Background The flavor theory of Chinese herbal medicines (CHMs) is one of the core theories of traditional Chinese medicine (TCM). Accurate flavor identification of CHMs is essential to guide the clinical application of CHMs. Objective To develop a new method for flavor identification of CHMs according to ingredient information of CHMs. Methods It was found that the chemical basis of medicinal flavors was CHM ingredients. We developed a bitter-pungent flavor identification scheme to build a relationship between medicinal flavors and CHM ingredients. We firstly proposed a scientific hypothesis that “CHMs with similar flavors should have similar chemical basis”. To test this scientific hypothesis, we then explored an intelligent algorithm for bitter-pungent flavor identification of CHMs based on the information similarity of CHM ingredients. Gas chromatography (GC) was used to separate the chemical ingredients of CHMs and analyze the ingredient information of CHMs. A distance metric learning algorithm was built to measure the similarity of GC chemical fingerprints. A bitter-pungent flavor identification scheme (BPFI) was proposed to predict the bitter-pungent flavor of CHMs. Finally, a number of experiments were built to evaluate the identification performance of our scheme. Results Comparing with classical algorithms, our proposed BPFI scheme has better flavor prediction performance. The total identification accuracy of our BPFI scheme reached 0.843. The area under ROC curve (AUC) is 0.899. Conclusions The experimental results confirmed our inference that the chemical basis of CHM flavors was CHM ingredients, and implied that CHMs with similar flavors had similar composition of substances. The BPFI model was proved to be effective and feasible. Highlights To construct a flavor identification model for analysis of bitter-pungent flavor of CHMs according to ingredient information of CHMs.

中文翻译：

---

基于中药材成分信息相似度的苦辛味鉴别

研究背景中药味学说是中医学的核心理论之一。中药风味的准确鉴定对于指导中药的临床应用至关重要。目的根据中药成分信息，建立中药风味鉴别新方法。方法发现药用香料的化学基础是中药成分。我们开发了苦辣味识别方案，以建立药用风味与中药成分之间的关​​系。我们首先提出了“相似口味的中药应该具有相似的化学基础”的科学假设。为了验证这一科学假设，我们探索了一种基于中药成分信息相似度的中药苦辛味智能识别算法。采用气相色谱法(GC)分离中药化学成分并分析中药成分信息。建立了距离度量学习算法来测量GC化学指纹的相似性。提出了苦辣味识别方案（BPFI）来预测中药的苦辣味。最后，进行了一些实验来评估我们方案的识别性能。结果与经典算法相比，我们提出的BPFI方案具有更好的风味预测性能。我们的BPFI方案的总识别精度达到了0.843。ROC 曲线下面积 (AUC) 为 0.899。结论 实验结果证实了中药香精的化学基础是中药成分的推断，暗示香精相似的中药具有相似的物质组成。实践证明BPFI模型是有效、可行的。研究亮点根据中药成分信息，构建中药苦辛味风味识别模型。