Down-regulation of EPB41L4A-AS1 mediated the brain aging and neurodegenerative diseases via damaging synthesis of NAD+ and ATP

Yang, Tingpeng; Wang, Yanzhi; Liao, Weijie; Zhang, Shikuan; Wang, Songmao; Xu, Ning; Xie, Wenrui; Luo, Cheng; Wang, Yangyang; Wang, Ziqiang; Zhang, Y

doi:10.21203/rs.3.rs-927236/v1

Cited by 1 publication

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Long non-coding RNAs (lncRNAs) are a class of non-coding RNAs usually longer than 200 ribonucleotides in length [1] and microRNAs (miRNAs) are a class of short non-coding RNAs consisting of approximately 22 ribonucleotides [2] [3]. In recent years, an increasing number of studies have shown that lncRNA and miRNA play significant regulatory roles in gene expression [4] [5], cancer development [6], aging [7], neurodegenerative diseases [8], etc., where lncRNA-miRNA interaction is one of the key mechanisms [9] [10]. RNA sequencing technology [11] reveals numerous novel RNA sequences, including many lncRNAs and miRNAs.…”

Section: Introductionmentioning

confidence: 99%

Introducing TEC-LncMir for practical prediction of lncRNA-miRNA interactions through deep learning of RNA sequence data

Wang,

Yang,

2024

Preprint

Self Cite

View full text Add to dashboard Cite

The interactions between long non-coding RNA (lncRNA) and microRNA (miRNA) play critical roles in many life processes, highlighting the necessity to further advance the performance of the state-of-the-art models. Here, we introduced a novel approach, named TEC-LncMir, for lncRNA-miRNA interaction prediction based on Transformer Encoder and convolutional neural networks (CNNs). TEC-LncMir treats both lncRNA and miRNA sequences as natural languages and encodes them using the Transformer Encoder. It then combines the meaningful representations of a pair of microRNA and lncRNA into a contact map (a three-dimensional array). Afterwards, TEC-LncMir treats the contact map as a multi-channel image, utilizes a four-layer CNN to extract the contact map's features, and then uses these features to predict the interaction between the pair of lncRNA and miRNA. We applied a series of comparative experiments to demonstrate that TEC-LncMir significantly improves lncRNA-miRNA interaction prediction, compared with existing state-of-the-art models. We also trained TEC-LncMir utilizing a large training dataset, and as expected, TEC-LncMir achieves unprecedented performance. Moreover, our approach is the first practical approach for practical miRNA-lncRNA interaction analysis. Specifically, we utilized TEC-LncMir to find microRNAs interacting with lncRNA NEAT1, where NEAT1 performs as a competitive endogenous RNA of the microRNAs’ targets (corresponding mRNAs) in the cellular context. We also demonstrated the regulatory mechanism of NEAT1 in Alzheimer’s disease via transcriptome analysis and sequence alignment analysis. These results reveal a potential regulatory mechanism of NEAT1 in Alzheimer’s disease and show that TEC-LncMir performs well in applications. Our results demonstrate the effectivity of TEC-LncMir and take a significant step forward in lncRNA-miRNA interaction prediction.

show abstract