Mode of access: World Wide Web.

System requirements: Adobe Acrobat Reader.

Part of: Synthesis digital library of engineering and computer science.

Includes bibliographical references (pages 113-129).

1. Introduction -- 1.1 Background -- 1.2 Data representation in the Semantic Web -- 1.3 Data query, management, and integration -- 1.4 Knowledge discovery in semantically integrated datasets -- 1.5 Chem2Bio2RDF --

2. Data representation and integration using RDF -- 2.1 Background -- 2.2 Methods -- 2.3 Discussion -- 2.4 Conclusion --

3. Data representation and integration using OWL -- 3.1 Introduction -- 3.2 System and methods -- 3.3 Implementation -- 3.4 Use cases -- 3.5 Discussion -- 3.6 Conclusion --

4. Finding complex biological relationships in PubMed articles using Bio-LDA -- 4.1 Introduction -- 4.2 Materials and methods -- 4.2.1 Databases -- 4.2.2 Bio-LDA -- 4.3 Experimental results -- 4.3.1 Analyzing the Bio-LDA model results -- 4.3.2 Comparing the Bio-LDA and LDA models -- 4.3.3 Identification of bio-term relationships within topics -- 4.3.4 Discovery of bio-term associations -- 4.4 Application tools -- 4.4.1 Literature Association Score Calculator (LASC) -- 4.4.2 Associated Bio-Terms Finder (ABTF) -- 4.5 Conclusion --

5. Integrated semantic approach for systems chemical biology knowledge discovery -- 5.1 Introduction -- 5.2 Datasets -- 5.3 Methods -- 5.3.1 Association prediction -- 5.3.2 Association search -- 5.3.3 Association exploration -- 5.3.4 Connectivity-map generation -- 5.3.5 Chem2Bio2RDF extension -- 5.4 Application tools -- 5.4.1 Association predictor -- 5.4.2 Association searcher -- 5.4.3 Association explorer -- 5.5 Use cases -- 5.5.1 Identifying potential drugs for a target -- 5.5.2 Investigating drug polypharmacology using association search -- 5.5.3 Building a disease-specific drug-protein connectivity map -- 5.5.4 Association search for discovery compounds -- 5.6 Conclusion --

6. Semantic link association prediction -- 6.1 Introduction -- 6.2 Materials and methods -- 6.2.1 Network building -- 6.2.2 Drug target pair preparation -- 6.2.3 Path finding -- 6.2.4 Statistical model -- 6.2.5 Model evaluation -- 6.2.6 Assess drug similarity -- 6.3 Results -- 6.3.1 Semantic linked data -- 6.3.2 Pattern score distribution -- 6.3.3 Pattern importance -- 6.3.4 Association scores of drug target pairs -- 6.3.5 Comparison with connectivity maps -- 6.3.6 Assessing drug similarity from biological function -- 6.4 Web services -- 6.5 Discussion --

7. Conclusions -- References -- Authors' biographies.

Abstract freely available; full-text restricted to subscribers or individual document purchasers.

Compendex

INSPEC

Google scholar

Google book search

The current drug development paradigm, sometimes expressed as, "one disease, one target, one drug," is under question, as relatively few drugs have reached the market in the last two decades. Meanwhile, the research focus of drug discovery is being placed on the study of drug action on biological systems as a whole, rather than on individual components of such systems. The vast amount of biological information about genes and proteins and their modulation by small molecules is pushing drug discovery to its next critical steps, involving the integration of chemical knowledge with these biological databases. Systematic integration of these heterogeneous datasets and the provision of algorithms to mine the integrated datasets would enable investigation of the complex mechanisms of drug action; however, traditional approaches face challenges in the representation and integration of multi-scale datasets, and in the discovery of underlying knowledge in the integrated datasets. The Semantic Web, envisioned to enable machines to understand and respond to complex human requests and to retrieve relevant, yet distributed, data, has the potential to trigger system-level chemical-biological innovations. Chem2Bio2RDF is presented as an example of utilizing Semantic Web technologies to enable intelligent analyses for drug discovery.

Also available in print.

Title from PDF title page (viewed on November 20, 2014).