Tensor decomposition: new strategy for deciphering mechanism of precision medicine for same treatment of different diseases / 中国中药杂志

The aging society has led to a substantial increase in the number of clinical comorbidities. To meet the needs of comorbidity treatment, polypharmacy is widely used in clinical practice. However, polypharmacy has drawbacks such as treatment conflict. Same treatment of different diseases refers to treating different diseases with same treatment. Therefore, the principle of same treatment of different diseases can alleviate the problems caused by polypharmacy. Under the research background of precision medicine, it becomes possible to explore the mechanism of same treatment of different diseases and achieve its clinical application. However, drugs successfully developed in the past have revealed shortcomings in clinical use. To better interpret the mechanism of precision medicine for same treatment of different diseases, under the multi-dimensional attributes including dynamic space and time, omics was performed, and a new strategy of tensor decomposition was proposed. With the characteristics of complete data, tensor decomposition is advantageous in data mining and can fully grasp the connotation of precision treatment of different diseases with same treatment under dynamic spatiotemporal changes. This method is used for drug repositioning in some biocomputations. By taking advantage of the dimensionality reduction of tensor decomposition and integrating the dual influences of time and space, this study achieved accurate target prediction of same treatment of different diseases at each stage, and discovered the mechanism of precision medicine of same treatment for different diseases, providing scientific support for precision prescription and treatment of different diseases with same treatment in clinical practice. This study thus conducted preliminary exploration of the pharmacological mechanism of precision Chinese medicine treatment.

A review of drug knowledge discovery using BioNLP and tensor or matrix decomposition

Prediction of the relations among drug and other molecular or social entities is the main knowledge discovery pattern for the purpose of drug-related knowledge discovery. Computational approaches have combined the information from different resources and levels for drug-related knowledge discovery, which provides a sophisticated comprehension of the relationship among drugs, targets, diseases, and targeted genes, at the molecular level, or relationships among drugs, usage, side effect, safety, and user preference, at a social level. In this research, previous work from the BioNLP community and matrix or tensor decomposition was reviewed, compared, and concluded, and eventually, the BioNLP open-shared task was introduced as a promising case study representing this area.