Knowledge Graph Enhanced Transformers for Diagnosis Generation of Chinese Medicine.

Chinese medicine (CM) diagnosis intellectualization is one of the hotspots in the research of CM modernization. The traditional CM intelligent diagnosis models transform the CM diagnosis issues into classification issues, however, it is difficult to solve the problems such as excessive or similar categories. With the development of natural language processing techniques, text generation technique has become increasingly mature. In this study, we aimed to establish the CM diagnosis generation model by transforming the CM diagnosis issues into text generation issues. The semantic context characteristic learning capacity was enhanced referring to Bidirectional Long Short-Term Memory (BILSTM) with Transformer as the backbone network. Meanwhile, the CM diagnosis generation model Knowledge Graph Enhanced Transformer (KGET) was established by introducing the knowledge in medical field to enhance the inferential capability. The KGET model was established based on 566 CM case texts, and was compared with the classic text generation models including Long Short-Term Memory sequence-to-sequence (LSTM-seq2seq), Bidirectional and Auto-Regression Transformer (BART), and Chinese Pre-trained Unbalanced Transformer (CPT), so as to analyze the model manifestations. Finally, the ablation experiments were performed to explore the influence of the optimized part on the KGET model. The results of Bilingual Evaluation Understudy (BLEU), Recall-Oriented Understudy for Gisting Evaluation 1 (ROUGE1), ROUGE2 and Edit distance of KGET model were 45.85, 73.93, 54.59 and 7.12, respectively in this study. Compared with LSTM-seq2seq, BART and CPT models, the KGET model was higher in BLEU, ROUGE1 and ROUGE2 by 6.00-17.09, 1.65-9.39 and 0.51-17.62, respectively, and lower in Edit distance by 0.47-3.21. The ablation experiment results revealed that introduction of BILSTM model and prior knowledge could significantly increase the model performance. Additionally, the manual assessment indicated that the CM diagnosis results of the KGET model used in this study were highly consistent with the practical diagnosis results. In conclusion, text generation technology can be effectively applied to CM diagnostic modeling. It can effectively avoid the problem of poor diagnostic performance caused by excessive and similar categories in traditional CM diagnostic classification models. CM diagnostic text generation technology has broad application prospects in the future.

Bibliometric and visualized analysis of nonpharmaceutical TCM therapies for rheumatoid arthritis over the last 20 years using VOSviewer and CiteSpace software.

BACKGROUND: Rheumatoid arthritis (RA) is a chronic autoimmune inflammatory disease that poses a significant threat to a patient's quality of life. Commonly used drugs include glucocorticoids, nonsteroidal anti-inflammatory drugs, disease-modifying antirheumatic drugs, and biological agents; however, there are associated side effects. Complementary and alternative medicines can play positive roles. Bibliometric analysis of herbal medicines for RA has been conducted, but current research trends in nonpharmaceutical traditional Chinese medicine (TCM) therapies for the treatment of RA have not been studied. Here, we conducted a bibliometric analysis of the application of nonpharmaceutical TCM therapies for RA over the last 20 years. METHODS: We retrieved relevant literature from the Web of Science Core Collection database and used VOSviewer and CiteSpace software for analysis. Visualized maps were then generated to display the relationships between the author, country, institution, and keywords. RESULTS: A total of 567 articles were included in the final analysis. The number of annual publications on nonpharmaceutical TCM interventions for RA increased over the study period. The journal with the highest number of publications on this topic was Evidence-based Complementary and Alternative Medicine; however, Cochrane Database of Systematic Reviews had the most citations. Collaborations were observed among worldwide institutions, with the People's Republic of China playing a dominant role in the research on treatment of RA using nonpharmaceutical TCM therapies. Ernst E was the most productive author, with 11 articles, whereas Green S had the highest number of citations (287) at the time of retrieval. Specific improvements in the efficacy and selection of nonpharmaceutical therapies were the main research hotspots based on citation burst analysis. CONCLUSION: This study characterizes the trends in the literature for nonpharmaceutical TCM therapy for RA over the past 20 years; showcasing the current research status for relevant researchers and their teams and providing a reference for future research directions.

Intelligent Identification Method of Geographic Origin for Chinese Wolfberries Based on Color Space Transformation and Texture Morphological Features.

Geographic origins play a vital role in traditional Chinese medicinal materials. Using the geo-authentic crude drug can improve the curative effect. The main producing areas of Chinese wolfberry are Ningxia, Gansu, Qinghai, and so on. The geographic origin of Chinese wolfberry can affect its texture, shape, color, smell, nutrients, etc. However, the traditional method for identifying the geographic origin of Chinese wolfberries is still based on human eyes. To efficiently identify Chinese wolfberries from different origins, this paper presents an intelligent identification method for Chinese wolfberries based on color space transformation and texture morphological features. The first step is to prepare the Chinese wolfberry samples and collect the image data. Then the images are preprocessed, and the texture and morphology features of single wolfberry images are extracted. Finally, the random forest algorithm is employed to establish a model of the geographic origin of Chinese wolfberries. The proposed method can accurately predict the origin information of a single wolfberry image and has the advantages of low cost, fast recognition speed, high recognition accuracy, and no damage to the sample.

