Similarity Measurement Of Chinese Medicine Ingredients For Cold-hot Nature Identification

For more information: emily.li@wecistanche.com

Guo-Hui Wei, Xian-Jun Fu, Zhen-Guo Wang

1Key Laboratory of Theory of TCM, Ministry of Education of China, Shandong University of Traditional Chinese Medicine, Jinan, China.

Highlights

In this study, we verified the hypothesis that Chinese medicines with a similar composition of substances should have similar medicinal nature. We used chemical fingerprints to analyze the chemical ingredients in Chinese medicines. We measured the similarity of ingredients with a distance metric and designed a retrieval scheme to identify the cold-hot nature of Chinese medicines.

Cistanche is a very good Chinese Medicine

Abstract

Objective: Nature theory of Chinese medicine(CM) is the core basic theory of Traditional Chinese Medicine (TCM), in which cold-hot nature is the focus of research. Studies have found that CM ingredients are the material basis for the production of medicine natures. Therefore, it is speculated that CMs with a similar composition of substances should have similar medicinal nature. Modern work studies cold-hot medicine of CMs with chemical fingerprinting technology because the chemical fingerprint data of CM can reflect the whole composition of CM ingredients.

Methods: To verify the hypothesis above, in this work, we study quantifying the similarity of CM ingredients to fingerprint similarity and explore the relationship between the composition of CMs and cold-hot nature. Firstly, we utilize ultraviolet (UV)spectrum technology to analyze 61 CMs, which have clear cold-hot nature (including 30'cold'CMs and 31'hot' CMs). Secondly, with the constructed fingerprint database of CMs. a distance metric learning algorithm is studied to metric the similarity of UV fingerprints. Finally, a retrieval scheme is proposed to build a predictive identification model to identify the cold-hot nature of CMs.

Results: By means of numerous experiment analyses, ultraviolet spectrum data of petroleum ether solvent can better represent CMs to distinguish between cold and hot natures. Compared with existing classical models, the proposed identification scheme has better predictive performance. 

Conclusion: The experimental results prove our inference that CMs with a similar composition of substances should have similar medicinal nature The proposed prediction model is proved to be effective and feasible.

Keywords: Traditional Chinese medicine, Chinese Medicine ingredients, Ultraviolet spectrum, Similarity measurement, Cold-hot nature

Background

As one of the core elements of Traditional Chinese Medicine(TCM), the nature theory of TCM has attracted the attention of scholars and research institutions for many years. The nature of Chinese medicine(CM) contain four types ie. cool, cold, hot, and warm, which cold and hot nature is an important part of TCM nature theory [1,2]." Treating the hot syndrome with cold nature medicine and treating cold syndrome with hot nature medicine" indicates that cold or hot property of medicine nature theory is an important basis for TCM treatment in regulating the balance between Yin and Yang of the human body, and the application of cold-hot medicine nature leads to effective treatment in TCM clinical medicine [3].

Numerous specialists maintain different views on the TCM cold-hot nature. Jin et al.[4] proposed a 'three-element mathematical analysis model to research the biological character of TCM in the basis of cold-hot medicine nature. Zhao et al. [5] explored a cold/hot plate method to differentiate the cold-hot nature of Mahuang and Maxingshigan decoctions. Wan et al.[6] studied the effect of TCM with different properties on thermoregulation and temperature-sensitive transient receptor potentiation channel protein of rats with yeast-induced fever. Liang et al.[7] analyzed the cold and hot properties of Chinese medicinal herbs with molecular network and chemical fragment methods. Wang et al. [8]identified 59 CHMs with typical cold/hot properties by self-organizing map. Fu et al. [9,10] investigated the presence of anticancer activity displayed by the cold-hot nature of traditional Chinese marine medicine with phylogenetic tree analysis and explored in Silico Mode-of-Action method to explain the cold, hot, and neutral nature of CMs.

