Mountain View
biomedical and healthCAre Data Discovery Index Ecosystem
help Advanced Search
Title: iTextMine      
aggregation:
digital object
privacy:
not applicable
refinement:
uncurated
ID:
http://clould1.proteininformationresource.org/demo/integrate
storedIn:
Multiple: Amazon Web Services, IBM
availability:
Available
creators:
Protein Information Resource
keywords:
text-mining, relation extraction, text annotation, knowledge integration
description:
iTextMine is an Integrated Text Mining System for Large Scale Knowledge Extraction from Literature. The system employs parallel processing for dockerized text mining tools with a common JSON output format, and implements a text alignment algorithm to align entity offsets in the text for result integration. The system currently contains four in-house developed relation extraction tools for phosphorylation, phosphorylation-dependent PPI, miRNA-gene regulation, and gene-disease-drug-response relations. We have processed all Medline abstracts for the four tools. A website is built to allow users to browse the text evidence and view integrated results for knowledge discovery through a network visualization.
types:
Computational
authors:
Jia Ren, Peter McGarvey, Shruti Rao, Gang Li, K. Vijay-Shanker, Subha Madhavan, Cathy H. Wu
publicationVenue:
Database
title:
iTextMine: Integrated Text-mining System for Large-Scale Knowledge Extraction from Literature.
name:
CreativeCommons BY-NC-SA 4.0 (Attribution-NonCommercial-ShareAlike 4.0 International) license
landingPage: https://creativecommons.org/licenses/by-nc-sa/4.0/
identifier:
U01GM120953
funders:
National Institutes of Health
identifier:
U01HG008390
funders:
National Institutes of Health
count:
1
unit:
MB
ID:
SCR:016270
name:
CEDAR Workbench
abbreviation:
CEDAR
homePage: https://cedar.metadatacenter.org

Feedback?

If you are having problems using our tools, or if you would just like to send us some feedback, please post your questions on GitHub.