We present the two Bacteria Track tasks of BioNLP 2013 Shared Task (ST): Gene Regulation Network (GRN) and Bacteria Biotope (BB). These tasks were previously introduced in the 2011 BioNLP-ST Bacteria Track as Bacteria Gene Interaction (BI) and Bacteria Biotope (BB). The Bacteria Track was motivated by a need to develop specific BioNLP tools for fine-grained event extraction in bacteria biology. The 2013 tasks expand on the 2011 version by better addressing the biological knowledge modeling needs. New evaluation metrics were designed for the new goals. Moving beyond a list of gene interactions, the goal of the GRN task is to build a gene regulation network from the extracted gene interactions. BB'13 is dedicated to the extraction of bacteria biotopes, i.e . bacterial environmental information, as was BB'11. BB'13 extends the typology of BB'11 to a large diversity of biotopes, as defined by the OntoBiotope ontology. The detection of entities and events is tackled by distinct subtasks in order to measure the progress achieved by the participant systems since 2011. This paper details the corpus preparations and the evaluation metrics, as well as summarizing and discussing the participant results. Five groups participated in each of the two tasks. The high diversity of the participant methods reflects the dynamism of the BioNLP research community. The highest scores for the GRN and BB'13 tasks are similar to those obtained by the participants in 2011, despite of the increase in difficulty. The high density of events in short text segments (multi-event extraction) was a difficult issue for the participating systems for both tasks. The analysis of the BB'13 results also shows that co-reference resolution and entity boundary detection remain major hindrances. The evaluation results suggest new research directions for the improvement and development of Information Extraction for molecular and environmental biology. The Bacteria Track tasks remain publicly open; the BioNLP-ST website provides an online evaluation service, the reference corpora and the evaluation tools.

BACKGROUND: We present the BioNLP 2011 Shared Task Bacteria Track, the first Information Extraction challenge entirely dedicated to bacteria. It includes three tasks that cover different levels of biological knowledge. The Bacteria Gene Renaming supporting task is aimed at extracting gene renaming and gene name synonymy in PubMed abstracts. The Bacteria Gene Interaction is a gene/protein interaction extraction task from individual sentences. The interactions have been categorized into ten different sub-types, thus giving a detailed account of genetic regulations at the molecular level. Finally, the Bacteria Biotopes task focuses on the localization and environment of bacteria mentioned in textbook articles. We describe the process of creation for the three corpora, including document acquisition and manual annotation, as well as the metrics used to evaluate the participants' submissions. RESULTS: Three teams submitted to the Bacteria Gene Renaming task; the best team achieved an F-score of 87%. For the Bacteria Gene Interaction task, the only participant's score had reached a global F-score of 77%, although the system efficiency varies significantly from one sub-type to another. Three teams submitted to the Bacteria Biotopes task with very different approaches; the best team achieved an F-score of 45%. However, the detailed study of the participating systems efficiency reveals the strengths and weaknesses of each participating system. CONCLUSIONS: The three tasks of the Bacteria Track offer participants a chance to address a wide range of issues in Information Extraction, including entity recognition, semantic typing and coreference resolution. We found common trends in the most efficient systems: the systematic use of syntactic dependencies and machine learning. Nevertheless, the originality of the Bacteria Biotopes task encouraged the use of interesting novel methods and techniques, such as term compositionality, scopes wider than the sentence.

MOTIVATION: High-density oligonucleotide tiling array technology holds the promise of a better description of the complexity and the dynamics of transcriptional landscapes. In organisms such as bacteria and yeasts, transcription can be measured on a genome-wide scale with a resolution >25 bp. The statistical models currently used to handle these data remain however very simple, the most popular being the piecewise constant Gaussian model with a fixed number of breakpoints. RESULTS: This article describes a new methodology based on a hidden Markov model that embeds the segmentation of a continuous-valued signal in a probabilistic setting. For a computationally affordable cost, this framework (i) alleviates the difficulty of choosing a fixed number of breakpoints, and (ii) permits retrieving more information than a unique segmentation by giving access to the whole probability distribution of the transcription profile. Importantly, the model is also enriched and accounts for subtle effects such as signal 'drift' and covariates. Relevance of this framework is demonstrated on a Bacillus subtilis dataset. AVAILABILITY: A software is distributed under the GPL.