Generally, the discrimination of the cold-hot nature of CMs contains two parts: feature representation and natural classification. Feature representation uses original effects of CM, fingerprint technology, or metabolomics method to extract the characteristics of CM. Nature classification needs to use classical machine learning classifiers or constructed classifiers to discriminate the cold-hot nature of CMs. The original effects of Chinese medicine are an effective characteristic expression. Xue research group [11-13] explored original efficacy features of CMs in "Chinese Herbal Medicine(CHM)" and used classical classifiers (such as the artificial neural networks) to classify the unknown nature of CMs. The metabolomics method is also used to represent the CMs. Nie et al. [14] studied Metabonomic features of CMs and constructed a random forest model to discriminate the unknown nature of CMs. Chemical technology is an important method for analyzing the cold-hot nature. Long et al. [15] analyzed the chemical components of 284 CMs with clear medical nature and explored a combination system for predicting the cold-hot nature of other CMs, Other methods. such as nuclear magnetic resonance spectroscopy of proton(1H-NMR), are used to investigate the feature of CMs. List al. [16] studied the characteristics of CMs with 1H-NMR and applied pattern recognition techniques to analyze the unknown nature of CMs.

Except for classical classifiers, the retrieval scheme is one of the popular and effective classification schemes, which has been applied widely in identifying benign and malignant Mammography and pulmonary nodules [17-20]. Compared with traditional classifiers, the retrieval scheme can provide the most similar cases for analysis and reference. Therefore, similarity measure plays an important role in the retrieval scheme for classification. Our group has done a lot of research work on similarity measurement of pulmonary nodules images [20,21]. We quantify the similarity of pulmonary nodules images to distance metrics. Although similarity measurement has been widely studied in medical images, it is rarely used in the nature identification of CMs.

The current research of medicine nature focused on revealing the connection of CM nature and material composition within CMs. For example, chemical fingerprinting techniques and CM nature discriminant models are applied to analyze CM material composition. The chemical fingerprint data of CM can reflect the whole composition of CM ingredients. Bioactivity is determined by material composition. and the bioactivities of CMs are the core of identifying medicine nature [2]. Thus, material composition indirectly determines the nature of CMs. Studies have found that CM ingredients are the material basis for the production of medicine natures [10]. Therefore, it is speculated that CMs with a similar composition of substances should have similar medicinal nature.

To verify the hypothesis proposed above, in this work, we explore the relationship between the CM ingredients and cold-hot medicinal nature. Firstly, we construct a CM ingredient database by using ultraviolet (UV) spectrum technology to represent 61 CMs, which have clear cold-hot nature (including 30 'cold' CMs and 31 'hot'CMs). Secondly, we study quantifying the similarity of CM ingredients to a distance metric. Mahalanobis distance is learned to measure the similarity of UV fingerprints of CMs. Finally, a retrieval scheme is proposed to build a predictive identification model to predict the cold-hot nature of CMs.

Materials and Methods

TCM Dataset

61 representative CMs are analyzed in this study, in which 30 CMs are 'cold medicines' and others are 'hot medicines. All the 61 CMs have been marked in the classical 'Chinese Materia Medica'and 'Shen Nong's Herbal Classic'. Table l shows the 61 representative CMs and their natures(characteristics in brackets).

UV fingerprint technology is used to test the 61 CMs. The main instrument is UV-3010 UV Spectrophotometer (Hitachi, Japan). Our group recorded the absorbance of a total of 61 CMs in the ultraviolet wavelength of 190-400nm with four different solvents (chloroform, distilled water, absolute ethanol, petroleum ether). A detailed method for obtaining a UV fingerprint can refer to in the manuscript [25]. As a ‘hot’ medicine, Mustard Seeds have been marked in the classical ‘Chinese Materia Medica’ and ‘Shen Nong’s Herbal Classic’. Figure 1 shows the UV absorption curve of Jiezhi (Mustard Seeds) and GeGen (Puerariae Lobatae Radix) with petroleum ether solvent.

UV Fingerprint Similarity

In this study, we investigate the relationship between the cold-hot nature and the material composition of CMs. To verify the hypothesis, CMs with a similar composition of substances should have similar medicinal nature, we want to quantify the similarity of CM ingredients and explore the method for identifying CM nature. A UV fingerprint reflects the material composition of a CM. Therefore, we want to reveal cold-hot nature based on UV fingerprints. If the ingredients of CMs are similar, we can think that their medicinal properties are similar. Hence, CMs with similar UV fingerprints should have the same medicinal nature.

