Mutation impact extraction is a hitherto unaccomplished task in state of the art mutation extraction systems.
The use of the impact ontology facilitates advanced queries and impact extraction.
We analyzed the performance of our approaches for mutation series and impact extraction in detail on different corpora.
For the purpose of mutation impact extraction we recognize relations between directionality words and protein properties which, taken together as a triple, constitute impact statements.
Second, the effectiveness of the impact extraction, as well as grounding to the correct mutation, is measured on literature describing enzymes.
NN designed the impact extraction and grounding rules, implemented the system, contributed to the ontology design, annotated the documents, and performed the evaluation.
Then, the effectiveness of the impact extraction, as well as grounding to the correct mutation is measured on literature describing enzymes.
The dedicated infrastructure we have developed for fully automated mutation impact extraction from unstructured text has a respectable level of precision of 0.86, albeit with moderate recall.
We address the problem of access to legacy mutation data in unstructured form through the creation of novel mutation impact extraction methods which are evaluated on a corpus of full-text articles on haloalkane dehalogenases, tagged by domain experts.
Mutants containing more than one point mutation were split so that each mutation was considered as one mutant, this was made to better evaluate the impact extraction task without interference from the variety of ways to describe mutants.
To evaluate the methods of mutation grounding and impact extraction a gold standard corpus was built as an extension to the corpus used by [ 5] containing documents about haloalkane dehalogenases.
