sites. On the basis of the recurring patterns in ferritin, EF-hand and lectins, we could separate proteins or domains that are structurally similar yet different in metal ion-binding characteristics. In addition, novel recurring patterns were observed in glutathione-S-transferase, phospholipase A2 and ferredoxin with potential structural/functional roles. The results are discussed in relation to the known functional sites in each family. Between 2000 and 50,000 patterns were enumerated from each protein with between ten and 500 patterns detected as common to an evolutionarily related protein pair. Our results show that unbiased extraction of functional site pattern is not feasible from an evolutionarily related protein pair but is feasible from protein sets comprising five or more proteins. The DRESPAT method does not require a user-defined pattern, size or location of the pattern and therefore, has the potential to uncover new functional sites in protein families.

Comparative study of clustering techniques for short text documents

We compare various document clustering techniques including K-means, SVD-based method and a graph-based approach and their performance on short text data collected from Twitter. We define a measure for evaluating the cluster error with these techniques. Observations show that graph-based approach using affinity propagation performs best in clustering short text data with minimal cluster error.

PLAN2L: a web tool for integrated text mining and literature-based bioentity relation extraction

There is an increasing interest in using literature mining techniques to complement information extracted from annotation databases or generated by bioinformatics applications. Here we present PLAN2L, a web-based online search system that integrates text mining and information extraction techniques to access systematically information useful for analyzing genetic, cellular and molecular aspects of the plant model organism Arabidopsis thaliana. Our system facilitates a more efficient retrieval of information relevant to heterogeneous biological topics, from implications in biological relationships at the level of protein interactions and gene regulation, to sub-cellular locations of gene products and associations to cellular and developmental processes, i.e. cell cycle, flowering, root, leaf and seed development. Beyond single entities, also predefined pairs of entities can be provided as queries for which literature-derived relations together with textual evidences are returned. PLAN2L does not require registration and is freely accessible at http://zope.bioinfo.cnio.es/plan2l.

Multi-view methods for protein structure comparison using latent dirichlet allocation

Motivation: With rapidly expanding protein structure databases, efficiently retrieving structures similar to a given protein is an important problem. It involves two major issues: (i) effective protein structure representation that captures inherent relationship between fragments and facilitates efficient comparison between the structures and (ii) effective framework to address different retrieval requirements. Recently, researchers proposed vector space model of proteins using bag of fragments representation (FragBag), which corresponds to the basic information retrieval model. Results: In this article, we propose an improved representation of protein structures using latent dirichlet allocation topic model. Another important requirement is to retrieve proteins, whether they are either close or remote homologs. In order to meet diverse objectives, we propose multi-viewpoint based framework that combines multiple representations and retrieval techniques. We compare the proposed representation and retrieval framework on the benchmark dataset developed by Kolodny and co-workers. The results indicate that the proposed techniques outperform state-of-the-art methods. Availability: http://www.cse.iitm.ac.in/~ashishvt/research/protein-lda/. Contact: ashishvt@cse.iitm.ac.in

Subcellular Distribution of the Human Putative Nucleolar GTPase GNL1 is Regulated by a Novel Arginine/Lysine-Rich Domain and a GTP Binding Domain in a Cell Cycle-Dependent Manner

GNL1, a putative nucleolar GTPase, belongs to the MMR1-HSR1 family of large GTPases that are emerging as crucial coordinators of signaling cascades in different cellular compartments. Members of this family share very closely related G-domains, but the signals and pathways regulating their subcellular localization with respect to cell growth remain unknown. To understand the nuclear transport mechanism of GNL1, we have identified a novel arginine/lysine-rich nucleolar localization signal in the NH(2)-terminus that is shown to translocate GNL1 and a heterologous protein to the nucleus/nucleolus in a pathway that is independent of importin-α and importin-β. In addition, the present investigation provided evidence that GNL1 localized to the nucleus and the nucleolus only in G2 stage, in contrast to its cytoplasmic localization in the G1 and S phases of the cell cycle. Using heterokaryon assay, we have demonstrated that GNL1 shuttles between the nucleus and the cytoplasm and that the motif between amino acids 201 and 225 is essential for its export from the nucleus by a signal-mediated CRM1-independent pathway. Alanine-scanning mutagenesis of conserved residues within G-domains suggests that the G2 motif is critical for guanine nucleotide triphosphate (GTP) binding of GNL1 and further showed that nucleolar retention of GNL1 is regulated by a GTP-gating-mediated mechanism. Expression of wild-type GNL1 promotes G2/M transition, in contrast to the G-domain mutant (G2m), which fails to localize to the nucleolus. These data suggest that nucleolar translocation during G2 phase may be critical for faster M-phase transition during cell proliferation. Replacement of conserved residues within the G5 motif alters the stability of GNL1 without changing GTP binding activity. Finally, our data suggest that ongoing transcription is essential for the efficient localization of GNL1 to the nucleolus. Overall, the results reported here demonstrate that multiple mechanisms are involved in the translocation of GNL1 to the nucleolus in a cell cycle-dependent manner to regulate cell growth and proliferation.

