| タンパク質化合物相互作用の網羅的予測手法とデータベースの開発
|
| | | Since tens of millions of chemical compounds have been accumulated in public chemical databases such as PubChem, fast comprehensive computational systems to predict interactions between chemical compounds and proteins are demanded for virtual screening of lead compounds. We have implemented a software system COPICAT for predicting protein-chemical interaction using two-layer Support Vector Machine (SVM) classifiers. Further, COPICAT Web System performs a prediction job against database which receives user compound or protein data as a query and returns prediction results against all molecules in one of system-side databases. Our fast and accurate in silico virtual screening system, COPICAT, enhances lead compound discovery against tens of millions of chemical compounds, implying that the search space for drug discovery is extended by more than 1,000 times compared with currently well-used high-throughput screening methodologies. | | | |