Systems Approach to Pathogenic Mechanism of Type 2 Diabetes and Drug Discovery Design Based on Deep Learning and Drug Design Specifications.

In this study, we proposed a systems biology approach to investigate the pathogenic mechanism for identifying significant biomarkers as drug targets and a systematic drug discovery strategy to design a potential multiple-molecule targeting drug for type 2 diabetes (T2D) treatment. We first integrated databases to construct the genome-wide genetic and epigenetic networks (GWGENs), which consist of protein-protein interaction networks (PPINs) and gene regulatory networks (GRNs) for T2D and non-T2D (health), respectively. Second, the relevant "real GWGENs" are identified by system identification and system order detection methods performed on the T2D and non-T2D RNA-seq data. To simplify network analysis, principal network projection (PNP) was thereby exploited to extract core GWGENs from real GWGENs. Then, with the help of KEGG pathway annotation, core signaling pathways were constructed to identify significant biomarkers. Furthermore, in order to discover potential drugs for the selected pathogenic biomarkers (i.e., drug targets) from the core signaling pathways, not only did we train a deep neural network (DNN)-based drug-target interaction (DTI) model to predict candidate drug's binding with the identified biomarkers but also considered a set of design specifications, including drug regulation ability, toxicity, sensitivity, and side effects to sieve out promising drugs suitable for T2D.

Prognostic factors in patients with metastatic spine tumors derived from lung cancer-a novel scoring system for predicting life expectancy.

BACKGROUND: Recently, molecule-targeting and bone-modifying agents have improved the treatment outcomes of lung cancer-derived metastatic spine tumors. Therefore, the prognostic factors for such tumors were examined, and novel scoring systems for predicting the life expectancy of patients with such tumors were proposed. METHODS: In 207 patients with lung cancer-derived metastatic spine tumors (surgery 49; conservative therapy 158), we retrospectively examined the factors that influenced the post-treatment survival time (age, sex, the affected site, pathology, general condition, the number of extraspinal bone metastases, the number of spinal metastases, the presence/absence of major internal organ metastasis, paralysis state, the total Tokuhashi score, the serum alkaline phosphatase level, the serum carcinoembryonic antigen level, molecule-targeting drug treatment, and bone-modifying agent treatment). Based on the results, we devised novel scoring systems for predicting the prognosis of such patients. RESULTS: Univariate analyses showed that the pathology of the primary lung tumor, the patient's general condition and paralysis state, and the presence/absence of molecule-targeting drug treatment significantly influenced survival. We performed a Cox regression analysis of these four factors and developed criteria for a novel scoring system based on the patient's general condition and paralysis state, which exhibited significance in the regression analysis. A retrospective review indicated that the consistency rate between predicted life expectancy and actual survival was 67.3%. When criteria based on the four factors that exhibited significance in the univariate analyses were adopted, the consistency rate was 76.2%. CONCLUSION: The patient's general condition and paralysis state, the pathology of the primary lung tumor, and molecule-targeting drug treatment influenced survival among patients with lung cancer-derived metastatic spine tumors. Novel scoring systems based on these four factors were proposed.