Subnetwork representation learning for discovering network biomarkers in predicting lymph node metastasis in early oral cancer

Cervical lymph node metastasis is the leading cause of poor prognosis in oral tongue squamous cell carcinoma and also occurs in the early stages. The current clinical diagnosis depends on a physical examination that is not enough to determine whether micrometastasis remains. The transcriptome profiling technique has shown great potential for predicting micrometastasis by capturing the dynamic activation state of genes. However, there are several technical challenges in using transcriptome data to model patient conditions: (1) An Insufficient number of samples compared to the number of genes, (2) Complex dependence between genes that govern the cancer phenotype, and (3) Heterogeneity between patients between cohorts that differ geographically and racially. We developed a computational framework to learn the subnetwork representation of the transcriptome to discover network biomarkers and determine the potential of metastasis in early oral tongue squamous cell carcinoma. Our method achieved high accuracy in predicting the potential of metastasis in two geographically and racially different groups of patients. The robustness of the model and the reproducibility of the discovered network biomarkers show great potential as a tool to diagnose lymph node metastasis in early oral cancer.

Identifying Network Biomarkers of Cancer By Sample-Specific Differential Network

Abundant datasets generated from various big science projects on diseases have presented great challenges and opportunities, which are contributed to unfold the complexity of diseases. The discovery of disease- associated molecular networks for each individual plays an important role in personalized therapy and precision treatment of cancer based on the reference networks. However, there are no effective ways to distinguish the consistency of different reference networks. In this study, we developed a statistical method, i.e. a sample-specific differential network (SSDN), to construct and analyze such networks based on gene expression of a single sample against a reference dataset. We proved that the SSDN is structurally consistent even with different reference datasets if the reference dataset can follow certain conditions. The SSDN also can be used to identify patient-specific disease modules or network biomarkers as well as predict the potential driver genes of a tumor sample.

Identifying critical states of hepatocellular carcinoma based on single-sample dynamic network biomarkers combined with simulated annealing algorithm

Background: Hepatocellular carcinoma(HCC) is one of the most common malignant tumors. Due to the insidious onset and poor prognosis, most patients have reached the advanced stage at the time of diagnosis. Objective: Studies have shown thatdynamic network biomarkers (DNB) can effectively identify the critical state of complex diseases such as HCC from normal state to disease state. Therefore, it is very important to detect DNB efficiently and reliably. Methods: This paper selects a dataset containing eight HCC disease states. First, anindividual-specific network is constructed for each sample and features are extracted. In the context of this network, a simulated annealing algorithm is used to search for potential dynamic network biomarker modules, and the evolution of HCC is determined. Results: In fact, in the period of low-grade dysplasia (LGD) and high-grade dysplasia (HGD), DNB will send an indicative warning signal, which means that liver dysplasia is a very important critical state in the development of HCC disease. Compared with landscape dynamic network biomarkers method (L-DNB), our method can not only describe the statistical characteristics of each disease state, but also yield better results including getting more DNBs enriched in HCC related pathways. Conclusion: The results of this study may be of great significance to the prevention and early diagnosis of HCC.

Metabolomics-based multidimensional network biomarkers for diabetic retinopathy identification in patients with type 2 diabetes mellitus

IntroductionDespite advances in diabetic retinopathy (DR) medications, early identification is vitally important for DR administration and remains a major challenge. This study aims to develop a novel system of multidimensional network biomarkers (MDNBs) based on a widely targeted metabolomics approach to detect DR among patients with type 2 diabetes mellitus (T2DM) efficiently.Research design and methodsIn this propensity score matching-based case-control study, we used ultra-performance liquid chromatography-electrospray ionization-tandem mass spectrometry system for serum metabolites assessment of 69 pairs of patients with T2DM with DR (cases) and without DR (controls). Comprehensive analysis, including principal component analysis, orthogonal partial least squares discriminant analysis, generalized linear regression models and a 1000-times permutation test on metabolomics characteristics were conducted to detect candidate MDNBs depending on the discovery set. Receiver operating characteristic analysis was applied for the validation of capability and feasibility of MDNBs based on a separate validation set.ResultsWe detected 613 features (318 in positive and 295 in negative ESI modes) in which 63 metabolites were highly relevant to the presence of DR. A panel of MDNBs containing linoleic acid, nicotinuric acid, ornithine and phenylacetylglutamine was determined based on the discovery set. Depending on the separate validation set, the area under the curve (95% CI), sensitivity and specificity of this MDNBs system were 0.92 (0.84 to 1.0), 96% and 78%, respectively.ConclusionsThis study demonstrates that metabolomics-based MDNBs are associated with the presence of DR and capable of distinguishing DR from T2DM efficiently. Our data also provide new insights into the mechanisms of DR and the potential value for new treatment targets development. Additional studies are needed to confirm our findings.