Annotations of clinical trials with controlled vocabularies of drugs and diseases, encode scienti c knowledge that can be mined to discover relationships between scienti c concepts. We present PAnG (Patterns in Annotation Graphs), a tool that relies on dense subgraphs, graph summarization and taxonomic distance metrics, computed using the NCI Thesaurus, to identify patterns.
Linked Open Data has made available a diversity of collections and can facilitate scientists to mine semantically annotated datasets. These annotations represent scienti c knowledge, for example, genes, proteins, drugs and diseases are annotated with controlled vocabulary terms (CV terms) from ontologies. Annotations describe properties of these concepts, and they are useful as a basis for focused literature review, and further, to plan a wet-lab experiment or a clinical trial. Annotation graphs as well as the ontologies are rich and complex, for example, the NCI Thesaurus version 12.05d has 93,788 terms. Thus, the challenge is to explore the potentially large number of annotations and to discover patterns. Automatic techniques and tools are therefore needed to support the scientist. These tools could range from making simple but valuable link predictions, e.g., predicting new gene functional annotation, to discovering complex patterns of annotation across multiple disease conditions and drug interventions.
We present PAnG (Patterns in Annotation Graphs), a tool that allows
scientists to identify patterns in annotated graph datasets. PAnG is based on
a complementary methodology of graph summarization (GS) and dense
subgraphs (DSG) [
Further, the pattern captures semantic knowledge not only about individual nodes and their connections, but also about groups of related nodes. LinkedCT (LinkedCT.org) is a Linked Open Data dataset from the clinical trial site (ClinicalTrial.gov). Conditions represent diseases and are typically described using the NCI Thesaurus. Interventions include a (unique) name, a description and a type, e.g., a drug, device, procedure, etc. PAnG for LinkedCT.org is available at http://pang.umiacs.umd.edu/iswc2012demo. 2
Figure 1 illustrates the overall work ow of PAnG. The input is a tripartite annotated graph G, and the output is a graph summary. Our work ow consists of two steps. The rst step is optional and deals with the identi cation of dense subgraphs, i.e., highly connected subgraphs of G that are (almost) cliques. The goal is to identify interesting regions of the graph by extracting a relevant subgraph. Graph summarization transforms the graph into an equivalent compact graph representation. Graph summaries are made up of the following elements: (1) supernodes; (2) superedges; (3) deletion and addition edges (corrections). Figure 2 shows the PAnG interface for the LinkedCT annotation graph dataset. A scientist can search on conditions or interventions and create a subset of clinical trials. She can then choose the DSG option, with a threshold for dtax for conditions or interventions or both. She can also skip the DSG option or choose a DSG without a distance restriction. She can also require that the DSG option favor the selection of triplets across the tri-partite graph, or favor the selection of independent doublets across the two bi-partite graphs. Figure 3 presents a possible summary graph. There are 10 supernodes; ve supernodes cluster conditions, four supernodes cluster clinical trials and one supernode clusters the two interventions cyclophosphamide, and Filgrastim. A superedge is a solid edge and occurs between two supernodes. It represents that all nodes in both supernodes are fully connected, for example, the superedge between the supernode with the condition Myelodysplastic Syndromes and the supernode of 4 clinical trials. The summary re ects the basic pattern (structure) of the graph and is accompanied by a list of corrections, i.e., deletions and additions, that express di erences between the graph and its simpli ed pattern. For example, a deletion edge to a condition that occurs within a supernode indicates that the speci c condition was not studied in a particular clinical trial, whereas the conditions within the supernode, without deletion edges, were studied. In Figure 3, the condition Lymphoma (top left-hand supernode) was not studied in the clinical trial NCT00004143 (top middle supernode).
As of September 2011, LinkedCT contains 106,308 trials, 2.7 million entities and
over 25 million RDF triples. We demonstrate two use cases:
Single Drug: We commence with a single drug and create a dataset of all
clinical trials associated with that drug, and all other conditions and interventions
associated with these trials. We use the taxonomic distance metric, dtax [
Drug Family: The NCI Thesaurus is used to explore drug families and their
properties. Starting with Alemtuzumab as an exemplar, we retrieve the
intersection of Monoclonal antibodies and Antineoplastic agents. This creates a dataset
of 12 drugs: Alemtuzumab, Bevacizumab, Brentuximab vedotin, Cetuximab,
Catumaxomab, Edrecolomab, Gemtuzumab, Ipilimumab, Ofatumumab, Panitumumab,
Rituximab, and Trastuzumab. We use the pairwise annotation similarity based on
the set of interventions associated with each drug to select interesting pairs of
drugs[