| Research interests |
| We have focused on developing innovative computational methods to understand mechanisms of protein function and related diseases. Our approaches are highly interdisciplinary in nature combining statistical data mining algorithms and 3D molecular modeling techniques. We also apply cutting-edge computational technologies to various drug discovery and protein engineering projects. To successfully achieve goals of our research, we have world-class computational facility including 64bit linux workstations, latest versions of commercial modeling software, subscription of commercial databases, in-house library of drug-like compounds and numerous in-house computational tools for bioinformatics and cheminformatics analyses. |
| |
| 1. Machine learning algorithms for biological sequence analysis |
| |
| ex) CSSP2 algorithm to detect disease-related amyloidogenic sequences |
| 2. Computer-aided drug discovery |
|  |
| ex) Application of Bayesian classifier for high-throughput virtual compound screening |
| 
|
| ex) Integrated knowledge-based approach for CADD |
| 3. Unique gene-specific profiling of microarray data for the discovery of nobel biomarkers |
| 
|
| ex) GS-LAGE, Development of new mining tool for NCBI GEO gene epxression data |
| 4. In silico protein engineering |
|  |
| ex) Computational optimization of protein sequences for therapeutic applications |
