ImReLnc: Identifying Immune-Related LncRNA Characteristics in Human Cancers Based on Heuristic Correlation Optimization

Role of long non-coding RNAs in cholangiocarcinoma: A systematic review and meta-analysis

BACKGROUND

Cholangiocarcinoma (CCA), as a rare malignancy of the biliary tree, has a poor prognosis most of the time. CCA is highly epigenetically regulated and several long non-coding RNAs (lncRNA) have been investigated to have a diagnostic and prognostic role in CCA. The current study aimed to assess the studies finding relevant lncRNAs in CCA systematically.

METHODS

International databases, including PubMed, Cochrane Library, and Embase, were comprehensively searched in order to identify studies investigating any lncRNA in CCA. After screening by title/abstract and full-text, necessary data were extracted. Random-effect meta-analysis was performed for pooling the areas under the curve (AUCs), specificity, and sensitivity of lncRNAs for the diagnosis of CCA.

RESULTS

A total of 33 studies were chosen to be included in the final analysis, comprised of 2677 patients. Meta-analysis of AUCs for evaluation of CCA resulted in pooled AUC of 0.79 (95% CI: 0.75-0.82; I2 = 69.11, p < .01). Additionally, overall sensitivity of 0.80 (95% CI 0.75-0.84) and specificity of 0.77 (95% CI: 0.68-0.84) were observed. Measurement of lncRANs in the assessment of CCA also improved overall survival significantly (effect size 1.61, 95% CI: 1.39-1.82). A similar result was found for progression-free survival (effect size 1.57, 95% CI: 1.20-1.93).

CONCLUSION

Based on our findings, lncRNAs showed promising results as biomarkers in the diagnosis of CCA since they had acceptable sensitivity and specificity, in addition to the fact that improved survival in this poor prognosis cancer. Further studies might be needed to address this issue and find the best clinically useful lncRNA.

Identification of associations between lncRNA and drug resistance based on deep learning and attention mechanism

Introduction

Abnormal lncRNA expression can lead to the resistance of tumor cells to anticancer drugs, which is a crucial factor leading to high cancer mortality. Studying the relationship between lncRNA and drug resistance becomes necessary. Recently, deep learning has achieved promising results in predicting biomolecular associations. However, to our knowledge, deep learning-based lncRNA-drug resistance associations prediction has yet to be studied.

Methods

Here, we proposed a new computational model, DeepLDA, which used deep neural networks and graph attention mechanisms to learn lncRNA and drug embeddings for predicting potential relationships between lncRNAs and drug resistance. DeepLDA first constructed similarity networks for lncRNAs and drugs using known association information. Subsequently, deep graph neural networks were utilized to automatically extract features from multiple attributes of lncRNAs and drugs. These features were fed into graph attention networks to learn lncRNA and drug embeddings. Finally, the embeddings were used to predict potential associations between lncRNAs and drug resistance.

Results

Experimental results on the given datasets show that DeepLDA outperforms other machine learning-related prediction methods, and the deep neural network and attention mechanism can improve model performance.

Dicsussion

In summary, this study proposes a powerful deep-learning model that can effectively predict lncRNA-drug resistance associations and facilitate the development of lncRNA-targeted drugs. DeepLDA is available at https://github.com/meihonggao/DeepLDA.