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 Matthew's 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 heteroge...

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 pairwise 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.

Structures of peptide fragments drawn from a protein can potentially occupy a vast conformational continuum. We co-ordinatize this conformational space with the help of geometric invariants and demonstrate that the peptide conformations of the currently available protein structures are heavily biased in favor of a finite number of conformational types or structural building blocks. This is achieved by representing a peptides' backbone structure with geometric invariants and then clustering peptides based on closeness of the geometric invariants. This results in 12,903 clusters, of which 2207 are made up of peptides drawn from functionally and/or structurally related proteins. These are termed "functional" clusters and provide clues about potential functional sites. The rest of the clusters, including the largest few, are made up of peptides drawn from unrelated proteins and are termed "structural" clusters. The largest clusters are of regular secondary structures such as helices and beta strands as well as of beta hairpins. Several categories of helices and strands are discovered based on geometric differences. In addition to the known classes of loops, we discover several new classes, which will be useful in protein structure modeling. Our algorithm does not require assignment of secondary structure and, therefore, overcomes the limitations in loop classification due to ambiguity in secondary structure assignment at loop boundaries.Keywords: geometric invariants; protein structure comparison; secondary structure; loop IntroductionGlobular proteins are made up of regular secondary structures such as a-helices and b-strands and non-regular secondary structures, which are referred to as loops. The regular secondary structures are defined based on a regular pattern of the backbone torsion angles for consecutive amino acid residues or periodic patterns of hydrogen bonding between the backbone NH and CvO groups.1 Loops are the regions that join the regular secondary structures and lack the regularity of torsion angles for consecutive residues. In fact, loops, polypeptide fragments from proteins, which trace a "loop-shaped" path in three-dimensional space, were considered to be random coils until recently.2 Loops are highly compact substructures and are typically situated at the protein surface. Certain loop geometries have been shown to recur across non-homologous proteins, which forms the basis for classification of loops into structural families. For example, the b-hairpin and a-turn families of loops have been described in detail.1,3 -7 A much wider classification of loops of various categories has been provided by Kwasigroch et al. 8 and by Oliva et al. 9 Loop classification has important implications in protein structure modeling and in fitting the NMR distance constraints or an X-ray crystallography electron density map to a loop geometry. On the contrary, no such fine-grained classification has been attempted for a-helices and b-strands, although detectable variations are reported in these regular secondar...

No abstract

Motivation: The exponential growth of scientific literature has resulted in a massive amount of unstructured natural language data that cannot be directly handled by means of bioinformatics tools. Such tools generally require structured data, often generated through a cumbersome process of manual literature curation. Herein, we present MyMiner, a free and user-friendly text annotation tool aimed to assist in carrying out the main biocuration tasks and to provide labelled data for the development of text mining systems. MyMiner allows easy classification and labelling of textual data according to user-specified classes as well as predefined biological entities. The usefulness and efficiency of this application have been tested for a range of real-life annotation scenarios of various research topics.