MLCDForest: multi-label classification with deep forest in disease prediction for long non-coding RNAs.

The long non-coding RNAs (lncRNAs) are subject of intensive recent studies due to its association with various human diseases. It is desirable to build the artificial intelligence-based models for prediction of diseases or tissues based on the lncRNAs data, which will be useful in disease diagnosis and therapy. The accuracy and robustness of existing models based on the machine learning techniques are subject to further improvement. In this study, we propose a deep learning model, called Multi-Label Classifications with Deep Forest, termed MLCDForest, to address multi-label classification on tissue prediction for a given lncRNA, which can be regarded as an implementation of the deep forest model in multi-label classification. The MLCDForest is a sequential multi-label-grained scanning method, which distinguishes from the standard deep forest model. It is proposed to train in sequential of multi-labels with label correlation considered. A systematic comparison using the lncRNA-disease association datasets demonstrates that our method consistently shows superior performance over the state-of-the-art methods in disease prediction. Considering label correlation in the sequential multi-label-grained scanning, our model provides a powerful tool to make multi-label classification and tissue prediction based on given lncRNAs.

MDA-GCNFTG: identifying miRNA-disease associations based on graph convolutional networks via graph sampling through the feature and topology graph.

Accurate identification of the miRNA-disease associations (MDAs) helps to understand the etiology and mechanisms of various diseases. However, the experimental methods are costly and time-consuming. Thus, it is urgent to develop computational methods towards the prediction of MDAs. Based on the graph theory, the MDA prediction is regarded as a node classification task in the present study. To solve this task, we propose a novel method MDA-GCNFTG, which predicts MDAs based on Graph Convolutional Networks (GCNs) via graph sampling through the Feature and Topology Graph to improve the training efficiency and accuracy. This method models both the potential connections of feature space and the structural relationships of MDA data. The nodes of the graphs are represented by the disease semantic similarity, miRNA functional similarity and Gaussian interaction profile kernel similarity. Moreover, we considered six tasks simultaneously on the MDA prediction problem at the first time, which ensure that under both balanced and unbalanced sample distribution, MDA-GCNFTG can predict not only new MDAs but also new diseases without known related miRNAs and new miRNAs without known related diseases. The results of 5-fold cross-validation show that the MDA-GCNFTG method has achieved satisfactory performance on all six tasks and is significantly superior to the classic machine learning methods and the state-of-the-art MDA prediction methods. Moreover, the effectiveness of GCNs via the graph sampling strategy and the feature and topology graph in MDA-GCNFTG has also been demonstrated. More importantly, case studies for two diseases and three miRNAs are conducted and achieved satisfactory performance.

[Effect of Schizonepetae Herba and Saposhnikoviae Radix on expression of AQP4 and AQP8 in colonic mucosa of rats with ulcerative colitis].

The aim of this paper was to investigate the effect of Schizonepetae Herba and Saposhnikoviae Radix(wind medicine) on the expression of AQP4 and AQP8 in colonic mucosa in rats with ulcerative colitis(UC). A total of 35 healthy SD male rats were randomly divided into normal group(gavaged with normal saline), DSS model group, as well as low, middle, and high dose wind medicine groups(Schizonepeta and Saposhnikovia 1∶1, gavaged at dosages of 6, 12, and 24 g·kg~(-1)·d~(-1)), with 7 in each group. UC rat model was established by free drinking of 3% dextran sulphate sodium(DSS) solution for 10 days. At the end of the 10 th day after the treatment, mice were put to death to collect colonic mucosa. The length of colon was measured; the colonic mucosal injury index(CMDI) and pathological changes of colon were observed. ELISA method was used for measuring the content of serum IL-1, IL-8, and immunohistochemical method was used to measure AQP4, AQP8 protein expressions in colon mucosa. The expressions of AQP4, AQP8 mRNA were measured by Real-time PCR. As compared with the normal group, the length of colon tissue was significantly reduced(P<0.01), CMDI scores and pathological scores were significantly increased(P<0.01), the levels of serum IL-1 and IL-8 were significantly increased(P<0.05) in model group; the immunohistochemical results showed that the protein expressions of AQP4, AQP8 were lower; the color was light yellow or brown; AQP4, AQP8 mRNA expressions in colon mucosa were significantly decreased in model group(P<0.01). CMDI scores, pathological scores, and the levels of serum IL-1, IL-8 in high, middle, low dose wind medicine groups were obvious lower than those in the model group(P<0.01 or P<0.05); the protein expressions of AQP4, AQP8 were higher; the color was chocolate brown or dark brown; the length of colon tissue, and the expressions of AQP4, AQP8 mRNA were obvious higher in wind medicine groups(P<0.01 or P<0.05). Schizonepetae Herba and Saposhnikoviae Radix could significantly improve the symptoms and histopathology of UC model rats and accelerate the intestinal mucosal healing. The mechanism may be related with up-regulating the expression level of AQP4 and AQP8 in colonic mucosa.

