Rapid advancing computational technologies have greatly speeded up the development of computer-aided drug design (CADD). Recently, pharmaceutical companies have increasingly shifted their attentions toward traditional Chinese medicine (TCM) for novel lead compounds. Despite the growing number of studies on TCM, there is no free 3D small molecular structure database of TCM available for virtual screening or molecular simulation. To address this shortcoming, we have constructed TCM Database@Taiwan (http://tcm.cmu.edu.tw/) based on information collected from Chinese medical texts and scientific publications. TCM Database@Taiwan is currently the world's largest non-commercial TCM database. This web-based database contains more than 20,000 pure compounds isolated from 453 TCM ingredients. Both cdx (2D) and Tripos mol2 (3D) formats of each pure compound in the database are available for download and virtual screening. The TCM database includes both simple and advanced web-based query options that can specify search clauses, such as molecular properties, substructures, TCM ingredients, and TCM classification, based on intended drug actions. The TCM database can be easily accessed by all researchers conducting CADD. Over the last eight years, numerous volunteers have devoted their time to analyze TCM ingredients from Chinese medical texts as well as to construct structure files for each isolated compound. We believe that TCM Database@Taiwan will be a milestone on the path towards modernizing traditional Chinese medicine.

MGraphDTA is designed to capture the local and global structure of a compound simultaneously for drug–target affinity prediction and can provide explanations that are consistent with pharmacologists.

The prediction of drug-target affinity (DTA) plays an increasingly important role in drug discovery. Nowadays, lots of prediction methods focus on feature encoding of drugs and proteins, but ignore the importance of feature aggregation. However, the increasingly complex encoder networks lead to the loss of implicit information and excessive model size. To this end, we propose a deep-learning-based approach namely FusionDTA. For the loss of implicit information, a novel muti-head linear attention mechanism was utilized to replace the rough pooling method. This allows FusionDTA aggregates global information based on attention weights, instead of selecting the largest one as max-pooling does. To solve the redundancy issue of parameters, we applied knowledge distillation in FusionDTA by transfering learnable information from teacher model to student. Results show that FusionDTA performs better than existing models for the test domain on all evaluation metrics. We obtained concordance index (CI) index of 0.913 and 0.906 in Davis and KIBA dataset respectively, compared with 0.893 and 0.891 of previous state-of-art model. Under the cold-start constrain, our model proved to be more robust and more effective with unseen inputs than baseline methods. In addition, the knowledge distillation did save half of the parameters of the model, with only 0.006 reduction in CI index. Even FusionDTA with half the parameters could easily exceed the baseline on all metrics. In general, our model has superior performance and improves the effect of drug–target interaction (DTI) prediction. The visualization of DTI can effectively help predict the binding region of proteins during structure-based drug design.