Hypothesis generation in the life sciences is an empirical process in which obtaining and structuring knowledge from literature plays a significant role. Text mining and Information Extraction techniques are seen as key for programmatically accessing the knowledge captured in the form of free text. We describe progress towards an application that supports the task of generating a hypothesis about biomolecular mechanisms using Semantic Web technologies and a workflow to carry out text mining in a service-oriented architecture. The output is a semantic model with putative biological relationships that have been extracted from literature, with each relationship linked to the corresponding evidence. We present preliminary data that extends a model for chromatin (de)condensation. The methodology can be used to bootstrap the process of human-guided construction of semantically rich biological models using the results of knowledge extraction processes.
implies integration of various types of information and distillation into a comprehensible model. This includes information from literature, our own knowledge, and interpretations of experimental data. Many Web resources such as Entrez PubMed1 provide such information. However, the difficulty of information retrieval from literature reveals the scale of today’s information overload: over 17 million biomedical documents are now available from PubMed. Support for extracting information from these resources is therefore a general requirement, with many scientists finding it increasingly challenging to ensure that all potentially
relevant facts are considered whilst forming a hypothesis. Developments in the area of
information extraction promise to deliver applications that will more directly support
the task of hypothesis generation. The general approach requires retrieving relevant
documents, recognizing named entities (e.g. proteins) and their relationships, and
storing results for later inspection [
In this study, we address the question of how the results of a knowledge extraction procedure should be stored to best support hypothesis conception for experimental biology. In particular, we focus on epigenetics and chromatin research, where typical examples are qualitative hypothetical models that attempt to explain the role of various proteins in changing the level of condensation of DNA as a means to regulate transcription (see for instance [12]). To support the linking of a knowledge extraction process to this type of modelling, we present an approach that extracts information from text and populates an OWL-based knowledge base with the extraction results. 2
developed for knowledge extraction and knowledge management in a virtual
laboratory for e-science1. It contains services for document retrieval based on Lucene2
[
Query Add query to semantic model log QQDDexp , QDexp Q / N , in which Q, D Retrieve documents from Medline
Atdodsdeomcaunmteicnmtso(dIDels) containing q, d, and q and d; QDexp is the
(Homo sapiens) q and d assuming independence of Q and D; sAedmdapnrtoicteminosdteol N is the total number of documents in ranCkainlcguslactoeres MedLine. The workflow further contains a
Ccrroesasterbefieorloengciceasl semantic model spyronvoindyinmgs UntoiProtthiedenotrifiigeirnsalfor qhuuemryan, arnatd,
Convert to to semantic model positives. This service, kindly provided by
table (html) Martijn Schuemie, wraps components from
Fig. 1 - Workflow to extract proteins from the text analysis tool Anni2.0 [
step in the workflow, the results are converted into OWL instance statements in RDF format in order to populate the ontologies pre-loaded in our knowledge base.
3
In order to represent our biological hypothesis, we would like an OWL ontology of the relevant biological domain entities and their biological relationships. The purpose of our knowledge extraction procedure is to populate this model with instances. We would also like to model the evidence that has led to these instances. This leads to a clash between our intention of enriching a biological model, and representing the artifacts of a text mining procedure such as ‘term’, ‘interaction assertion’, or ‘term collocation’. For these, we have concrete instance but that have no direct meaning in the biological domain. Within our OWL representation, we purposefully kept five distinct OWL models in order to avoid the conflation of knowledge from the different stages of our knowledge extraction process. Our models represent:
Decondensed chromatin HDAC
HAT Histone acetylation Histone methylation at H3K9 DNA methylation Condensed chromatin
Chromatin condensation hypothesis Protein hasParticipant some HDAC1 PCAF hasModelComponent hasModelComponent hasModelComponent hasParticipant hasParticipant
Protein Association HDAC1-PCAF interaction
classes for a biological model with proteins and protein-protein associations (Fig. 3). We cannot directly inspect concrete instances of proteins or their interactions. We regard instances in the biological model as interpretations of certain observations, in our case, of text mining results. We also do not consider such instances as biological facts; they are restricted to a hypothetical model. The evidence for the interpretation is important, but it is not within the scope of this model. In the case of text mining, evidence is modeled by the document and text mining models.