The similarity measure is defined as semantic relevance, which has been used to measure the similarity of lung nodule images in our study [21]. If two CMs are both cold medicine, they are semantically similar. The Mahalanobis distance is used to measure the similarity of UV fingerprints of CMs. The smaller the Mahalanobis distance, the higher the similarity of UV fingerprints.

Performance Assessment

In this subsection, to verify the feasibility of the proposed retrieval scheme for the identification of cold-hot nature, extensive experiments are constructed to assess the performance of the retrieval scheme. We compare the performance of our scheme with that of the state-of-the-art classification models, including extreme leaming machine(ELM)[24], artificial neural network (ANN), and support vector machine(SVM). All experiments evaluations are on the basis of the existing TCM dataset. The application assists to test the unknown nature of a CM by retrieving similar UV spectra of CMs with clear cold-hot nature. In this study, we firstly compared the nature identification performance of UV spectra with different solvents and selected the solvent corresponding to the optimal identification performance. Secondly, we designed experiments to evaluate the proposed scheme performance, called stability evaluation. Thirdly, we illustrated the retrieval scheme with examples. Finally, an independent dataset is used to test the robustness of the proposed algorithm.

In our experiments, stability evaluation is used to analyze the performance of the proposed prediction model. Stability evaluation is calculated with the leave-one-CM-out method [20] in the whole dataset. Each time, one CM was selected as the query CM and the remaining 60 CMs as the reference database. Because every TCM was selected as the query CM, this process was performed 6ltimes. In this retrieval scheme, we retrieved K'most similar's and then obtained a cold nature probability. At last, 61 probabilities were calculated. With varying the threshold of the 'cold nature probability, a Receiver Operating Characteristic (ROC)curve is generated. The area under the ROC curve(AUC)and prediction accuracy(ACC) are used to evaluate the performance of our scheme. The larger the area, the more stable the model is, ACC value is the probability of correct classification of the cold-hot nature of CMs. The formula of ACC is as follows:

The AUC and ACC value were applied for the stability evaluation.

Results

Performance Evaluation with Different Solvents.

The chemical fingerprints of CMs reflect the material composition of CMs. UV spectra are one fingerprint of CMs, which can be applied to discriminate the cold-hot nature of CMs. In this study, we construct experiments to quantitatively analyze the relationship between material composition and the nature of CMs by means of ultraviolet spectroscopy.

In this work, the classification performance of the UV spectra with different solvents (distilled water. chloroform. petroleum ether, absolute ethanol) was analyzed to select UV data under solvent for optimal recognition performance. The leave-one-CM-out method is used to evaluate the parameters of our scheme. Figure 2 displays the ACC value curves for the medicine nature classification of the UV spectra with different solvents. The ACC value is computed as a function of the number of referenced CMs (K) retrieved to obtain a more comprehensive curve for predicting the performance of the model. In Figure 2, the curve of ACC value under petroleum ether solvent is better than that under other solvents, which means that the UV spectra of petroleum ether solvent have the best discriminant performance of cold-hot nature. When K is set as 7, the curve of ACC value under petroleum ether solvent has a peak. The identification performance reaches the maximal value of 0.803. From the curve of ACC value under absolute ethanol, UV fingerprint with absolute ethanol has the lowest predicting performance. The CM nature identification with distilled water and chloroform is inferior to that with petroleum ether but outperforms that with absolute ethanol solvent. According to the figure, the maximum ACC values of distilled water and chloroform are both 0.656. Therefore, these two solvents are poor for predicting medicine's nature.

In this study, the effect of parameter p in Eg. (4)under petroleum ether solvent is investigated to evaluate the predicting performance of cold-hot nature. The value of er p is set within the range

parameter【10-3，10*²，10'，1，5，10，102，103】1.Figure 3A displays the ACC value curve with different p. It can be concluded that the performance curve has small fluctuations and the ACC value reaches the maximum when parameter p is set as 5.