Association between high galectin expression and poor prognosis in hematologic cancers: a systematic review and meta-analysis.

BACKGROUND: Galectin (Gal) is considered a promising immune checkpoint molecule. More and more studies have shown that high expression levels of galectins in hematologic cancer are positively correlated with poor clinical prognosis. However, the exact prognostic significance of galectins remains unclear. METHODS: PubMed, Embase, Web of Science, and Cochrane Library were searched for studies addressing the correlation of galectin expression levels with prognosis of hematologic cancers. Stata software was used to estimate hazard ratios (HR) and 95% confidence intervals (CI). RESULT: Hematologic cancer patients with high galectin expression levels showed poor overall survival (OS, HR = 2.43, 95% CI: 1.95, 3.04), disease-free survival (DFS, HR = 3.29, 95% CI: 1.61, 6.71), and event-free survival (EFS, HR = 2.20, 95% CI: 1.47, 3.29) outcomes. Subgroup analysis revealed that high expression levels of galectins pointed to relatively poor OS in MDS (HR = 5.44, 95% CI: 2.09, 14.18), as compared to AML, CHL and CLL. No correlation was found between galectins and OS in NHL and MM. Among the three galectins, Gal-9 (HR = 3.60, 95% CI: 2.03, 6.38) showed higher correlation with poor prognosis than Gal-1 and Gal-3. In addition, use of peripheral blood (HR = 2.96, 95% CI: 2.07, 4.22) samples and qRT-PCR (HR = 2.80, 95% CI: 1.96, 4.01) method for galectin detection were shown to improve its prognostic correlation in hematologic cancers. CONCLUSION: Meta-analysis revealed high expression of galectins was associated with poor prognosis in hematologic cancer patients and galectins can be considered a promising prognostic predictive marker.

Molecular mechanism of Ruxian Shuhou prescription in the treatment of triple-negative breast cancer based on network pharmacology.

We aimed to explore the molecular mechanism of Ruxian Shuhou prescription in the treatment of triple-negative breast cancer (TNBC) by using network pharmacology. The active components and targets of the prescription were obtained by Traditional Chinese medicine systems pharmacology database. Gencards database, online mendelian inheritance in man database, therapeutic target database, and DRUGBANK database were used to search for the TNBC-related targets. The potential targets of Ruxian Shuhou prescription for TNBC were screened out by the intersection of effective ingredient action targets and disease targets. A herb-active ingredient-target network was constructed and analyzed for key ingredients. A protein-protein interaction network was constructed for studying key targets. Furthermore, gene ontology analysis and Kyoto encyclopedia of genes and genomes pathway enrichment analysis were carried out. Finally, the relationship between key ingredients and key genes was evaluated by molecular docking. The key ingredients of Ruxian Shuhou prescription for the treatment of TNBC may be Quercetin, Luteolin and Kaempferol, while the key therapeutic targets may be protein kinase B, interleukin-6, cellular tumor antigen p53, and vascular endothelial growth factor A. The related signaling pathways were mainly involved in tumor, apoptosis and virus infection, among which the PI3K-Akt signaling pathway was the most closely related to TNBC. Molecular docking showed that the key ingredients had high binding activity with the key targets. The molecular mechanisms of Ruxian Shuhou prescription for TNBC are likely to involve multi-ingredient, multi-target and multi-pathway.

