Our random walk framework results in a ranking of scientific documents which is shown to be more effective in facilitating literature exploration than PageRank measured against a proxy gold standard based on papers' potential usefulness in facilitating later research.
This step may also involve a prioritization or ranking of documents, with documents containing information on novel discoveries (genes, proteins interactions) assigned a higher priority.
Firstly, we assume that the ranking of documents by relevance to a given reaction is independent of other reactions in the pathway, and we consider a single reaction at a time.
Such estimations are typical of document triaging, which is an established task in the realm of text mining (27 29) that involves the ranking of documents according to their curation priority.
Challenge evaluation tasks over the years have included ranking of documents for curation based on presence of curatable information ('document triage'), as well as extraction of genes and proteins from abstracts and articles (6, 7) and their linkage to identifiers in standard biological resources (e.g. Entrez Gene, UniProt) (8 10).
Mr. Paterson's office has long refused to make public key documents in the Aqueduct deal, including a ranking of the various bidders compiled by the State Lottery Division.
Challenge Evaluation tasks over the years have included ranking of relevant documents (document triage), extraction of genes and proteins (gene mention) and their linkage to database identifiers (gene normalization), as well as extraction of functional annotation in standard ontologies (e.g. Gene Ontology (10)) and extraction of entity relations (e.g. protein protein interaction).
Participants in the shared task were not only required to provide an optimized ranking of target documents, but also to deliver other relevant entities (genes, diseases and chemicals) mentioned in each abstract.
A Web search would typically return, say, 5,000,000 results with a very poor ranking of the documents.