[Application and development of systems biology in computer-aided drug design].

With the advances in medicine, people have deeply understood the complex pathogenesis of diseases. Revealing the mechanism of action and therapeutic effect of drugs from an overall perspective has become the top priority of drug design. However, the traditional drug design methods cannot meet the current needs. In recent years, with the rapid development of systems biology, a variety of new technologies including metabolomics, genomics, and proteomics have been used in drug research and development. As a bridge between traditional pharmaceutical theory and modern science, computer-aided drug design(CADD) can shorten the drug development cycle and improve the success rate of drug design. The application of systems biology and CADD provides a methodological basis and direction for revealing the mechanism and action of drugs from an overall perspective. This paper introduces the research and application of systems biology in CADD from different perspectives and proposes the development direction, providing reference for promoting the application.

Minimizing the Spread of Negative Influence in SNIR Model by Contact Blocking.

This paper presents a method to minimize the spread of negative influence on social networks by contact blocking. First, based on the infection-spreading process of COVID-19, the traditional susceptible, infectious, and recovered (SIR) propagation model is extended to the susceptible, non-symptomatic, infectious, and recovered (SNIR) model. Based on this model, we present a method to estimate the number of individuals infected by a virus at any given time. By calculating the reduction in the number of infected individuals after blocking contacts, the method selects the set of contacts to be blocked that can maximally reduce the affected range. The selection of contacts to be blocked is repeated until the number of isolated contacts that need to be blocked is reached or all infection sources are blocked. The experimental results on three real datasets and three synthetic datasets show that the algorithm obtains contact blockings that can achieve a larger reduction in the range of infection than other similar algorithms. This shows that the presented SNIR propagation model can more precisely reflect the diffusion and infection process of viruses in social networks, and can efficiently block virus infections.

RNAPhaSep: a resource of RNAs undergoing phase separation.

Liquid-liquid phase separation (LLPS) partitions cellular contents, underlies the formation of membraneless organelles and plays essential biological roles. To date, most of the research on LLPS has focused on proteins, especially RNA-binding proteins. However, accumulating evidence has demonstrated that RNAs can also function as 'scaffolds' and play essential roles in seeding or nucleating the formation of granules. To better utilize the knowledge dispersed in published literature, we here introduce RNAPhaSep (http://www.rnaphasep.cn), a manually curated database of RNAs undergoing LLPS. It contains 1113 entries with experimentally validated RNA self-assembly or RNA and protein co-involved phase separation events. RNAPhaSep contains various types of information, including RNA information, protein information, phase separation experiment information and integrated annotation from multiple databases. RNAPhaSep provides a valuable resource for exploring the relationship between RNA properties and phase behaviour, and may further enhance our comprehensive understanding of LLPS in cellular functions and human diseases.

[Recognition of producing areas of Angelicae Sinensis Radix based on structure-texture image decomposition].

The pharmacological effects of Angelicae Sinensis Radix from different producing areas are uneven. Accurate identification of its producing areas by computer vision and machine learning(CVML) is conducive to evaluating the quality of Angelicae Sinensis Radix. This paper collected the high-definition images of Angelicae Sinensis Radix from different producing areas using a digital camera to construct an image database, followed by the extraction of texture features based on the grayscale relationship of adjacent pixels in the image. Then a support vector machine(SVM)-based prediction model for predicting the producing areas of Angelicae Sinensis Radix was built. The experimental results showed that the prediction accuracy reached up to 98.49% under the conditions of the model training set occupying 80%, the test set occupying 20%, and the sampling radius(r) of adjacent pixels being 2. When the training set was set to 10%, the prediction accuracy was still over 93%. Among the three producing areas of Angelicae Sinensis Radix, Huzhu county, Qinghai province exhibited the highest error rate, while Heqing county, Yunnan province the lowest error rate. Angelicae Sinensis Radix from Minxian county, Gansu province and Huzhu county, Qinghai province were both wrongly attributed to Heqing county, Yunnan province, while most of those from Huzhu county, Qinghai province were misjudged as the samples produced in Minxian county, Gansu province. The method designed in this paper enabled the rapid and non-destructive prediction of the producing areas of Angelicae Sinensis Radix, boasting high accuracy and strong stability. There were definite morphological differences between Angelicae Sinensis Radix samples from Minxian county, Gansu province and those from Huzhu county, Qinghai province. The wrongly predicted samples from Minxian county, Gansu province and Huzhu city, Qinghai province shared similar morphological characteristics with those from Heqing county, Yunnan province. Most wrongly predicted samples from Heqing county, Yunnan province were similar to the ones from Minxian county, Gansu province in morphological characteristics.