Efficacy and safety of CDK4/6 inhibitors combined with endocrine therapy versus endocrine therapy alone in hormone receptor-positive, HER2-negative, advanced breast cancer: a systematic review and meta-analysis.

BACKGROUND: In previous studies on the application of cyclin-dependent kinase 4/6 (CDK4/6) inhibitors combined with endocrine therapy in advanced breast cancer, the outcomes of overall survival (OS) were inconsistent. This systematic review and meta-analysis aimed to further evaluate the clinical efficacy and safety of CDK4/6 inhibitors combined with endocrine therapy on patients with hormone receptor (HR)-positive and human epidermal growth factor receptor 2 (HER2)-negative advanced breast cancer. METHODS: Randomized controlled trials (RCTs) comparing CDK4/6 inhibitors plus endocrine therapy and endocrine therapy alone in patients with HR-positive and HER2-negative advanced breast cancer were searched in the databases of PubMed, Embase, Cochrane Library, China National Knowledge Infrastructure (CNKI), WANFANG and China Science and Technology Journal Database (VIP) up to November 2022. Hazard ratios (HRs) and confidence intervals (CI) of OS, progression-free survival (PFS), the time from randomization to the first recorded disease progression while the patient was receiving next-line therapy or death from any cause (PFS2), time to first subsequent chemotherapy after discontinuation (TTC), and objective response rate (ORR), clinical benefit rate (CBR), safety indicators were extracted. Stata 14.0 software was used for meta analysis and the Cochrane risk-of-bias tool 2.0 was used to evaluate the bias risk. RESULTS: A total of 9 RCTs with 4,920 participants were included. The addition of CDK4/6 inhibitors to endocrine therapy significantly prolonged OS (HR 0.76; 95% CI: 0.69-0.84; P<0.001), regardless of the application in first-line and second-line treatment, compared with endocrine therapy alone. Similar benefit was observed in PFS (HR 0.56; 95% CI: 0.52-0.60; P<0.001). Moreover, the CDK4/6 inhibitors group improved results of ORR [relative risk (RR) 1.43; 95% CI: 1.27-1.62; P<0.001], CBR (RR 1.24; 95% CI: 1.08-1.41; P<0.01 and RR 1.11; 95% CI: 1.06-1.18; P<0.001), PFS2 (HR 0.68; 95% CI: 0.60-0.76; P<0.001) and TTC (HR 0.65; 95% CI: 0.58-0.72; P<0.001). One of the included RCTs had performance bias. Publication bias was not significant. CONCLUSIONS: CDK4/6 inhibitors combined with endocrine therapy effectively prolong OS, PFS, PFS2, and TTC, and also improve ORR and CBR in patients with HR-positive, HER2-negative advanced breast cancer, and the safety was within the controllable range.

MDA-CF: Predicting MiRNA-Disease associations based on a cascade forest model by fusing multi-source information.

MicroRNAs (miRNAs) are significant regulators in various biological processes. They may become promising biomarkers or therapeutic targets, which provide a new perspective in diagnosis and treatment of multiple diseases. Since the experimental methods are always costly and resource-consuming, prediction of disease-related miRNAs using computational methods is in great need. In this study, we developed MDA-CF to identify underlying miRNA-disease associations based on a cascade forest model. In this method, multi-source information was integrated to represent miRNAs and diseases comprehensively, and the autoencoder was utilized for dimension reduction to obtain the optimal feature space. The cascade forest model was then employed for miRNA-disease association prediction. As a result, the average AUC of MDA-CF was 0.9464 on HMDD v3.2 in five-fold cross-validation. Compared with previous computational methods, MDA-CF performed better on HMDD v2.0 with an average AUC of 0.9258. Moreover, MDA-CF was implemented to investigate colon neoplasm, breast neoplasm, and gastric neoplasm, and 100%, 86%, 88% of the top 50 potential miRNAs were validated by authoritative databases. In conclusion, MDA-CF appears to be a reliable method to uncover disease-associated miRNAs. The source code of MDA-CF is available at https://github.com/a1622108/MDA-CF.