Ontologies are a well-motivated formal representation to model knowledge needed to extract and encode data from text. Yet, their tight integration with Information Extraction (IE) systems is still a research issue, a fortiori with complex ones that go beyond hierarchies. In this paper, we introduce an original architecture where IE is specified by designing an ontology, and the extraction process is seen as an Ontology Population (OP) task. Concepts and relations of the ontology define a normalized text representation. As their abstraction level is irrelevant for text extraction, we introduced a Lexical Layer (LL) along with the ontology, i.e. relations and classes at an intermediate level of normalization between raw text and concepts. On the contrary to previous IE systems, the extraction process only involves normalizing the outputs of Natural Language Processing (NLP) modules with instances of the ontology and the LL. All the remaining reasoning is left to a query module, which uses the inference rules of the ontology to derive new instances by deduction. In this context, these inference rules subsume classical extraction rules or patterns by providing access to appropriate abstraction level and domain knowledge. To acquire those rules, we adopt an Ontology Learning (OL) perspective, and automatically acquire the inference rules with relational Machine Learning (ML). Our approach is validated on a genic interaction extraction task from a Bacillus subtilis bacterium text corpus. We reach a global recall of 89.3% and a precision of 89.6%, with high scores for the ten conceptual relations in the ontology.

MOTIVATION: The availability of increasing amounts of sequence data about completely sequenced genomes spurs the development of new methods in the fields of automated annotation, and of comparative genomics. Tools allowing the visualization of results produced by analysis methods, superimposed on possibly annotated sequence data, and enabling synchronized navigation in multiple genomes, provide new means for interactive genome exploration. This kind of visual inspection can be used as a basis to assess the quality of new analysis algorithms, or to discover genome portions to be subjected to in-depth studies. RESULTS: We propose a software package, MuGeN, built for navigating through multiple annotated genomes. It is capable of retrieving annotated sequences in several formats, stored in local files, or available in databases over the network. From these, it then generates an interactive display, or an image file, in most common formats suitable for printing, further editing or integrating in Web pages. Genome maps may be mixed with computer analysis results loaded from XML files, whose format is generic enough to be adapted to a majority of sequence oriented analysis methods. AVAILABILITY: MuGeN is available at http://www-mig.jouy.inra.fr/bdsi/MuGeN.

MOTIVATION: Protein-protein interactions are a potential source of valuable clues in determining the functional role of as yet uncharacterized gene products in metabolic pathways. Graph-like structures emerging from the accumulation of interaction data make it difficult to maintain a consistent and global overview by hand. Bioinformatics tools are needed to perform this graph visualization while maintaining a link to the experimental data. RESULTS: "SPiD" is an online database for exploring networks of interacting proteins in Bacillus subtilis characterized by the two-hybrid system. Graphical displays of interaction networks are created dynamically as users interactively navigate through these networks. Third party applications can interface the database through a Common Object Request Broker Architecture (CORBA) tier. AVAILABILITY: SPiD is available through its web site at http://www-mig.versailles.inra.fr/bdsi/SPiD, and through an Interoperable Object Reference (IOR) and its associated Interface Definition Language (IDL). CONTACT: [email protected]

MOTIVATION: We created Micado, a database for managing genomic information, as part of the Bacillus subtilis genome programs. Its content will be progressively extended to the whole microbial world. RESULTS: A relational schema is defined for selective queries. It links eubacterial and archaeal sequences, genetic maps for Bacillus subtilis and Escherichia coli, and information on mutants. The latter comes from a new functional analysis project of unknown genes in B subtilis, and the database allows the community to curate information. To help queries from users, a graphical interface is built on SQL access to the database and provided through the WWW. We have automated imports of microbial sequences, and E. coli genetic map, by programming parsers of flat file distributions. These ensure smooth updates from molecular biology repositories on the Internet. Hyperlinks are created as a complement, to reference other general and specialized related information resources.