An E-nose and Convolution Neural Network based Recognition Method for Processed Products of Crataegi Fructus.

BACKGROUND: The manual identification of Fructus Crataegi processed products is inefficient and unreliable. Therefore, efficient identification of the Fructus Crataegis' processed products is important. OBJECTIVE: In order to efficiently identify Fructus Crataegis processed products with different odor characteristics, a new method based on an electronic nose and convolutional neural network is proposed. METHODS: First, the original smell of Fructus Crataegis processed products is obtained by using the electronic nose and then preprocessed. Next, feature extraction is carried out on the preprocessed data through convolution pooling layer LCP1, convolution pooling layer LCP2 and a full connection layer LFC. Thus, the feature vector of the processed products can be obtained. Then, the recognition model for Fructus Grataegis processed products is constructed, and the model is trained to obtain the optimized parameters: filters F1 and F2, bias vectors B1, B2, B3, and B4, matrices M1 and M2. Finally, the features of the target processed products are extracted through the trained parameters to achieve accurate prediction. RESULTS: The experimental results show that the proposed method has higher accuracy for the identification of Fructus Crataegis processed products, and is competitive with other machine learning based methods. CONCLUSION: The method proposed in this paper is effective for the identification of Fructus Crataegi processed products.

Identifying essential proteins in dynamic protein networks based on an improved h-index algorithm.

BACKGROUND: The essential proteins in protein networks play an important role in complex cellular functions and in protein evolution. Therefore, the identification of essential proteins in a network can help to explain the structure, function, and dynamics of basic cellular networks. The existing dynamic protein networks regard the protein components as the same at all time points; however, the role of proteins can vary over time. METHODS: To improve the accuracy of identifying essential proteins, an improved h-index algorithm based on the attenuation coefficient method is proposed in this paper. This method incorporates previously neglected node information to improve the accuracy of the essential protein search. Based on choosing the appropriate attenuation coefficient, the values, such as monotonicity, SN, SP, PPV and NPV of different essential protein search algorithms are tested. RESULTS: The experimental results show that, the algorithm proposed in this paper can ensure the accuracy of the found proteins while identifying more essential proteins. CONCLUSIONS: The described experiments show that this method is more effective than other similar methods in identifying essential proteins in dynamic protein networks. This study can better explain the mechanism of life activities and provide theoretical basis for the research and development of targeted drugs.

Analyzing hedyotis diffusa mechanisms of action from the genomics perspective.

BACKGROUND AND OBJECTIVE: Hedyotis diffusa is an herb used for anti-cancer, anti-oxidant, anti-inflammatory, and anti-fibroblast treatment in the clinical practice of Traditional Chinese Medicine. However, its pharmacological mechanisms have not been fully established and there is a lack of modern scientific verification. One of the best ways to further understand Hedyotis diffusa's mechanisms of action is to analyze it from the genomics perspective. METHODS: In this study, we used network pharmacology approaches to infer the herb-gene interactions, the herb-pathway interactions, and the gene families. We then analyzed Hedyotis diffusa's mechanisms of action using the genomics context combined with the Traditional Chinese Medicine clinical practice and the pharmacological research. RESULTS: The results obtained in the pathway and gene family analysis were consistent with the Traditional Chinese Medicine clinical experience and the pharmacological activities of Hedyotis diffusa. CONCLUSIONS: Our approach can identify related genes and pathways correctly with little a priori knowledge, and provide potential directions to facilitate further research.

Research on Ratio of Dosage of Drugs in Traditional Chinese Prescriptions by Data Mining.

Maximizing the effectiveness of prescriptions and minimizing adverse effects of drugs is a key component of the health care of patients. In the practice of traditional Chinese medicine (TCM), it is important to provide clinicians a reference for dosing of prescribed drugs. The traditional Cheng-Church biclustering algorithm (CC) is optimized and the data of TCM prescription dose is analyzed by using the optimization algorithm. Based on an analysis of 212 prescriptions related to TCM treatment of kidney diseases, the study generated 87 prescription dose quantum matrices and each sub-matrix represents the referential value of the doses of drugs in different recipes. The optimized CC algorithm can effectively eliminate the interference of zero in the original dose matrix of TCM prescriptions and avoid zero appearing in output sub-matrix. This results in the ability to effectively analyze the reference value of drugs in different prescriptions related to kidney diseases, so as to provide valuable reference for clinicians to use drugs rationally.