Chemical Structure Reconstruction with chemoCR

chemoCR makes chemical information contained in depictions of chemical structures accessible as connection table for computer programs. In order to solve the problem of recognizing and translating chemical structures in image documents, our chemoCR system combines pattern recognition techniques with supervised machine learning concepts. The method is based on the idea of identifying from structural formulas the most significant semantic entities. Semantic entities are for example chiral bonds, superatoms and reaction arrows. The workflow consists of three phases: image preprocessing, semantic entity recognition, and molecule reconstruction plus validation of the result. All steps of the process make use of chemical knowledge in order to detect and fix errors. The system can be trained and adapted to different sources of input images. The reconstructed connection table can be used by all chemical software. Figure 1: This figure shows the drug azithromycin drawn with two different structural editors. The drawn molecules are identical but the images are quite different.