The number of eigenvectors k in the proposed retrieval algorithm is analyzed within the range [50 100 150 200 210]. From Figure 3B, a higher ACC value can be achieved with an increasing number k. Maximum classification performance (ACC value) corresponds to the maximum number of eigenvectors k=210.

Model Performance Assessment

To demonstrate the feasibility and stability of our proposed retrieval scheme for identifying the cold-hot nature of CMs, this study compares the classification performance of our scheme( the retrieval scheme, denoted as "RS") with that of some classical classifiers (i.e., ANN, SVM, ELM) or classifiers used in CM nature identification. All comparative algorithms use the optimal parameters from the dataset. According to the results of the previous section, the UV spectra data under petroleum ether solvent are used to study the cold-hold nature prediction. Table 2 shows the performance comparison of stability assessment between RS and other algorithms. Pearson correlation coefficient (PCC) is used as a comparative reference to measure the similarity of UV spectra. According to the prediction results of cold-hot nature, we can conclude as follows. Firstly, our scheme RS performs best in the identification of cold-hot nature. Especially, RS and PCC have better identification accuracy than other comparison classical algorithms. This illustrates that Chinese medicines with similar ultraviolet spectrum have similar medicine nature. Secondly, ANN and ELM with UV spectral data are poor in identifying medicine nature.

Thirdly, the identification accuracy of SVM is better than that of ANN and ELM. However, it is poor than our scheme. Finally, the stability assessment of our scheme is the best.

Prediction Examples

The leave-one-out method is used to obtain prediction examples. Two retrieval CM cases returned by RS are listed in Table 3. The query Chinese medicine (first row)and its top k=7 retrieved reference CMs are shown in the table. The retrieved reference CMs are computed by RS and ranked with monotonically incremental Mahalanobis distance. Cold medicine (DiFuZhi(Kochiae Fructus))and hot medicine(BiBa(Piperis Longi Fructus)) are served as examples to illustrate the principle of cold-hot medicine identification. In the first column, the query medicine is Piperis Longi Fructus. Its retrieved reference medicines are all hot nature. The calculated cold nature probability is 0, which indicates that the query medicine maybe be hot nature. In the second column, the query medicine is Kochiae Fructus. The retrieved results have six cold nature medicines and one hot nature medicine. Its cold nature probability is 0.9464, indicating the query medicine is more likely to be cold in nature. The prediction examples demonstrate that similar UV fingerprints can characterize the same medical nature.

Overall Prediction Performance.

In this study, we perform a holistic assessment of the proposed RS method. Table 4 shows the prediction confusion matrix of 61 CMs. The total prediction accuracy is 80.3% (49/61). The identification accuracy of cold nature medicine is 86.7% (26/30), while the prediction accuracy of hot nature medicine is 74.2 (23/31). It can be seen that this scheme has a good prediction rate for medicines with cold nature. The recall, precision, and F-score of 61 CM identification are listed in Table 5. Generally, our scheme has a good identification rate.

Robustness of the proposed

method An independent dataset is used to test the robustness of the proposed algorithm. In this dataset, molecular descriptors are calculated to represent the CMs, including Molweight, H.Acceptors, H.Donors, Polar.Surface.Area, Rotatable.Bonds, Sp3.Atoms, Symmetric. atoms and Amines. The detailed process has been described in the manuscript [10]. In the dataset, there are 534 hot medicines and 724 cold medicines. Table 6 shows the identification confusion matrix of 1258 CMs (534+724 medicines). The total identification accuracy is 81.1% (1020/1258). The prediction accuracy of cold nature medicines is 83.0% (443/534), while the identification accuracy of hot nature medicines is 79.7% (577/724). The experimental results demonstrate that the proposed method has better robustness. Generally, our scheme has a good prediction rate.

Discussion

In this study, we have explored the feasibility of classifying CM nature with a retrieval scheme on the basis of the similarity of UV spectral data. Experiment results have demonstrated that it is an effective method for identifying the unknown CM nature by calculating the similarity of the UV spectrum. Meanwhile, the experimental results verify the proposed hypothesis that CMs with a similar composition of substances should have similar medicinal nature.

