My research concerns the searching and data mining of huge volumes of public chemical and biological information contained in databases, generated by computational tools, and contained in journal articles and web documents. This can be categorized into three main areas: searching and mining public chemical & biological information, searching and mining journal articles and documents, and research on infrastructure to support these tasks.
Searching and Mining Public Chemical & Biological Information
- Aggregate Compound Information Web Services
- High Throughput Predictive Models for PubChem Bioassays
- Network models of Compound, Bioassay and Target information
- Integrated data mining of chemical, biological and genomic information
- Prediction of Protein Function by Protein-Ligand Docking Profile
- Accurate Molecular Docking on Huge Datasets
Searching and Mining Journal Articles and Documents
- A chemical structure index for calculating similarity between chemical documents
- Semantic markup of chemistry documents using Natural Language Processing and Ontologies
- Clustering based on chemical structure and ontological markup
Web service infrastructure research
- Developing a web service infrastructure for cheminformatics
- A workflow composition algorithm for automatically generating workflows to handle complex queries
- Extending functionality of web-based cheminformatics resources with Userscripts