Toward drug-miRNA resistance association prediction by positional encoding graph neural network and multi-channel neural network.

Drug discovery is a costly and time-consuming process, and most drugs exert therapeutic efficacy by targeting specific proteins. However, there are a large number of proteins that are not targeted by any drug. Recently, miRNA-based therapeutics are becoming increasingly important, since miRNA can regulate the expressions of specific genes and affect a variety of human diseases. Therefore, it is of great significance to study the associations between miRNAs and drugs to enable drug discovery and disease treatment. In this work, we propose a novel method named DMR-PEG, which facilitates drug-miRNA resistance association (DMRA) prediction by leveraging positional encoding graph neural network with layer attention (LAPEG) and multi-channel neural network (MNN). LAPEG considers both the potential information in the miRNA-drug resistance heterogeneous network and the specific characteristics of entities (i.e., drugs and miRNAs) to learn favorable representations of drugs and miRNAs. And MNN models various sophisticated relations and synthesizes the predictions from different perspectives effectively. In the comprehensive experiments, DMR-PEG achieves the area under the precision-recall curve (AUPR) score of 0.2793 and the area under the receiver-operating characteristic curve (AUC) score of 0.9475, which outperforms the most state-of-the-art methods. Further experimental results show that our proposed method has good robustness and stability. The ablation study demonstrates each component in DMR-PEG is essential for drug-miRNA drug resistance association prediction. And real-world case study presents that DMR-PEG is promising for DMRA inference.

Graph embedding ensemble methods based on the heterogeneous network for lncRNA-miRNA interaction prediction.

BACKGROUND: Researchers discover LncRNA-miRNA regulatory paradigms modulate gene expression patterns and drive major cellular processes. Identification of lncRNA-miRNA interactions (LMIs) is critical to reveal the mechanism of biological processes and complicated diseases. Because conventional wet experiments are time-consuming, labor-intensive and costly, a few computational methods have been proposed to expedite the identification of lncRNA-miRNA interactions. However, little attention has been paid to fully exploit the structural and topological information of the lncRNA-miRNA interaction network. RESULTS: In this paper, we propose novel lncRNA-miRNA prediction methods by using graph embedding and ensemble learning. First, we calculate lncRNA-lncRNA sequence similarity and miRNA-miRNA sequence similarity, and then we combine them with the known lncRNA-miRNA interactions to construct a heterogeneous network. Second, we adopt several graph embedding methods to learn embedded representations of lncRNAs and miRNAs from the heterogeneous network, and construct the ensemble models using two ensemble strategies. For the former, we consider individual graph embedding based models as base predictors and integrate their predictions, and develop a method, named GEEL-PI. For the latter, we construct a deep attention neural network (DANN) to integrate various graph embeddings, and present an ensemble method, named GEEL-FI. The experimental results demonstrate both GEEL-PI and GEEL-FI outperform other state-of-the-art methods. The effectiveness of two ensemble strategies is validated by further experiments. Moreover, the case studies show that GEEL-PI and GEEL-FI can find novel lncRNA-miRNA associations. CONCLUSION: The study reveals that graph embedding and ensemble learning based method is efficient for integrating heterogeneous information derived from lncRNA-miRNA interaction network and can achieve better performance on LMI prediction task. In conclusion, GEEL-PI and GEEL-FI are promising for lncRNA-miRNA interaction prediction.

A systematic review of computational methods for predicting long noncoding RNAs.

Accurately and rapidly distinguishing long noncoding RNAs (lncRNAs) from transcripts is prerequisite for exploring their biological functions. In recent years, many computational methods have been developed to predict lncRNAs from transcripts, but there is no systematic review on these computational methods. In this review, we introduce databases and features involved in the development of computational prediction models, and subsequently summarize existing state-of-the-art computational methods, including methods based on binary classifiers, deep learning and ensemble learning. However, a user-friendly way of employing existing state-of-the-art computational methods is in demand. Therefore, we develop a Python package ezLncPred, which provides a pragmatic command line implementation to utilize nine state-of-the-art lncRNA prediction methods. Finally, we discuss challenges of lncRNA prediction and future directions.

Comparison of clinicopathological features and survival between patients with left-sided colon cancer and rectal cancer / 中国肿瘤生物治疗杂志

@#[Abstract] Objective: To compare the differences in clinical and pathological features and survival time between patients with left -sided colon cancer and rectal cancer. Methods:Atotal of 323 patients with colorectal cancer (CRC) underwent surgical resection at Changhai Hospital of the Second Military Medical University between January 2011 and January 2012 were enrolled in this study. The clinical data of patients were collected and the follow-up was started from the day of surgery or pathological confirmation with the death of patients as endpoints. The follow-up lasted untilAugust 1,2017. Results: There were significant differences in initial symptoms, pathologic type, tumor stage, anemia before surgery, p53 positive rate, and BRAF mutation (χ2=59.088， 4.188， 24.305， 11.956， 4.221， 4.001， all P<0.05) between patients with left-sided colon cancer and rectal cancer. For all the patients, the median survival time was not observed. The five-year survival rates of patients with left-sided colon cancer and rectal cancer were 79.2% and 74.3%, respectively. The Kaplan-Meier survival curves of patients at StageⅠ-Ⅱshowed that there was no statistical difference between patients with left-sided colon cancer and rectal cancer（P=0.840） and the survival of Stage Ⅲ patients between the two groups also showed no statistical difference (P=0.106). Cox regression analysis showed that both the pathologic types [HR=1.759, P=0.047] and tumor stage [HR=2.104, P<0.001] were independent predictive factors for OS of CRC patients. Conclusion: There were no differences in survival time between patients with left-sided colon cancer and rectal cancer. The pathologic types and tumor stage were factors influencing the OS of CRC patients.

Differences in biological behaviors and clinical treatment between colon and rectal cancers / 中国肿瘤生物治疗杂志

@#At present, more and more evidence shows that colon and rectal cancers are different diseases. There are many differences no matter in the epidemiology, anatomy and histology, molecular characteristics, transfer patterns, or clinical treatment methods, therapeutic effects and prognosis. In clinical treatment, it cann’t be considered as the same disease in general. Through the retrospective analysis of the three clinical studies of CALGB/SWOG 80405, CRYSTAL, and FIRE-3, it has been found that there were significant differences in the efficacy of cetuximab and bevacizumab in left and right colon cancer. Based on the above clinical trials, the National Cancer Institute for the United States (NCCN) for the first time includes the guidelines for the impact of primary sites on the treatment of colon cancer into guidelines in 2017. In the current era of advocating precision and individualized treatment, to clarify the pathogenesis, histological differences and clinical response to drugs in colon cancer and rectal cancer, can not only reduce the economic burden of patients, but also provide the most scientific basis for the precise treatment of patients gradually.