Position-wise binding preference is important for miRNA target site prediction

A deep learning method to integrate extracelluar miRNA with mRNA for cancer studies

MOTIVATION

Extracellular miRNAs (exmiRs) and intracellular mRNAs both can serve as promising biomarkers and therapeutic targets for various diseases. However, exmiR expression data is often noisy, and obtaining intracellular mRNA expression data usually involves intrusive procedures. To gain valuable insights into disease mechanisms, it is thus essential to improve the quality of exmiR expression data and develop noninvasive methods for assessing intracellular mRNA expression.

RESULTS

We developed CrossPred, a deep-learning multi-encoder model for the cross-prediction of exmiRs and mRNAs. Utilizing contrastive learning, we created a shared embedding space to integrate exmiRs and mRNAs. This shared embedding was then used to predict intracellular mRNA expression from noisy exmiR data and to predict exmiR expression from intracellular mRNA data. We evaluated CrossPred on three types of cancers and assessed its effectiveness in predicting the expression levels of exmiRs and mRNAs. CrossPred outperformed the baseline encoder-decoder model, exmiR or mRNA-based models, and variational autoencoder models. Moreover, the integration of exmiR and mRNA data uncovered important exmiRs and mRNAs associated with cancer. Our study offers new insights into the bidirectional relationship between mRNAs and exmiRs.

AVAILABILITY AND IMPLEMENTATION

The datasets and tool are available at https://doi.org/10.5281/zenodo.13891508.

A computational modeling of pri-miRNA expression

MicroRNAs (miRNAs) play crucial roles in gene regulation. Most studies focus on mature miRNAs, which leaves many unknowns about primary miRNAs (pri-miRNAs). To fill the gap, we attempted to model the expression of pri-miRNAs in 1829 primary cell types, cell lines, and tissues in this study. We demonstrated that the expression of pri-miRNAs can be modeled well by the expression of specific sets of mRNAs, which we termed their associated mRNAs. These associated mRNAs differ from their corresponding target mRNAs and are enriched with specific functions. Most associated mRNAs of a miRNA are shared across conditions, while on average, about one-fifth of the associated mRNAs are condition-specific. Our study shed new light on understanding miRNA biogenesis and general gene transcriptional regulation.

The Mechanisms of miRNAs on Target Regulation and their Recent Advances in Atherosclerosis

miRNAs are crucial regulators in a variety of physiological and pathological processes, while their regulation mechanisms were usually described as negatively regulating gene expression by targeting the 3'-untranslated region(3'-UTR) of target gene miRNAs through seed sequence in tremendous studies. However, recent evidence indicated the existence of non-canonical mechanisms mediated by binding other molecules besides mRNAs. Additionally, accumulating evidence showed that functions of intracellular and intercellular miRNAs exhibited spatiotemporal patterns. Considering that detailed knowledge of the miRNA regulating mechanism is essential for understanding the roles and further clinical applications associated with their dysfunction and dysregulation, which is complicated and not fully clarified. Based on that, we summarized the recently reported regulation mechanisms of miRNAs, including recognitions, patterns of actions, and chemical modifications. And we also highlight the novel findings of miRNAs in atherosclerosis progression researches to provide new insights for non-coding RNA-based therapy in intractable diseases.

Genome-wide association studies identify miRNA-194 as a prognostic biomarker for gastrointestinal cancer by targeting ATP6V1F, PPP1R14B, BTF3L4 and SLC7A5

Background

The dysregulated genes and miRNAs in tumor progression can be used as biomarkers for tumor diagnosis and prognosis. However, the biomarkers for predicting the clinical outcome of gastrointestinal cancer (GIC) are still scarce.

Methods

Genome-wide association studies were performed to screen optimal prognostic miRNA biomarkers. RNA-seq, Ago-HITS-CLIP-seq, western blotting and qRT-PCR assays were conducted to identify target genes of miR-194. Genome-wide CRISPR-cas9 proliferation screening analysis were conducted to distinguish passenger gene and driver gene.

