XTractor Knowledgebase

Category Cross-Omics>Knowledge Bases/Databases/Tools and Cross-Omics>Data/Text Mining Systems/Tools

Abstract XTractor™ is a free scientific literature knowledge base (KB) and alert service based on Web 2.0 technology, for biomedical data analysis, collaboration and providing manually annotated relationships regularly on Proteins, Diseases, Drugs and Biological Processes published in PubMed every day.

XTractor™ is highly accurate and more efficient than many of the Natural Language Processing (NLP) engines, since it is a ‘hybrid model’ using technology and manual validation.

Since the annotation is highly accurate researchers can also perform complex queries and retrieve some of the most complex relations available in literature, which is currently Not possible with the conventional NLP systems.

In addition to this, XTractor™ acts as a platform for data sharing and categorization.

The Data behind XTractor comes from manual annotation, which is carried out by qualified scientists from this manufacturer.

The manufacturer's scientists regularly handpick and annotate the most relevant sentences to public ontologies. Each of the data points is quality checked to ensure the highest levels of data accuracy.

The extracted facts are also referenced back to the PubMed abstract(s).

The sentences in XTractor are also manually categorized into nine (9) definite categories such as, Gene - Gene relationships, Gene-Disease relationships, Knockout/Knockdown studies, Mutation studies, Gene - Drug interactions, Gene - Biological Process, Biomarker - Disease correlations, Drug - Disease and Pathway studies.

These mappings help the researcher to draw inferences from the enormous data heap that gets processed everyday.

XTractor feature highlights include:

1) Accurate manually annotated sentences of the researcher’s choice of proteins, diseases, drugs and Biological processes.

2) Regular E-mail alerts on scientific literature updates within a week of publication.

3) An option for changing key words with changing research preferences.

4) Tracking scientific topics of interest.

5) Annotated sentences and abstracts are saved and stored in the researcher’s profile when they get updated in PubMed.

6) Access to stored data - anytime, anywhere (via the Web).

7) Sharing, collaborating and tagging of scientific data into customized datasets.

8) Classifying tags and creating personal data sets/databases of annotated facts.

9) An enhanced experience in reading and analyzing literature.

10) The discovery and creation of newer relations from scientific facts classified by the XTractor™ Community.

11) The addition of approx. 600 relationships/sentences, on an average to XTractor™ everyday.

XTractor™ New Unique Feature – ‘Insta Search’ enables you to get an instant snapshot of XTractor content for entities of your choice. It is a quicker way to decide on the queries that need to be added in XTractor.

XTractor Knowledgebase Statistics --

The Knowledgebase currently contains:

The total Facts / Relationships in XTractor Knowledgebase are as follows:

The categorized Relationships Statistics in XTractor Knowledgebase are as follows:

System Requirements

Contact manufacturer.

Manufacturer

Manufacturer Web Site XTractor Knowledgebase

Price Contact manufacturer.

G6G Abstract Number 20358

G6G Manufacturer Number 104008