Useful pathway models require a complete and accurate representation of the system, which requires that all relevant molecular species are captured, together with their physical interactions and chemical reactions. Pathway model reconstruction is currently largely carried out manually by domain experts, who must carefully read the scientific literature, in order to retrieve, evaluate and interpret and distil relevant fine-grained statements. Moreover, due to the proliferation of scientific databases and ontologies, discovery of previously unknown knowledge demands that scientists take into account information from many different resources, covering different levels of contextual information (e.g., degree of confidence or certainty expressed towards a finding). Thus, given the high complexity mechanisms involved in pathway models, whose detailed description can only be derived from analysis of heterogeneous, fragmented and incomplete sources, reconstructing pathway models is a slow, difficult and laborious process. Accordingly, there is a need to develop methods that help experts to make sense of the continuously growing body of literature, in order to increase the speed and reliability of knowledge discovery.
In response to the above, text mining (TM) aims to automate the above process, by finding relations (such as interactions) that hold between concepts of different types (e.g., genes/proteins, chemical compounds, metabolites, subcellular components, anatomical entities, organisms, cell lines, strains, diseases). A large number of TM methods aim to extract simple binary relations from e.g., A binds B. This is mainly achieved by focusing on textual co-occurrences, using bag-of-words approaches, analysis of controlled vocabulary metadata, and other shallow techniques. However, these approaches have several disadvantages, including the identification of many false positive relations. Additionally, they fail to take into account contextual information about relations, e.g., the cellular context of a signaling event, such as cell type and localization.
able to capture detailed information about mechanisms of biological pertinence, e.g.,, reactions such as negative regulation, phosphorylation, carboxylation), by linking together interacting participants, which play specific roles (e.g., modifier, reactant, product, cause, location). As such, they are able to encode several types of contextual information, that are frequently missing when only binary relations are considered.
Consider an intuitive example from the literature to explain our goal: The results suggest that the narL gene product activates the nitrate reductase operon. (PMID: 3035558). This sentence provides interpretative information about the reaction between the narL gene product and the nitrate reductase operon, namely that the information stated in based on an analysis/interpretation of experimental results, and that there is a certain amount of speculation expressed towards the reaction (according to the use of the verb suggest, rather than a more definite verb, such as demonstrate). Next, consider a more complex example: The analysis showed that IEXC29S was unable to significantly transactivate the c-sis/PDGFB promoter. Whilst a conventional TM analysis to find binary relationships would simply discover that some type of interaction occurs between IEXC29S and csis/PDFG-B, a more detailed contextual analysis would allow the construction of a representation that encodes the complex details of the interaction, e.g., that the information is stated based on an experimental analysis, and that the interaction has been shown to occur with a low level of intensity. .
In order to extract such complex events
automatically, we have developed a pipeline-based event
extraction system, EventMine [
EventMine utilises a rich set of features including
those obtained from dependency parse trees supplied by
the GENIA Dependency Parser [
The automatic extraction of events from biomedical text has a broad range of applications, which include not only support for the creation and annotation of pathways [8], but also automatic population/enrichment of databases and semantic search systems. To develop systems that are customized for different tasks such as the above, a text mining infrastructure is needed, which is able to support the curation and maintenance of pathways, sharing and re-using of knowledge distributed over thousands of scientific publications and monitoring of recent publications is needed to maintain relevance. To foster adaptability of TM solutions, we are using our UIMA based Argo platform [9], which enables the development of highly customisable solutions in the form of reconfigurable modular text mining pipelines (workflows). Apart from supporting the straightforward integration of application-specific components, reconfigurable workflows allow for discovery of optimal solutions [10] owing to their interchangeable underlying components. For components to be interoperable (i.e., for one component to build on the text annotations created by another), the outputs of a predecessor component must be type-compatible with the inputs expected by a successor. In Argo, this is ensured by mechanisms that support mapping between similar semantic types and conversion of annotations [11].
Argo has supported the development of systems such as PathText21, an integrated search system that links biological pathways with supporting knowledge in the literature [8]. It reads formal pathway models (represented in the Systems Biology Markup Language (SBML) and converts them into queries that are submitted to three semantic search systems operating over MEDLINE, i.e., KLEIO, which improves and expands on standard literature querying with semantic categories and facetted search, FACTA+ (see below) and MEDIE (http://www.nactem.ac.uk/medie/), which extracts events. MEDIE has been found to achieve the highest hit ratio, which demonstrates the superiority of events for finding relevant interactions.
FACTA+2 [12] discovers hidden, previously unknown associations between both concepts and complex events from the literature (such as Gene expression, Positive regulation, Binding, Regulation, etc.). Such associations can often only be found by linking information that may be dispersed across many documents, and thus which might be missed using manual search methods. This facilitates hypothesis generation, which is directly relevant to pathway construction. FACTA+ approaches the problem of automatic discovery of useful hypotheses by combining two (or more) known associations, i.e., if concept X is associated with concept Y and concept Y is associated with concept Z, then the potential indirect association between X and Z is considered as a useful hypothesis unless there is already a known association between X and Z. FACTA+ supports the discovery of indirect associations based not only on concepts but also on complex events such as Gene expression, Positive regulation, Binding, Regulation, etc.
support pathway curation, validation and maintenance. Their employment yields improved coverage, faster acquisition and throughput, combined with easier identification and normalisation of duplicates, greater consistency, completeness and accuracy in description, and reduced curator burden. This helps to free experts from mundane and tedious tasks while aiding with more intellectually challenging ones.