Return to

Drug Discovery Research

DATA MINING

P-Pie

With overwhelming increase in the amount of literature data on genes, proteins and their roles in biological processes, Natural Language Processing (NLP) has emerged as the state-of-the-art technology to filter relevant information from the literature for large-scale drug discovery research. At O2I, we are using NLP for automated text mining to offer as yet untapped opportunity to integrate many fragments of information gathered by researchers from disparate sources into a complete picture exposing the interrelated roles of various genes, proteins and chemical reactions in cells and organisms.

P-Pie is developed to extract protein-protein interaction information from published literature that gets automatically loaded into a relational database and displayed in interactive graphics. An intervening manual step at a logical point in the process ensures removal of the false positives.

DATABASES

DiaBase

(A Database for Drug Discovery Research in Diabetes)

DiaBase is a database approach to conveniently manage biological and structural data for drug discovery research in diabetes. It is an information resource for molecular target based drug discovery research for diabetes. Extensive annotation for the genes and its products are stored in the database. At the core of DiaBase is a comprehensive relational database. The data store contains a variety of pharmaceutically relevant information on the genes and proteins that are implicated in diabetes. The architecture of the database incorporates a gene component, a protein component, 3D structures and a clinical component. Relevant data are mined from disparate public domain sources including scientific literature by curation experts and stored in the database. A user-friendly graphical interface is provided for easy access of information.

IntegrinDB

IntegrinDB is an encyclopedia on integrins with interactive visualizers and exhaustive information. Integrin is a family of transmembrane glycoprotein, which constitutes about 1% of the total drug targets. It addresses the critical discovery steps, from screening, identification to validation of drug targets in the target-focused molecular target based drug discovery research.

The data store in the database contains a variety of information catered to the needs of discovery scientists of the field. The data is seamlessly integrated from disparate sources through XML technology. Key features of this database include data culled by scientific experts from more than 27000 scientific articles, interactive visualizers, user friendly query system and integration of public domain software.

Please contact us here with your outsourcing requirements.