PMC

The regular hexagons indicate the sources from which Textpresso is built. The rounded rectangles are either intermediate or final processed parts of the corpus. The dashed-dotted rectangles signify automatic processing units or actions.

A simple retrieval was performed with “let-23” as keyword and “regulation,” “cell or cell group,” and “molecular function” as categories. A total of 245 matches were found in 113 publications.

Sentences from eight journal articles were both queried by Textpresso and evaluated by a human expert for sentences that described genetic interaction (information retrieval task). In the information extraction task, a human expert inspected the sentences returned by each method to determine the amount of distinct gene-gene interactions that could be extracted in order to analyze the output of the first task.

The process of marking up the sentence “In par-1, par-4 and par-3 mutant four-cell embryos, MEX-3 is present at high levels in all cells, indicating that activity of these par genes is required to restrict MEX-3 to the anterior.” This sentence is taken from .
(A) The computer identifies terms that are stored in a lexicon according to categories of the ontology. A text-to-XML converter marks up the terms by enclosing them in XML brackets.
(B) The fully marked-up sentence. Some categories have subcategories (for example, the category “regulation” is subdivided into “positive,” “negative,” and “unknown”). Grammar attributes have been omitted here for the sake of clarity, because they are not used in the current version of the system. Some white spaces have been inserted in the graphics for clarity enhancement.