Mechanism of host cell MAPK/ERK-2 incorporation into lentivirus particles: characterization of the interaction between MAPK/ERK-2 and proline-rich-domain containing capsid region of structural protein Gag.

The characteristic event that follows infection of a cell by retroviruses Including human immunodeficiency virus (HIV)/ simian immunodeficiency virus (SIV) is the formation of a reverse transcription complex in which viral nucleic acids are synthesized. Nuclear transport of newly synthesized viral DNA requires phosphorylation of proteins in the reverse transcription complex by virion-associated cellular kinases. Recently, we demonstrated that disruption of cellular mitogen-activated protein kinase (MAPK)/extracellular signal-regulated kinase 2 (ERK-2) incorporation into SIV virions inhibits virus replication in nonproliferating target cells, indicating that MAPK/ERK-2 plays an important role in HIV /SIV replication. The mechanism of incorporation of MAPK/ERK-2 into virus particles is not defined. In this regard, we hypothesized that a likely interaction of MAPK/ERK-2 with Gag(p55) may enable its packaging into virus particles. In the present investigation, we provided evidence for the first time that MAPK/ERK-2 interacts with the structural Gag polyprotein p55 using a combination of mutagenesis and protein-protein interaction analysis. We further show that MAPK/ERK-2 interacts specifically with the poly-proline motif present in the capsid region of Gag(p55). Utilizing virus-like particles directed by Gag, we have shown that the exchange of conserved proline residues within capsid of Gag(p55) resulted in impaired incorporation of MAPK/ERK-2. In addition, the deletion of a domain comprising amino acids 201 to 255 within host cell MAPK/ERK-2 abrogates its interaction with Gag(p55). The relevance of the poly-proline motif is further evident by its conservation in diverse retroviruses, as noted from the sequence analysis and structural modeling studies of predicted amino acid sequences of the corresponding Gag proteins. Collectively, these data suggest that the interaction of MAPK/ERK-2 with Gag polyprotein results in its incorporation into virus particles and may be essential for retroviral replication.

Drug discovery against H1N1 virus (influenza A virus) via computational virtual screening approach

The H1N1 virus is the causative agent of the recent outbreak of Swine flu pandemic. Neuraminidase is an enzyme that cleave glycosidic linkage of neuraminic acid on viral cell surface and is known to occur as antigen determinant to evoke immune response in host cell. It plays an important role in life cycle of influenza virus. Inhibitors of neuraminidase are, therefore, believed to have a potential in development of new drugs against swine flu. Using a recently published model structure of neuraminidase, we have carried out virtual screening of 70 compounds obtained from Ligand databases. The ligands library also included 57 natural plant metabolites from medicinal plants. The virtual screening was performed via PatchDock & GemDock softwares. Two of the plant metabolites, Hesperidin & Narirutin showed significantly higher docking score than the currently marketed anti-influenza drug Oseltamivir (Tamiflu).

A geometric invariant-based framework for the analysis of protein conformational space

MOTIVATION Characterization of the restricted nature of the protein local conformational space has remained a challenge, thereby necessitating a computationally expensive conformational search in protein modeling. Moreover, owing to the lack of unilateral structural descriptors, conventional data mining techniques, such as clustering and classification, have not been applied in protein structure analysis. RESULTS We first map the local conformations in a fixed dimensional space by using a carefully selected suite of geometric invariants (GIs) and then reduce the number of dimensions via principal component analysis (PCA). Distribution of the conformations in the space spanned by the first four PCs is visualized as a set of conditional bivariate probability distribution plots, where the peaks correspond to the preferred conformations. The locations of the different canonical structures in the PC-space have been interpreted in the context of the weights of the GIs to the first four PCs. Clustering of the available conformations reveals that the number of preferred local conformations is several orders of magnitude smaller than that suggested previously. SUPPLEMENTARY INFORMATION www.it.iitb.ac.in/~ashish/bioinfo2005/.

FragKB: Structural and Literature Annotation Resource of Conserved Peptide Fragments and Residues

Background FragKB (Fragment Knowledgebase) is a repository of clusters of structurally similar fragments from proteins. Fragments are annotated with information at the level of sequence, structure and function, integrating biological descriptions derived from multiple existing resources and text mining. Methodology FragKB contains approximately 400,000 conserved fragments from 4,800 representative proteins from PDB. Literature annotations are extracted from more than 1,700 articles and are available for over 12,000 fragments. The underlying systematic annotation workflow of FragKB ensures efficient update and maintenance of this database. The information in FragKB can be accessed through a web interface that facilitates sequence and structural visualization of fragments together with known literature information on the consequences of specific residue mutations and functional annotations of proteins and fragment clusters. FragKB is accessible online at http://ubio.bioinfo.cnio.es/biotools/fragkb/. Significance The information presented in FragKB can be used for modeling protein structures, for designing novel proteins and for functional characterization of related fragments. The current release is focused on functional characterization of proteins through inspection of conservation of the fragments.