HANSynergy: Heterogeneous Graph Attention Network for Drug Synergy Prediction.

Drug synergy therapy is a promising strategy for cancer treatment. However, the extensive variety of available drugs and the time-intensive process of determining effective drug combinations through clinical trials pose significant challenges. It requires a reliable method for the rapid and precise selection of drug synergies. In response, various computational strategies have been developed for predicting drug synergies, yet the exploitation of heterogeneous biological network features remains underexplored. In this study, we construct a heterogeneous graph that encompasses diverse biological entities and interactions, utilizing rich data sets from sources, such as DrugCombDB, PubChem, UniProt, and cancer cell line encyclopedia (CCLE). We initialize node feature representations and introduce a novel virtual node to enhance drug representation. Our proposed method, the heterogeneous graph attention network for drug-drug synergy prediction (HANSynergy), has been experimentally validated to demonstrate that the heterogeneous graph attention network can extract key node features, efficiently harness the diversity of information, and further enhance network functionality through the incorporation of a multihead attention mechanism. In the comparative experiment, the highest accuracy (Acc) and area under the curve (AUC) are 0.877 and 0.947, respectively, in DrugCombDB_early data set, demonstrating the superiority of HANSynergy over the competing methods. Moreover, protein-protein interactions are important in understanding the mechanism of action of drugs. The heterogeneous attention mechanism facilitates protein-protein interaction analysis. By analyzing the changes of attention weight before and after heterogeneous network training, we investigated proteins that may be associated with drug combinations. Additionally, case studies align our findings with existing research, underscoring the potential of HANSynergy in drug synergy prediction. This advancement not only contributes to the burgeoning field of drug synergy prediction but also holds the potential to provide valuable insights and uncover new drug synergies for combating cancer.

HPE-GCN: Predicting efficacy of tonic formulae via graph convolutional networks integrating traditionally defined herbal properties.

Chinese herbal formulae are the heritage of traditional Chinese medicine (TCM) in treating diseases through thousands of years. The formula function is not just a simple herbal efficacy addition, but produces complex and nonlinear relationships between different herbs and their overall efficacy, which brings challenges to the formula efficacy analysis. In our study, we proposed a model called HPE-GCN that combines graph convolutional networks (GCN) with TCM-defined herbal properties (TCM-HPs) to predict formulae efficacy. In addition, to process the unstructured natural language in the formula text, we proposed a weighting calculation method related to herb frequency and the number of herbs in a formula called Formula-Herb dependence degree (FHDD), to assess the dependency degree of a formula with its herbs. In our research, 214 classic tonic formulae from ancient TCM books such as Synopsis of the Golden Chamber, Jingyue's Complete Works and the Golden Mirror of Medicin were collected as datasets. The performance of HPE-GCN on multi-classification of tonic formulae reached the best result compared with classic machine learning models, such as support vector machine, naive Bayes, logistic regression, gradient boosting decision tree, and K-nearest neighbors. The evaluated index Macro-Precision, Macro-Recall, Macro-F1 of HPE-GCN on the test set were 87.70%, 84.08% and 83.51% respectively, increased by 7.27%, 7.41% and 7.30% respectively from second best compared models. GCN has the advantage of low-dimensional feature expression for herbs and formulae, and is an effective analysis tool for TCM research. HPE-GCN integrates TCM-HPs and fits the complex nonlinear mapping relationship between TCM-HPs and formulae efficacy, which provides new ideas for related research.

[Traditional Chinese Medicine data management policy in big data environment].

As traditional data management model cannot effectively manage the massive data in traditional Chinese medicine(TCM) due to the uncertainty of data object attributes as well as the diversity and abstraction of data representation, a management strategy for TCM data based on big data technology is proposed. Based on true characteristics of TCM data, this strategy could solve the problems of the uncertainty of data object attributes in TCM information and the non-uniformity of the data representation by using modeless properties of stored objects in big data technology. Hybrid indexing mode was also used to solve the conflicts brought by different storage modes in indexing process, with powerful capabilities in query processing of massive data through efficient parallel MapReduce process. The theoretical analysis provided the management framework and its key technology, while its performance was tested on Hadoop by using several common traditional Chinese medicines and prescriptions from practical TCM data source. Result showed that this strategy can effectively solve the storage problem of TCM information, with good performance in query efficiency, completeness and robustness.

Combining convolutional attention mechanism and residual deformable Transformer for infarct segmentation from CT scans of acute ischemic stroke patients.

