Journal of Chemical Information & Computer Sciences
Introduction to Information Retrieval
Introduction to Information Retrieval
Hi-index | 0.00 |
Chemical structural formulas are commonly used for presenting the structural and functional information of organic chemicals. Searching for chemical structures with similar chemical properties is highly desirable especially for drug discovery. However, structural search for chemical formulas is a challenging problem as chemical formulas are highly symbolic and spatially structured. In this paper, we propose a new approach for chemical feature extraction and retrieval. In the proposed approach, we extract four types of functional features from Chemical Functional Group (CFG) Graph built from a chemical structural formula, and use them for the first time for chemical retrieval. The extracted chemical functional features are then used for similarity measurement and query retrieval. The performance evaluation shows that the proposed approach achieves promising accuracy and outperforms a state-of-the-art method for chemical retrieval.