Results

A total of 9 prognostic miRNAs for GIC were identified by global microRNA expression analysis. Among them, miR-194 was the only one miRNA that significantly associated with overall survival, disease-specific survival and progress-free interval in both gastric, colorectal and liver cancers, indicating miR-194 was an optimal prognostic biomarker for GIC. RNA-seq analysis confirmed 18 conservative target genes of miR-194. Four of them, including ATP6V1F, PPP1R14B, BTF3L4 and SLC7A5, were directly targeted by miR-194 and required for cell proliferation. Cell proliferation assay validated that miR-194 inhibits cell proliferation by targeting ATP6V1F, PPP1R14B, BTF3L4 and SLC7A5 in GIC.

Conclusion

In summary, miR-194 is an optimal biomarker for predicting the outcome of GIC. Our finding highlights that miR-194 exerts a tumor-suppressive role in digestive system cancers by targeting ATP6V1F, PPP1R14B, BTF3L4 and SLC7A5.

Two lncRNAs, MACC1-AS1 and UCA1, co-mediate the expression of multiple mRNAs through interaction with individual miRNAs in breast cancer cells

BACKGROUND

Increasing studies have shown that lncRNAs often play roles through interaction with miRNAs to control gene expression by inhibiting translation or facilitating degradation of target mRNAs. Here, we report that two lncRNAs, MACC1-AS1 and UCA1 are coordinately expressed in breast cancer cells and share the ability to interact with multiple miRNAs to mediate the expression of different genes.

METHODS

Targetscan, starBase and miRDB databases were used to predict the relationships of MACC1-AS1/UCA1-miRNA-mRNA network. qRT-PCR, and RNA sequencing were used to study the differential expression of lncRNAs and miRNA-targeted genes in breast cancer cells. RIP, RNA pull-down and luciferase assays were performed to confirm the molecular interactions of MACC1-AS1 or UCA1 with predicted miRNAs. The role of lncRNA-mediated miRNA-mRNA interactions in cell proliferation was examined by MTT assays following loss-of-function and gain-of-function effects.

RESULTS

We identified a lncRNA-miRNA-mRNA regulatory network in breast cancer cells, in which a number of mRNAs can be co-regulated by MACC1-AS1 and UCA1 lncRNAs. Each lncRNA possesses the capacity as a ceRNA to compete with various mRNA-targeting miRNAs. Interaction of MACC1-AS1 or UCA1 with individual miRNAs is able to increase the expression of the same target mRNAs, such as TBL1X and MEF2D, thus affecting cancer-cell growth phenotype.

CONCLUSIONS

Our study suggests that in each cell type, there is a balance of interactions between certain lncRNAs and miRNAs. Disrupting the balance would eventually affect the expression of miRNA-targeted genes and cell proliferation.

A deep learning method for miRNA/isomiR target detection

Accurate identification of microRNA (miRNA) targets at base-pair resolution has been an open problem for over a decade. The recent discovery of miRNA isoforms (isomiRs) adds more complexity to this problem. Despite the existence of many methods, none considers isomiRs, and their performance is still suboptimal. We hypothesize that by taking the isomiR-mRNA interactions into account and applying a deep learning model to study miRNA-mRNA interaction features, we may improve the accuracy of miRNA target predictions. We developed a deep learning tool called DMISO to capture the intricate features of miRNA/isomiR-mRNA interactions. Based on tenfold cross-validation, DMISO showed high precision (95%) and recall (90%). Evaluated on three independent datasets, DMISO had superior performance to five tools, including three popular conventional tools and two recently developed deep learning-based tools. By applying two popular feature interpretation strategies, we demonstrated the importance of the miRNA regions other than their seeds and the potential contribution of the RNA-binding motifs within miRNAs/isomiRs and mRNAs to the miRNA/isomiR-mRNA interactions.