Background: Segmentation and evaluation of infarcts on medical images are essential for diagnosis and prognosis of acute ischemic stroke (AIS). Computed tomography (CT) is the first-choice examination for patients with AIS. Methods: To accurately segment infarcts from the CT images of patients with AIS, we proposed an automated segmentation method combining the convolutional attention mechanism and residual Deformable Transformer in this article. The method used the encoder-decoder structure, where the encoders were employed for downsampling to obtain the feature of the images and the decoder was used for upsampling and segmentation. In addition, we further applied the convolutional attention mechanism and residual network structure to improve the effectiveness of feature extraction. Our code is available at: https://github.com/XZhiXiang/AIS-segmentation/tree/master. Results: The proposed method was assessed on a public dataset containing 397 non-contrast CT (NCCT) images of AIS patients (AISD dataset). The symptom onset to CT time was less than 24 h. The experimental results illustrate that this work had a Dice coefficient (DC) of 58.66% for AIS infarct segmentation, which outperforms several existing methods. Furthermore, volumetric analysis of infarcts indicated a strong correlation (Pearson correlation coefficient = 0.948) between the AIS infarct volume obtained by the proposed method and manual segmentation. Conclusion: The strong correlation between the infarct segmentation obtained via our method and the ground truth allows us to conclude that our method could accurately segment infarcts from NCCT images.

SMRGAT: A traditional Chinese herb recommendation model based on a multi-graph residual attention network and semantic knowledge fusion.

ETHNOPHARMACOLOGICAL RELEVANCE: Traditional Chinese Medicine (TCM) prescriptions are a product of the Chinese medical theory's distinct thinking and clinical experience. TCM practitioners treat diseases by enhancing the efficacy of TCM prescriptions and reducing their poisonous effects. Some TCM herb recommendation methods have been provided for curing the given symptoms to generate a group of herbs according to the TCM principles. However, they ignored the symptoms' semantic characteristics and herbs' different effects on symptoms. AIM OF THE STUDY: We aim to recommend TCM herbs by considering symptoms' semantic information and the strength of different herbs in curing symptoms. MATERIALS AND METHODS: We propose a herb recommendation model named Multi-Graph Residual Attention Network and Semantic Knowledge Fusion (SMRGAT) to address these problems. Concretely, it uses a multi-head attention mechanism to focus on herbs' different effects on symptoms. Meanwhile, it augments entities' features with a residual network structure while incorporating symptoms' semantic information and external knowledge of herbs. We will verify the effect of SMRGAT on the existing public datasets and the datasets that we have collected and cleaned. RESULTS: Compared with the current best TCM herb recommendation model, on the public dataset, SMRGAT were increased by 15.11%, 20.60%, and 18.25% in Precision@5, Recall@5, and F1 - score@5, respectively; on ours, respectively increased by 9.72%, 9.03%, 9.24%. CONCLUSIONS: Our experimental results on two datasets indicate that SMRGAT is capable of recommending herbs with greater precision and outperforms several comparison methods. It can provide a basis for assisting TCM clinical prescriptions.

Changes in metabolites in raw and wine processed Corni Fructus combination metabolomics with network analysis focusing on potential hypoglycemic effects.

Introduction: Corni Fructus (CF) is a Chinese herbal medicine used for medicinal and dietary purposes. It is available commercially in two main forms: raw CF (unprocessed CF) and wine-processed CF. Clinical observations have indicated that wine-processed CF exhibits superior hypoglycemic activity compared to its raw counterpart. However, the mechanisms responsible for this improvement are not well understood. Methods: To address this gap in knowledge, we conducted metabolomics analysis using ultra-performance liquid chromatography-quadrupole/time-of-flight mass spectrometry (UPLC-QTOF-MS) to compare the chemical composition of raw CF and wine-processed CF. Subsequently, network analysis, along with immunofluorescence assays, was employed to elucidate the potential targets and mechanisms underlying the hypoglycemic effects of metabolites in CF. Results: Our results revealed significant compositional differences between raw CF and wine-processed CF, identifying 34 potential markers for distinguishing between the two forms of CF. Notably, wine processing led to a marked decrease in iridoid glycosides and flavonoid glycosides, which are abundant in raw CF. Network analysis predictions provided clues that eight compounds might serve as hypoglycemic metabolites of CF, and glucokinase (GCK) and adenylate cyclase (ADCYs) were speculated as possible key targets responsible for the hypoglycemic effects of CF. Immunofluorescence assays confirmed that oleanolic acid and ursolic acid, two bioactive compounds present in CF, significantly upregulated the expression of GCK and ADCYs in the HepG2 cell model. Discussion: These findings support the notion that CF exerted hypoglycemic activity via multiple components and targets, shedding light on the impact of processing methods on the chemical composition and hypoglycemic activity of Chinese herbal medicine.

