Bioinformatics · 2022 · 106 citations · 35 references
Life SciencesBioinformaticsMolecular BiologyGene ExpressionGene Regulatory NetworksTranscriptional RegulationBulk TranscriptomicsGraph-based LearningRegulatory Network InferenceSingle-cell GenomicsSingle-cell Rna Sequencing AnalysisSingle-cell TranscriptomicsCausal Network InferenceGene Regulatory InteractionsGraph Attention NetworksLink PredictionLow-dimensional EmbeddingsSingle-cell Gene Expression ProfilingSingle-cell Network InferenceSingle-cell Regulatory Network Inference
MOTIVATION: Single-cell RNA sequencing (scRNA-seq) data provides unprecedented opportunities to reconstruct gene regulatory networks (GRNs) at fine-grained resolution. Numerous unsupervised or self-supervised models have been proposed to infer GRN from bulk RNA-seq data, but few of them are appropriate for scRNA-seq data under the circumstance of low signal-to-noise ratio and dropout. Fortunately, the surging of TF-DNA binding data (e.g. ChIP-seq) makes supervised GRN inference possible. We regard supervised GRN inference as a graph-based link prediction problem that expects to learn gene low-dimensional vectorized representations to predict potential regulatory interactions. RESULTS: In this paper, we present GENELink to infer latent interactions between transcription factors (TFs) and target genes in GRN using graph attention network. GENELink projects the single-cell gene expression with observed TF-gene pairs to a low-dimensional space. Then, the specific gene representations are learned to serve for downstream similarity measurement or causal inference of pairwise genes by optimizing the embedding space. Compared to eight existing GRN reconstruction methods, GENELink achieves comparable or better performance on seven scRNA-seq datasets with four types of ground-truth networks. We further apply GENELink on scRNA-seq of human breast cancer metastasis and reveal regulatory heterogeneity of Notch and Wnt signalling pathways between primary tumour and lung metastasis. Moreover, the ontology enrichment results of unique lung metastasis GRN indicate that mitochondrial oxidative phosphorylation (OXPHOS) is functionally important during the seeding step of the cancer metastatic cascade, which is validated by pharmacological assays. AVAILABILITY AND IMPLEMENTATION: The code and data are available at https://github.com/zpliulab/GENELink. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
35
Damian Szklarczyk, Annika L. Gable, David Lyon et al. · Nucleic Acids Research · 2018 · 19.2K citations · Full text
SCENIC: single-cell regulatory network inference and clustering
Sara Aibar, Carmen Bravo González‐Blas, Thomas Moerman et al. · Nature Methods · 2017 · 6.9K citations · Full text
Dimensionality reduction for visualizing single-cell data using UMAP
Étienne Becht, Leland McInnes, John Healy et al. · Nature Biotechnology · 2018 · 5.8K citations
Expanded encyclopaedias of DNA elements in the human and mouse genomes
Federico Abascal, Reyes Acosta, Nicholas J. Addleman et al. · Nature · 2020 · 2.6K citations · Full text
Inferring Regulatory Networks from Expression Data Using Tree-Based Methods
Vân Anh Huynh‐Thu, Alexandre Irrthum, Louis Wehenkel et al. · PLoS ONE · 2010 · 2.3K citations · Full text