A model of the structure of documents and statements therein is less ambiguous than the biological model, because we can directly inspect concrete instances such as (references to) documents or pieces of text (Fig. 4). We can be sure of the scope of the model and we can be clear about the distinction between classes and instances because we computationally process the documents. For our knowledge extraction experiment, we have created classes for documents, protein or gene terms, and mentions of associations between proteins or genes. Unfortunately, we cannot make a distinction between proteins and genes at this stage due to the limits of biological text mining.
Protein or gene term
PMID: 15298701 “HDAC1” “p68” isComponentOf isComponentOf relates relates isComponentOf Association
term “associate” relatesBy Protein or gene association assertion
Document search query “HDAC1 AND chromatin”
Discovery
score searchesWith 4.78
Text mining
process AIDA based extraction process
Retrieved document
Discovered protein or gene term
PMID: 15298701 discoveredBy “p68”
“interacts” discoveredBy hasDiscoveryScore discoveredBy discoveredBy
Discovered association term
Discovered association assertion text model as text mining discoveries. For clarity, property restrictions between classes and model components of the text mining process are not shown. process instances of documents that contain instances of terms. In addition, in this model we represent information about the likelihood of terms and relationships being found in the literature. We also gain valuable knowledge provenance that can be used to track down any conflicting statements later on. This allows us to qualify the uncertainty of the text mining procedure. For more complete knowledge provenance, we have also created a semantic model representing the implementation of the text mining process as a workflow of (AIDA) Web Services (not shown).
At this point, we have a clear framework for the description of our biological domain and the documents and the text mining results as instances in our document and process ontologies. The next step is to relate the mined information to the biological domain model. Our strategy is to initially keep the domain model simple at the class and object property level, and to map sets of instances from our results to the domain model. For this, we created an additional mapping model that defines reference properties between the models (Fig. 6). We can now see that an interaction between the proteins labeled ‘p68’ and ‘HDAC1’ in our hypothetical model is referred to by a mention of an association between the terms ‘p68’ and ‘HDAC1’, with a likelihood score for finding this combination in literature.
BiologicalModel
references Chromatin condensation hypothesis
Protein or gene
references Association HDAC1-p68 association HDAC1
p68 references Fig. 6 – Mined knowledge mapping strategy. Instances from the results set (right) refer to instances in the domain model (left).
The final result of the knowledge extraction workflow is a knowledge base extended with text mining results captured in OWL. We performed an example experiment starting with the query ‘HDAC1 AND chromatin’. As a result we could query our knowledge base to find an instance of our biological hypothesis model and its partial representation by the input query and its expanded form (35 synonyms were added for document retrieval). We could further find 257 proteins linked to this model as putative components. We could also recover that these links were discovered through 489 protein terms found in 276 documents, and by what process, Web Service and workflow. The data is per individual: for each we stored its specific links to other individuals within a domain (e.g. the biological) and between domains. For instance, NF-KappaB is linked to our initial hypothesis and ‘HDAC1’ within the biological model, and to its associated term which was found in 10 abstracts. As our knowledge base grows with instances and different types of evidence we can perform increasingly interesting queries in search of novel relations with respect to our nascent hypothesis. A prototypical example is the protein referred to by the term ‘p68’ that was found to be collocated with the query term ‘HDAC1’ and also in a direct mention of this interaction in an abstract by Wilson et al. [13], suggesting p68 as a candidate for investigating its role in relation to HDAC1 and chromatin. 5
We have demonstrated first steps towards automating support for the processes
involved in the formation of scientific hypotheses, particularly in studying
biomolecular mechanisms. Text mining supports a researcher by inspecting more
papers than an individual could and without human bias, while the use of an
OWLbased knowledge base supports exploration of semantic relationships of one or many
experiments. Our focus is on modeling information that is extracted during a
computational experiment, rather than on improving a particular text mining
procedure. The approach is not limited to the modeling of text mining results but
could be applied to the results of other computational experiments. Our method shares
some features with the general task of ontology learning from text [