Glycosides of Buyang Huanwu decoction inhibits pyroptosis associated with cerebral ischemia-reperfusion through Nrf2-mediated antioxidant signaling pathway both in vivo and in vitro.

BACKGROUND: Glycosides are the pharmacodynamic substances of Buyang Huanwu Decoction (BYHWD) and they exert a protective effect in the brain by inhibiting neuronal pyroptosis of cerebral ischemia-reperfusion (CIR). However, the mechanism by which glycosides regulate neuronal pyroptosis of CIR is still unclear. PURPOSE: A significant part of this study aimed to demonstrate whether glycosides have an anti-pyroptotic effect on CIR by nuclear factor erythroid 2-related factor (Nrf2)-mediated antioxidative mechanism. METHODS: Rats were used in vivo models of middle cerebral artery occlusion and reperfusion (MCAO/R). Neuroprotective effect of glycosides after Nrf2 inhibiting was observed by nerve function score, Nissl staining, Nrf2 fluorescence staining and pyroptotic proteins detection. SH-SY5Y cells were used in vitro models of oxygen-glucose deprivation/reperfusion (OGD/R). Glycosides was evaluated for their effects by measuring cell morphology, survival rate, lactate dehydrogenase (LDH) rate and expression of pyroptotic proteins. Nrf2 si-RNA 54-1 interference with lentivirus was used to create silenced Nrf2 SH-SY5Y cells (si-Nrf2-SH-SY5Y). Glycosides were evaluated on si-Con-SH-SY5Y and si-Nrf2-SH-SY5Y cells based on the expression of Nrf2 signaling pathway, pyroptotic proteins and cell damage manifestation. RESULTS: In vivo, glycosides significantly promoted the fluorescence level of nuclear Nrf2, added more Nissl bodies, reduced neurological function scores and inhibited the pyroptotic proteins level. In vitro, glycosides significantly repaired the morphological damage of cells, promoted the survival rate, reduced the LDH rate, inhibited the pyroptosis. Moreover, antioxidant activity of glycosides was enhanced via Nrf2 activation. Both Nrf2 blocking in vivo and Nrf2 silencing in vitro significantly weakened the pyroptosis inhibitory and neuroprotective effects of glycosides. CONCLUSION: These results suggested for the first time that glycosides inhibited neuronal pyroptosis by regulating the Nrf2-mediated antioxidant stress pathway, thereby exerting brain protection of CIR. As a result of this study, This study improved understanding of the pharmacodynamics and mechanism of BYHWD, as well as providing a Traditional Chinese Medicine (TCM) treatment strategy for CIR .

PMMS: Predicting essential miRNAs based on multi-head self-attention mechanism and sequences.

Increasing evidence has proved that miRNA plays a significant role in biological progress. In order to understand the etiology and mechanisms of various diseases, it is necessary to identify the essential miRNAs. However, it is time-consuming and expensive to identify essential miRNAs by using traditional biological experiments. It is critical to develop computational methods to predict potential essential miRNAs. In this study, we provided a new computational method (called PMMS) to identify essential miRNAs by using multi-head self-attention and sequences. First, PMMS computes the statistic and structure features and extracts the static feature by concatenating them. Second, PMMS extracts the deep learning original feature (BiLSTM-based feature) by using bi-directional long short-term memory (BiLSTM) and pre-miRNA sequences. In addition, we further obtained the multi-head self-attention feature (MS-based feature) based on BiLSTM-based feature and multi-head self-attention mechanism. By considering the importance of the subsequence of pre-miRNA to the static feature of miRNA, we obtained the deep learning final feature (WA-based feature) based on the weighted attention mechanism. Finally, we concatenated WA-based feature and static feature as an input to the multilayer perceptron) model to predict essential miRNAs. We conducted five-fold cross-validation to evaluate the prediction performance of PMMS. The areas under the ROC curves (AUC), the F1-score, and accuracy (ACC) are used as performance metrics. From the experimental results, PMMS obtained best prediction performances (AUC: 0.9556, F1-score: 0.9030, and ACC: 0.9097). It also outperformed other compared methods. The experimental results also illustrated that PMMS is an effective method to identify essential miRNA.

Improving the Accuracy in Classification of Blood Pressure from Photoplethysmography Using Continuous Wavelet Transform and Deep Learning.