In summary. the advantages of our research are as follows. First, to realize CM nature identification, a dataset of 61 reference CM UV spectrum is assembled in which each CM has clearly cold or hot nature. Thus, it is effective and feasible for CM nature determination.

Second, cold-hot nature plays a critical role in TCM nature theory. In this study, we investigate the interrelationship between material composition within CM and cold-hot nature. Material composition is represented by UV spectra. Experiment evaluations have illustrated that there is a correlation between material composition and cold-hot medicine nature, which can be applied for cold-hot nature classification. Furthermore, we demonstrate that material composition determines the CM cold-hot nature.

Third, in the light of UV spectral characteristics of CM, we investigate a retrieval scheme to identify CM nature. The distance metric is studied to measure the similarity of UV spectra. Experiment results display that our scheme performs best. The potential explanation is that our scheme sufficiently explores the relationship between material composition and CM cold-hot nature.

Fourth, another performance that has been thoroughly demonstrated in this study is the robustness of the proposed retrieval scheme for future clinical applications. For an intelligent discriminant model, our goal is to assist researchers in reading ultraviolet spectra and identifying cold-hot nature. The model is not feasible if the robustness is too low for an independent TCM dataset. We have demonstrated that our model has high robustness in the experiments. More CM fingerprint data will be extracted to confirm the robustness of our model in the future.

However, our research still has some limitations. First, this study only used UV spectra to represent the CMs. Other fingerprint techniques are not analyzed in this study, The CMs are complex mixtures of compounds. It is impossible to reflect the whole composition of CM compounds by only one fingerprint technique. In the future, we want to use multiple fingerprints to analyze CM's cold-hot nature. Second, we investigate the similarity of UV spectra with a distance metric. The fingerprint data have the characteristics of high dimension and small sample. Based on such characteristics, the design of the forecasting model is the focus of the future. Third, our study focuses on exploring retrieval schemes for cold-hot nature classification. UV spectrum features have not been thoroughly analyzed. Subsequently, we will integrate more effective fingerprint data to improve medicine nature classification performance.

Our study gives not only a method for nature identification but a new scheme for nature marker of Chinese medicines. Nature marker is a novel concept, indicating the ingredients of Chinese medicines closely related to medicine natures. With our nature identification scheme, we want to look for Chinese medicines with similar ingredients under the same nature restriction conditions. Such several Chinese medicines have the same ingredients, which can be considered as the nature markers of these several Chinese medicines.

Conclusion

In this study, a retrieval scheme is proposed to predict cold-hot medicine nature. Based on the characteristics of CM.this scheme has better classification performance than classical classifiers. Effective experiments demonstrate that cold-hot medicine nature and UV spectral fingerprint data are relevant.

References

1 Gao J, Chen C. Discussion on the scientific connotation of four natures of Chinese materia medica. Acta Univ. Tradit. Med. Sin Pharmacol Shanghai 2007, 21:16-18.

2. Ouyang B, Wang ZG, Wang P. Research thinking and method of modern study on four properties theory of Chinese materia medica. J Beijing Univ Tradit Chin Med 2006, 29: 592-594.

3. Wu LJ, Wang YY, Li YD, et al. Understanding ZHENG in Traditional Chinese Medicine in the context of Neuro-Endocrine-Immune network. IET Syst Biol 2007,1: 51-60.

4. Jin R, Zhang B, Liu X-Q, et al. Study of biological performance of Chinese materia medica with either a cold or hot property based on the three-element mathematical analysis model. J Chin Integr Med 2011, 9:715-724.

5. Zhao Y, Jia L, Wang J, et al. Cold/hot pad differentiating assay of property differences of mahuang and maxingshigan decoctions. Pharm Biol 2016, 54(7):1298-302.

6. Wan HY, Kong XY, Li XM, et al. Effect of traditional Chinese medicines with different properties on thermoregulation and temperature-sensitive transient receptor potential channel protein of rats with yeast-induced fever. China J Chin Meter Med 2014, 39:3813-3818.

