DRDB: A Machine Learning Platform to Predict Chemical-Protein Interactions towards Diabetic Retinopathy.

Diabetic retinopathy (DR), a diabetic microangiopathy caused by diabetes, affects approximately 93 million people, worldwide. However, the drugs used to treat DR have limited efficacy and the variety of side effects. This is possibly because the complicated pathogenesis of DR is associated with multiple proteins. In this work, we attempted to identify potential drugs against DR-associated proteins and predict potential targets for drugs using in silico prediction of chemical-protein interactions (CPI) based on multitarget quantitative structure-activity relationship (mt-QSAR) method. Therefore, we developed 128 binary classifiers to predict the CPI for 15 DR targets using random forest (RF), k-nearest neighbours (KNN), support vector machine (SVM), and neural network (NN) algorithms with MACCS, extended connectivity fingerprints (ECFP6) fingerprints, and protein descriptors. In order to facilitate discovery of the novel drugs and target identification using the 128 binary classifiers, a free web server (DRDB) was developed. Compound Danshen Dripping Pills (CDDP), composed of Salvia miltiorrhiza, Panax notoginseng, and borneol, is commonly used in the treatment of cardiovascular diseases. To explore the applicability of DRDB, the potential CPIs of CDDP in treatment of DR were investigated based on DRDB. In vitro experimental validation demonstrated that cryptotanshinone and protocatechuic acid, two key components of CDDP, are capable of targeting ICAM-1 which is one of the key target of DR. We hope that this work can facilitate development of more effective clinical strategies for the treatment of DR.

Hub genes associated with immune cell infiltration in breast cancer, identified through bioinformatic analyses of multiple datasets.

OBJECTIVE: The aim of this study was to identify hub genes associated with immune cell infiltration in breast cancer through bioinformatic analyses of multiple datasets. METHODS: Nonparametric (NOISeq) and robust rank aggregation-ranked parametric (EdgeR) methods were used to assess robust differentially expressed genes across multiple datasets. Protein-protein interaction network, GO, KEGG enrichment, and sub-network analyses were performed to identify immune-associated hub genes in breast cancer. Immune cell infiltration was evaluated with the CIBERSORT, XCELL, and TIMER methods. The association between the hub gene-based risk signature and survival was determined through Kaplan-Meier survival analysis, multivariate Cox analysis, and a nomogram with external verification. RESULTS: We identified 163 robust differentially expressed genes in breast cancer through applying both nonparametric and parametric methods to multiple GEO (n = 2,212) and TCGA (n = 1,045) datasets. Integrated bioinformatic analyses further identified 10 hub genes: CXCL10, CXCL9, CXCL11, SPP1, POSTN, MMP9, DPT, COL1A1, ADAMDEC1, and RGS1. The 10 hub-gene-based risk signature significantly correlated with the prognosis of patients with breast cancer. Moreover, these hub genes were strongly associated with the extent of infiltration of CD4+ T cells, CD8+ T cells, neutrophils, macrophages, and myeloid dendritic cells into breast tumors. CONCLUSIONS: Integrated analyses of multiple databases led to the discovery of 10 robust hub genes that together may serve as a risk factor characteristic of the immune microenvironment in breast cancer.