Analysing the meta-interaction between pathways by gene set topological impact analysis

Shu, Yan; Chi, Xu; Chang, Xiao; Tian, Mengliang

doi:10.1186/s12864-020-07148-y

Cited by 4 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, The B group vitamins help convert carbohydrates into energy in CM ( Calderón-Ospina and Nava-Mesa, 2020 ). Moreover, such a pathway interdependence is asymmetric due to upstream/downstream relationships between pathways ( Yan et al , 2020 ). Therefore, the characterization of asymmetric interdependences among pathways would enhance the prediction task in the context that a compound participates in uncertain numbers of metabolic pathways.…”

Section: Introductionmentioning

confidence: 99%

MLGL-MP: a Multi-Label Graph Learning framework enhanced by pathway interdependence for Metabolic Pathway prediction

Zhao

Zhu

et al. 2022

Bioinformatics

View full text Add to dashboard Cite

Motivation During lead compound optimization, it is crucial to identify pathways where a drug-like compound is metabolized. Recently, machine learning-based methods have achieved inspiring progress to predict potential metabolic pathways for drug-like compounds. However, they neglect the knowledge that metabolic pathways are dependent on each other. Moreover, they are inadequate to elucidate why compounds participate in specific pathways. Results To address these issues, we propose a novel Multi-Label Graph Learning framework of Metabolic Pathway prediction boosted by pathway interdependence, called MLGL-MP, which contains a compound encoder, a pathway encoder and a multi-label predictor. The compound encoder learns compound embedding representations by graph neural networks. After constructing a pathway dependence graph by re-trained word embeddings and pathway co-occurrences, the pathway encoder learns pathway embeddings by graph convolutional networks. Moreover, after adapting the compound embedding space into the pathway embedding space, the multi-label predictor measures the proximity of two spaces to discriminate which pathways a compound participates in. The comparison with state-of-the-art methods on KEGG pathways demonstrates the superiority of our MLGL-MP. Also, the ablation studies reveal how its three components contribute to the model, including the pathway dependence, the adapter between compound embeddings and pathway embeddings, as well as the pre-training strategy. Furthermore, a case study illustrates the interpretability of MLGL-MP by indicating crucial substructures in a compound, which are significantly associated with the attending metabolic pathways. It is anticipated that this work can boost metabolic pathway predictions in drug discovery. Availability and implementation The code and data underlying this article are freely available at https://github.com/dubingxue/MLGL-MP.

show abstract

Section: Introductionmentioning

confidence: 99%

MLGL-MP: a Multi-Label Graph Learning framework enhanced by pathway interdependence for Metabolic Pathway prediction

Zhao

Zhu

et al. 2022

Bioinformatics

View full text Add to dashboard Cite

show abstract

Metabolomic data presents challenges for epidemiological meta-analysis: a case study of childhood body mass index from the ECHO consortium

Prince,

Liang,

Tan

et al. 2024

Metabolomics

View full text Add to dashboard Cite

Esm-1 mediates transcriptional polarization associated with diabetic kidney disease

Gaudet

Zheng

Kambham

et al. 2023

Preprint

View full text Add to dashboard Cite

BackgroundEsm-1, endothelial cell-specific molecule-1, is a susceptibility gene for diabetic kidney disease (DKD) and is a cytokine- and glucose-regulated, secreted proteoglycan, that is notably expressed in kidney and attenuates inflammation and albuminuria.Esm1has restricted expression at the vascular tip during development but little is known about its expression pattern in mature tissues, and its precise effects in diabetes.MethodsWe utilized publicly available single-cell RNA sequencing data to explore the characteristics ofEsm1expression in 27,786 renal endothelial cells obtained from four adult human and three mouse databases. We validated our findings using bulk transcriptome data from an additional 20 healthy subjects and 41 patients with DKD and using RNAscope. Using correlation matrices, we relate Esm1 expression to the glomerular transcriptome and evaluated these matrices with systemic over-expression of Esm-1.ResultsIn both mice and humans,Esm1is expressed in a subset of all renal endothelial cell types and represents a minority of glomerular endothelial cells. In patients,Esm1(+) cells exhibit a highly conserved enrichment for blood vessel development genes. With diabetes, these cells are fewer in number and profoundly shift expression to reflect chemotaxis pathways. Analysis of these gene sets highlight candidate genes such asIgfbp5for cross talk between cell types. We also find that diabetes induces correlations in the expression of large clusters of genes, within cell type-enriched transcripts.Esm1significantly correlates with a majority genes within these clusters, delineating a glomerular transcriptional polarization reflected by the magnitude ofEsm1deficiency. In diabetic mice, these gene clusters linkEsm1expression to albuminuria, and over-expression of Esm-1 reverses the expression pattern in many of these genes.ConclusionsA comprehensive analysis of single cell and bulk transcriptomes demonstrates that diabetes correlates with lowerEsm1expression and with changes in the functional characterization ofEsm1(+) cells.Esm1is both a marker for glomerular transcriptional polarization, and a mediator that re-orients the transcriptional program in DKD.

show abstract

Analysing the meta-interaction between pathways by gene set topological impact analysis

Cited by 4 publications

References 19 publications

MLGL-MP: a Multi-Label Graph Learning framework enhanced by pathway interdependence for Metabolic Pathway prediction

MLGL-MP: a Multi-Label Graph Learning framework enhanced by pathway interdependence for Metabolic Pathway prediction

Metabolomic data presents challenges for epidemiological meta-analysis: a case study of childhood body mass index from the ECHO consortium

Esm-1 mediates transcriptional polarization associated with diabetic kidney disease

Contact Info

Product

Resources

About