HPIminer - A web Server for Minining Human Protein/gene’s Interactions, Related Interactions and Pathways from Biomedical Literature

About HPIminer

HPIminer is an automated text mining system for visualizing human protein interactions and pathways from biomedical literature. HPIminer uses our three pre-developed tools namely NAGGNER (http://www.biominingbu.org:8080/NAGGNER/), ProNormz (http://www.biominingbu.org/pronormz) and PPInterFinder (http://www.biominingbu.org/ppinterfinder) for human PPI extraction from biomedical literature. The text mining system further uses two databases namely interaction database with 39,141 PPI information and 479 information on interaction of proteins with other non-protein biological entities and pathway database with 20,206 entries on gene-pathways relationships for retrieving PPI. The interaction database includes data curated from HPRD and the pathway database includes curated data from KEGG. The two databases are used for visualizing human PPIs and pathways information from biomedical literature. HPIminer is able to retrieve both known and New PPI information from the biomedical literature.

The input for HPIminer can be a biomedical abstract(s) (plain text/MEDLINE/XML format) or a list of protein names. The corresponding output is the mined PPI information which further gives information on related PPI and pathway based on user selection. Samples inputs are available in the home page. Presence of some special character like Greek letters is not supported by the server.

Team
Dr. Suresh Subramani Dr. Kalpana Raja Dr. Jeyakumar Natarajan
sureshsubramani(at)hotmail.com Professor
     

Publication
Suresh Subramani, Kalpana Raja, Pankaj Moses Monickaraj, Jeyakumar Natarajan. HPIminer - A text mining system for building and visualizing human protein interaction networks and pathways. Journal of Biomedical Informatics. 2015. S1532-0464(15)00008-8. [IF: 2.48] (Indexed PubMed and ScienceDirect)

Data Mining and Text Mining Laboratory,
Department of Bioinformatics,
School of Life Sciences,
Bharathiar University,
Coimbatore - 641 046,
Tamilnadu, INDIA


Acknowledgement

This work has been carried out as a part of the Department of Information Technology (DIT) project entitled "Text Mining and Data Warehousing of Protein Kinases Relationships and Pathways" at Data Mining and Text Mining Laboratory, Department of Bioinformatics, Bharathiar University, Coimbatore, India.