7. Liang F, Li L, Wang M, et al. Molecular network and chemical fragment-based characteristics of medicinal herbs with cold and hot properties from Chinese medicine. J Ethnopharmacol 2013, 148(3):770-779.

8. Wang M, Li L, Yu C, et al. Classification of mixtures of Chinese herbal medicines based on a self-organizing map (SOM). Mol Inform 2016, 35(3-4):109-115.

9. Fu X, Song X, Li X, et al. Phylogenetic tree analysis of the cold-hot nature of traditional Chinese marine medicine for possible anticancer activity. Evid Based Complement Alternat Med 2017, 2017:1-10.

10. Fu X, Mervin LH, Li X, et al. Toward understanding the cold, hot, and neutral nature of Chinese medicines using in silico mode-of-action analysis. J Chem Inf Model 2017, 57(3):468-483.

11. Li Y, Li X, Xue FZ, et al. Discrimination of properties of Chinese traditional medicines based on an artificial neural network. J Shandong Univ (Health Sciences) 2011, 49:57-61.

12. Liu WH, Li Y, Ji YJ, et al. Partial least squares in the discrimination of traditional Chinese herbal medicine property. J. Shandong Univ (Health Sciences) 2012, 50:151-154.

13. Zhang XX, Li Y, Ji YJ, et al. Discrimination of properties of Chinese traditional medicine with principal component analysis-linear discriminant analysis. J Shandong Univ (Health Sciences) 2012, 50:143-146.

14. Nie B, Hao ZL, Gui B, et al. The research for metabolomics discriminant method for the cold and hot property of traditional Chinese medicine based on random forest. J Jiangxi Univ Traditi Chin Med 2015, 27:82-86.

15. Long W, Liu P, Xiang J, et al. A combination system for prediction of Chinese Materia Medica properties. Comput. Methods Programs Biomed. 2011, 101(3):253-264.

16. Li H, Xu Q, Zhang J, et al. Cold-hot nature distinguish of traditional Chinese medicinal herbs by discriminant analysis of 1H-NMR spectral data. 2017 International Conference on Medical Science and Human Health (MSHH 2017), 2017, 174-179.

17. Jiang M, Zhang S, Li H, et al. Computer-aided diagnosis of mammographic masses using scalable image retrieval. IEEE Trans Biomed Eng 2015, 62(2):783-92.

18. Tsochatzidis L, Zagoris K, Arikidis N, et al. Computer-aided diagnosis of mammographic masses based on a supervised content-based image retrieval approach. Pattern Recog 2017, 71:106-117.

19. Wei G, Ma H, Qian W, et al. Similarity measurement of lung masses for medical image retrieval using a kernel-based semisupervised distance metric. Med Phys 2016, 43(12):6259-6269.

20. Wei G, Ma H, Qian W, et al. A content-based image retrieval scheme for lung nodule classification. Curr Med Imaging Rev 2017, 13(2):210-216.

21. Liu Y, Rong J, Lily M, et al. A boosting framework for visuality-preserving distance metric learning and its application to medical image retrieval. IEEE Trans Pattern Anal Mach Intell 2010, 32(1):30-44.

22. Weinberger KQ, Blitzer J, Saul LK. Distance metric learning for large margin nearest neighbor classification. J Mach Learn Res 2009, 10(1):207-244.

23. Tao D, Li X, Wu X, et al. General tensor discriminant analysis and Gabor features for gait recognition. IEEE Trans. Pattern Anal Mach Intell 2007, 29(10):1700–1715.

24. Malar E, Kandaswamy A, Chakravarthy D, et al. A novel approach for detection and classification of mammographic microcalcifications using wavelet analysis and extreme learning machine. Comput Biol Med 2012, 42:898–905.

25. H. Li. Construction of the digital representation system based on the ultraviolet spectrum fingerprints of the substantial basis of traditional Chinese medicine (TCM) with cold-heat nature. Jinan: Shandong University of Traditional Chinese Medicine 2011.