To ensure that CTD biocurators review only those articles that are most likely to yield curatable information within the context of CTD's structured curation paradigm, staff assessed the feasibility and potential advantages of implementing a text-mining pipeline (11).
From the client side, implementing a text-mining pipeline that integrates Web service-based calls to external NER tool providers certainly cedes some control of the pipeline to the Web service providers, and introduces the inherent risk of reliance on third parties.
We implemented a text message-based Short Message Service computer-assisted self-interviewing (SMS-CASI) system to aid adherence and monitor behavior in MTN-017, a phase 2 safety and acceptability study of rectally-applied reduced-glycerin 1% tenofovir gel compared to oral emtricitabine/tenofovir disoproxil fumarate tablets.
Our objectives as we initiated this software search were first to identify, then implement a text mining solution that could minimize this bottleneck.
An earlier study [ 34] implemented a text categorisation method using a machine-learning technique for the purpose of automatically categorising pathology reports solely on their content, which has demonstrated very good performances.
In order to populate the links between antibodies and publications, we implemented a text mining assisted (semiautomatic) curation process inside of the DOMEO tool, because manual curation of antibody information from publications is tedious, but in most cases, quite necessary.
Fttss is a research project (http://fttss.sourceforge.net) that implements a Text-To-Speech System based on PHP (4.3.0 or newer) and MySQL (4.1.2 or newer).
CTD has already successfully developed and implemented a text-mining algorithm that ranks selected articles with respect to relevant data content for any particular chemical-of-interest (8).
Recently, Zhou and his co-workers [16] designed and implemented a chemistry text hybrid search engine to combine both chemistry text and structure searching in literature.
In addition, we implemented a full text parser of the Elsevier articles using the lxml.etree library [ 71].