BACKGROUND: Continuous wavelet transform (CWT) based scalogram can be used for photoplethysmography (PPG) signal transformation to classify blood pressure (BP) with deep learning. We aimed to investigate the determinants that can improve the accuracy of BP classification based on PPG and deep learning and establish a better algorithm for the prediction. METHODS: The dataset from PhysioNet was accessed to extract raw PPG signals for testing and its corresponding BPs as category labels. The BP category of normal or abnormal followed the criteria of the 2017 American College of Cardiology/American Heart Association (ACC/AHA) Hypertension Guidelines. The PPG signals were transformed into 224 ∗ 224 ∗ 3-pixel scalogram via different CWTs and segment units. All of them are fed into different convolutional neural networks (CNN) for training and validation. The receiver-operating characteristic and loss and accuracy curves were used to evaluate and compare the performance of different methods. RESULTS: Both wavelet type and segment length could affect the accuracy, and Cgau1 wavelet and segment-300 revealed the best performance (accuracy 90%) without obvious overfitting. This method performed better than previously reported MATLAB Morse wavelet transformed scalogram on both of our proposed CNN and CNN-GoogLeNet. CONCLUSIONS: We have established a new algorithm with high accuracy to predict BP classification from PPG via matching of CWT type and segment length, which is a promising solution for rapid prediction of BP classification from real-time processing of PPG signal on a wearable device.

An Improved Deep Learning Model: S-TextBLCNN for Traditional Chinese Medicine Formula Classification.

Purpose: This study proposes an S-TextBLCNN model for the efficacy of traditional Chinese medicine (TCM) formula classification. This model uses deep learning to analyze the relationship between herb efficacy and formula efficacy, which is helpful in further exploring the internal rules of formula combination. Methods: First, for the TCM herbs extracted from Chinese Pharmacopoeia, natural language processing (NLP) is used to learn and realize the quantitative expression of different TCM herbs. Three features of herb name, herb properties, and herb efficacy are selected to encode herbs and to construct formula-vector and herb-vector. Then, based on 2,664 formulae for stroke collected in TCM literature and 19 formula efficacy categories extracted from Yifang Jijie, an improved deep learning model TextBLCNN consists of a bidirectional long short-term memory (Bi-LSTM) neural network and a convolutional neural network (CNN) is proposed. Based on 19 formula efficacy categories, binary classifiers are established to classify the TCM formulae. Finally, aiming at the imbalance problem of formula data, the over-sampling method SMOTE is used to solve it and the S-TextBLCNN model is proposed. Results: The formula-vector composed of herb efficacy has the best effect on the classification model, so it can be inferred that there is a strong relationship between herb efficacy and formula efficacy. The TextBLCNN model has an accuracy of 0.858 and an F1-score of 0.762, both higher than the logistic regression (acc = 0.561, F1-score = 0.567), SVM (acc = 0.703, F1-score = 0.591), LSTM (acc = 0.723, F1-score = 0.621), and TextCNN (acc = 0.745, F1-score = 0.644) models. In addition, the over-sampling method SMOTE is used in our model to tackle data imbalance, and the F1-score is greatly improved by an average of 47.1% in 19 models. Conclusion: The combination of formula feature representation and the S-TextBLCNN model improve the accuracy in formula efficacy classification. It provides a new research idea for the study of TCM formula compatibility.

Metabolomics Analysis of Hippocampus and Cortex in a Rat Model of Traumatic Brain Injury in the Subacute Phase.

Traumatic brain injury (TBI) is a complex and serious disease as its multifaceted pathophysiological mechanisms remain vague. The molecular changes of hippocampal and cortical dysfunction in the process of TBI are poorly understood, especially their chronic effects on metabolic profiles. Here we utilize metabolomics-based liquid chromatography coupled with tandem mass spectrometry coupled with bioinformatics method to assess the perturbation of brain metabolism in rat hippocampus and cortex on day 7. The results revealed a signature panel which consisted of 13 identified metabolites to facilitate targeted interventions for subacute TBI discrimination. Purine metabolism change in cortical tissue and taurine and hypotaurine metabolism change in hippocampal tissue were detected. Furthermore, the associations between the metabolite markers and the perturbed pathways were analyzed based on databases: 64 enzyme and one pathway were evolved in TBI. The findings represented significant profiling changes and provided unique metabolite-protein information in a rat model of TBI following the subacute phase. This study may inspire scientists and doctors to further their studies and provide potential therapy targets for clinical interventions.