Search

Objective The recent surge in large language models (LLMs) across various fields has yet to be fully realized in traditional Chinese medicine (TCM). This study aims to bridge this gap by developing a large language model tailored to TCM knowledge, enhancing its performance and accuracy in clinical reasoning tasks such as diagnosis, treatment, and prescription recommendations. Materials and Methods This study harnessed a wide array of TCM data resources, including TCM ancient books, textbooks, and clinical data, to create 3 key datasets: the TCM Pre-trained Dataset, the Traditional Chinese Patent Medicine (TCPM) Question Answering Dataset, and the Spleen and Stomach Herbal Prescription Recommendation Dataset. These datasets underpinned the development of the Lingdan Pre-trained LLM and 2 specialized models: the Lingdan-TCPM-Chat Model, which uses a Chain-of-Thought process for symptom analysis and TCPM recommendation, and a Lingdan Prescription Recommendation model (Lingdan-PR) that proposes herbal prescriptions based on electronic medical records. Results The Lingdan-TCPM-Chat and the Lingdan-PR Model, fine-tuned on the Lingdan Pre-trained LLM, demonstrated state-of-the art performances for the tasks of TCM clinical knowledge answering and herbal prescription recommendation. Notably, Lingdan-PR outperformed all state-of-the-art baseline models, achieving an improvement of 18.39% in the Top@20 F1-score compared with the best baseline. Conclusion This study marks a pivotal step in merging advanced LLMs with TCM, showcasing the potential of artificial intelligence to help improve clinical decision-making of medical diagnostics and treatment strategies. The success of the Lingdan Pre-trained LLM and its derivative models, Lingdan-TCPM-Chat and Lingdan-PR, not only revolutionizes TCM practices but also opens new avenues for the application of artificial intelligence in other specialized medical fields. Our project is available at https://github.com/TCMAI-BJTU/LingdanLLM. [ABSTRACT FROM AUTHOR]

Phenolic acids are the major secondary metabolites and significant bioactive constituents of the medicinal plant Salvia miltiorrhiza. Many enzyme-encoding genes and transcription factors involved in the biosynthesis of phenolic acids have been identified, but the underlying post-translational regulatory mechanisms are poorly understood. Here, we demonstrate that the S. miltiorrhiza Kelch repeat F-box protein SmKFB5 physically interacts with three phenylalanine ammonia-lyase (PAL) isozymes and mediates their proteolytic turnover via the ubiquitin-26S proteasome pathway. Disturbing the expression of SmKFB5 reciprocally affected the abundance of SmPAL protein and the accumulation of phenolic acids, suggesting that SmKFB5 is a post-translational regulator responsible for the turnover of PAL and negatively controlling phenolic acids. Furthermore, we discovered that treatment of the hairy root of S. miltiorrhiza with methyl jasmonate suppressed the expression of SmKFB5 while inducing the transcription of SmPAL1 and SmPAL3. These data suggested that methyl jasmonate consolidated both transcriptional and post-translational regulation mechanisms to enhance phenolic acid biosynthesis. Taken together, our results provide insights into the molecular mechanisms by which SmKFB5 mediates the regulation of phenolic acid biosynthesis by jasmonic acid, and suggest valuable targets for plant breeders in tailoring new cultivars. [ABSTRACT FROM AUTHOR]

Danshensu, as the effective component of Salvia miltiorrhiza (Danshen), has been widely used in clinical studies for treatment of cardiovascular diseases in China. A new metabolite, 4-hydroxy-3-methoxyphenyllactic acid was isolated from the urine of rats, and its chemical structure was identified by ultraviolet (UV), Infrared Spectroscopy (IR), mass spectrometry (MS) and nuclear magnetic resonance (NMR). Furthermore, a selective and sensitive high performance liquid chromatography-tandem mass spectrometric (HPLC-MS/MS) method was developed for the simultaneous quantification of danshensu and its major metabolite, 4-hydroxy-3-methoxyphenyllactic acid, in rat plasma after oral and intravenous administration of danshensu. The separation was performed on a Hypersil Gold C18 column (150 × 2.1 mm i.d., 3.0 µm, Thermo, San jose CA, USA) with gradient elution using a mobile phase composed of methanol and water (containing 0.1% formic acid) at a flow rate of 0.2 mL/min. Linear detection responses were obtained for danshensu and 4-hydroxy-3-methoxyphenyllactic acid ranging from 5 to 10000 ng/mL and 5 to 4000 ng/mL, respectively. The lower limits of quantification (LLOQs) for the two compounds were both 5 ng/mL. The intra-and inter-day precision (R.S.D %) were within 5.61% for the two analytes. The average recoveries of the analytes were greater than 72.43%. The method was proved to be stable during all sample storage, preparation and analytic procedures. This method was successfully applied to the pharmacokinetic studies of danshensu and 4-hydroxy-3-methoxyphenyllactic acid after oral and intravenous administration of danshensu in rats.Copyright © 2014 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]