Deep Learning in LncRNAome: Contribution, Challenges, and Perspectives

Alam, Tanvir; Al-Absi, Hamada R. H.; Schmeier, Sebastian

doi:10.3390/ncrna6040047

Cited by 10 publications

(6 citation statements)

References 121 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GCN is expected to render high classification performance by employing the structural data. For example, GCN has shown promising results in finding the relationship between long non-coding RNAs and diseases ( Alam et al , 2020 ; Zhao et al, 2020 ). In phage classification, different phage genomes and contigs can share genes or proteins, which can be encoded in the graph of GCN.…”

Section: Methodsmentioning

confidence: 99%

Bacteriophage classification for assembled contigs using graph convolutional network

2021

View full text Add to dashboard Cite

Motivation Bacteriophages (aka phages), which mainly infect bacteria, play key roles in the biology of microbes. As the most abundant biological entities on the planet, the number of discovered phages is only the tip of the iceberg. Recently, many new phages have been revealed using high-throughput sequencing, particularly metagenomic sequencing. Compared to the fast accumulation of phage-like sequences, there is a serious lag in taxonomic classification of phages. High diversity, abundance and limited known phages pose great challenges for taxonomic analysis. In particular, alignment-based tools have difficulty in classifying fast accumulating contigs assembled from metagenomic data. Results In this work, we present a novel semi-supervised learning model, named PhaGCN, to conduct taxonomic classification for phage contigs. In this learning model, we construct a knowledge graph by combining the DNA sequence features learned by convolutional neural network and protein sequence similarity gained from gene-sharing network. Then we apply graph convolutional network to utilize both the labeled and unlabeled samples in training to enhance the learning ability. We tested PhaGCN on both simulated and real sequencing data. The results clearly show that our method competes favorably against available phage classification tools. Availability and implementation The source code of PhaGCN is available via: https://github.com/KennthShang/PhaGCN.

show abstract

Section: Methodsmentioning

confidence: 99%

Bacteriophage classification for assembled contigs using graph convolutional network

2021

View full text Add to dashboard Cite

show abstract

“…For both 5' and 3' UTR, the length (UTR ratio) was relatively high for mRNA transcripts compared to the lncRNA transcripts. The GC content in the genic region of lncRNA [50] and in the promoter region of lncRNA models [33] [48] are not as enriched as protein coding genes. But the UTR regions of lncRNA transcripts are more GC enriched than the mRNA transcripts (Figure 3a and 3b).…”

Section: B Sequence Patterns At the Utr Regions Of Lncrna And Mrna Transcriptsmentioning

confidence: 90%

LNCRI: Long Non-Coding RNA Identifier in Multiple Species

2021

Self Cite

View full text Add to dashboard Cite

The pervasive nature of long non-coding RNA (lncRNA) transcription in the mammalian genomes has changed our protein-centric view of genomes. But the identification of lncRNAs is an important task to discover their functional role in species. The rapid development of next-generation sequencing technology leveraged the opportunity to discover many lncRNA transcripts. However, the cost and time-consuming nature of transcriptomics verification techniques barred the research community from focusing on lncRNA identification. To overcome these challenges we developed LNCRI (Long Non-Coding RNA Identifier), a novel machine learning (ML)-based tool for the identification of lncRNA transcripts. We leveraged weighted k-mer, pseudo nucleotide composition, hexamer usage bias, Fickett score, information of open reading frame, UTR regions, and HMMER score as a feature set to develop LNCRI. LNCRI outperformed other existing models in the task of distinguishing lncRNA transcripts from protein-coding mRNA transcripts with high accuracy in human and mouse. LNCRI also outperformed the existing tools for cross-species prediction on chimpanzee, monkey, gorilla, orangutan, cow, pig, frog and zebrafish. We applied the SHAP algorithm to demonstrate the importance of most dominating features that were leveraged in the model. We believe our tool will support the research community to identify the lncRNA transcripts in a highly accurate manner.The benchmark datasets and source code are available in GitHub: http://github.com/smusleh/LNCRI.

show abstract

“…Deep learning is a subfield of machine learning that employs biology-inspired neural networks to learn and model the complicated associations between data and output for classification and prediction ( Tang et al, 2019 ). It has been studied for many different applications, such as cancer diagnostics ( Kleppe et al, 2021 ), medical image analysis ( Wiestler and Menze, 2020 ), multi-omics and big data analyses ( Krassowski et al, 2020 ; Haemmig et al, 2021 ; Mahmud et al, 2021 ), long noncoding RNA research ( Alam et al, 2020 ), and protein structural modeling and design ( Gao et al, 2020 ). Recently, deep learning was employed to identify senescent ECs ( Kusumoto et al, 2021 ).…”

Section: Recent Advances In Cellular Senescencementioning

confidence: 99%

Vascular Endothelial Senescence: Pathobiological Insights, Emerging Long Noncoding RNA Targets, Challenges and Therapeutic Opportunities

Sun

Feinberg

2021

Front. Physiol.

View full text Add to dashboard Cite

Cellular senescence is a stable form of cell cycle arrest in response to various stressors. While it serves as an endogenous pro-resolving mechanism, detrimental effects ensue when it is dysregulated. In this review, we introduce recent advances for cellular senescence and inflammaging, the underlying mechanisms for the reduction of nicotinamide adenine dinucleotide in tissues during aging, new knowledge learned from p16 reporter mice, and the development of machine learning algorithms in cellular senescence. We focus on pathobiological insights underlying cellular senescence of the vascular endothelium, a critical interface between blood and all tissues. Common causes and hallmarks of endothelial senescence are highlighted as well as recent advances in endothelial senescence. The regulation of cellular senescence involves multiple mechanistic layers involving chromatin, DNA, RNA, and protein levels. New targets are discussed including the roles of long noncoding RNAs in regulating endothelial cellular senescence. Emerging small molecules are highlighted that have anti-aging or anti-senescence effects in age-related diseases and impact homeostatic control of the vascular endothelium. Lastly, challenges and future directions are discussed including heterogeneity of endothelial cells and endothelial senescence, senescent markers and detection of senescent endothelial cells, evolutionary differences for immune surveillance in mice and humans, and long noncoding RNAs as therapeutic targets in attenuating cellular senescence. Accumulating studies indicate that cellular senescence is reversible. A better understanding of endothelial cellular senescence through lifestyle and pharmacological interventions holds promise to foster a new frontier in the management of cardiovascular disease risk.

show abstract

Deep Learning in LncRNAome: Contribution, Challenges, and Perspectives

Cited by 10 publications

References 121 publications

Bacteriophage classification for assembled contigs using graph convolutional network

Bacteriophage classification for assembled contigs using graph convolutional network

LNCRI: Long Non-Coding RNA Identifier in Multiple Species

Vascular Endothelial Senescence: Pathobiological Insights, Emerging Long Noncoding RNA Targets, Challenges and Therapeutic Opportunities

Contact Info

Product

Resources

About