SPaRTAN, a computational framework for linking cell-surface receptors to transcriptional regulators

Ma, Xiao‐Jun; Somasundaram, Ashwin; Qi, Zengbiao; Singh, Harinder; Osmanbeyoglu, Hatice U.

doi:10.1101/2020.12.22.423961

Cited by 3 publications

(4 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A SPaRTAN model is utilized to decipher the connections between cell surface receptors and transcriptional factors, which are then used as predictions for future transcriptional factor (TF) activity. 19 The model includes a bilinear regression algorithm that learns an interaction matrix. SPaRTAN was applied to malignant peritoneal (MPeM) and pleural mesothelioma (MPM) tumors to obtain and analyze the regulatory states of CD8+ T cells.…”

Section: Abnormal Gene Expression In Mesotheliomamentioning

confidence: 99%

Multiple institutions’ research findings using the National Mesothelioma Virtual Bank

et al. 2022

View full text Add to dashboard Cite

Mesothelioma remains an under-researched cancerous disease due to the lack of high-quality patient samples and clinical information especially outcomes and asbestos exposure data. The National Mesothelioma Virtual Bank (NMVB) is a biobank in which mesothelioma annotated biospecimens can be made widely available to the research community. Here, we summarized the significant research findings from 20 publications that utilized the NMVB samples for novel biomarker and therapeutic discoveries. The results showed that the use of the NMVB resource was dispersed among a variety of basic science topics including, but not limited to, biomarkers, abnormal gene expression, and potential therapeutic targets. Positive biomarkers included several miRNAs and antibodies, HMGB1, ATG5, PIAS3, pancytokeratin and GATA3. Genes that had mutations or high/low levels of expression were BAP1, a human control gene of importance in this disease, as well as various cytokines, and checkpoint inhibitors TM4SF1, PKM2, ARHGDIA, COBLL1, WT1, FOXM1, and CD30. Treatments investigated include thiostrepton, interferon-�� gene, and Brentuximab. Publications reviewed indicated a significant impact of the NMVB resource utilized in significant studies focusing on biomarker and therapeutic discoveries, which can act as a model for rare diseases, especially in oncology.

show abstract

Section: Abnormal Gene Expression In Mesotheliomamentioning

confidence: 99%

Multiple institutions’ research findings using the National Mesothelioma Virtual Bank

et al. 2022

View full text Add to dashboard Cite

show abstract

“…We used the trained interaction matrix (W) to predict TF activity from the surface protein expression profile of a cell. We trained sample-specific and cell type-specific SPaRTAN models (17) and predicted cell-specific TF activities for each CITE-seq dataset (6)(7)(8)(9)(10). We also calculated the correlation between surface protein expression and TF activities across cells.…”

Section: Training Sample-specific and Cell Type-specific Spartan Modelsmentioning

confidence: 99%

“…We recently developed SPaRTAN (Single-cell Proteomic and RNA-based Transcription factor Activity Network) to mine the single-cell proteomic (scADT-seq) and corresponding scRNA-seq datasets obtained by CITE-seq. SPaRTAN links cell-specific expression of surface proteins with inferred transcription factor (TF) activities (5). Although the cell surface phenotype of immune cells can be readily determined by flow cytometry, signaling pathways downstream of cell surface receptors/co-receptors drive changes in transcription and chromatin states.…”

Section: Introductionmentioning

confidence: 99%

COVID-19db linkage maps of cell surface proteins and transcription factors in immune cells

Ramjattun

Gao

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The highly contagious SARS-CoV-2 and its associated disease (COVID-19) are a threat to global public health and economies. To develop effective treatments for COVID-19, we must understand the host cell types, cell states and regulators associated with infection and pathogenesis such as dysregulated transcription factors (TFs) and surface proteins, including signaling receptors. To link cell surface proteins with TFs, we recently developed SPaRTAN (Single-cell Proteomic and RNA-based Transcription factor Activity Network) by integrating parallel single-cell proteomic and transcriptomic data based on Cellular Indexing of Transcriptomes and Epitopes by sequencing (CITE-seq), which contains gene cis-regulatory information. We apply SPaRTAN to CITE-seq datasets from patients with varying degrees of COVID-19 severity and healthy controls to identify the associations between surface proteins and TFs in host immune cells. Here, we present COVID-19db of Immune Cell States (https://covid19db.streamlit.app/), a web server containing cell surface protein expression, SPaRTAN-inferred TF activities, and their associations with major host immune cell types. The data include four high-quality COVID-19 CITE-seq datasets with a toolset for user-friendly data analysis and visualization. We provide interactive surface protein and TF visualizations across major immune cell types for each dataset, allowing comparison between various patient severity groups for the discovery of potential therapeutic targets and diagnostic biomarkers.

show abstract

“…For statistical evaluation, we computed the mean Spearman correlation between predicted and measured gene expression profiles on the testing set (see Methods). CITRUS achieved significantly better performance than a regularized bilinear regression algorithm called affinity regression (AR) (20)(21)(22) that was trained independently for each cancer type. and explain gene expression across tumors in terms of somatic alteration status and presence of TF binding sites based on a pan-cancer ATAC-seq atlas (Fig.…”

Section: Pan-cancer Modeling Of Transcriptional Programsmentioning

confidence: 99%

Interpretable deep learning for chromatin-informed inference of transcriptional programs driven by somatic alterations across cancers

Tao

Laliotis

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Cancer is a disease of gene dysregulation, where cells acquire somatic and epigenetic alterations that drive aberrant cellular signaling. These alterations adversely impact transcriptional programs and cause profound changes in gene expression. Ultimately, interpreting patient somatic alterations within context-speciﬁc regulatory programs will facilitate personalized therapeutic decisions for each individual. Towards this goal, we develop a partially interpretable neural network model with encoder-decoder architecture, called Chromatin-informed Inference of Transcriptional Regulators Using Self-attention mechanism (CITRUS), to model the impact of somatic alterations on cellular states and further onto downstream gene expression programs. The encoder module employs a self-attention mechanism to model the contextual impact of somatic alterations in a tumor-specific manner. Furthermore, the model uses a layer of hidden nodes to explicitly represent the state of transcription factors (TFs), and the decoder learns the relationships between TFs and their target genes guided by the sparse prior based on TF binding motifs in the open chromatin regions of tumor samples. We apply CITRUS to genomic, mRNA sequencing and ATAC-seq data from tumors of 17 cancer types profiled by The Cancer Genome Atlas. Our computational framework enables us to share information across tumors to learn patient-specific TF activities, revealing regulatory program similarities and differences between and within tumor types. We show that CITRUS not only outperforms the competing models in predicting RNA expression, but also yields biological insights in delineating TFs associated with somatic alterations in individual tumors. We also validate the differential activity of TFs associated with mutant PIK3CA in breast cancer cell line and xenograft models using a panel of PI3K pathway inhibitors.

show abstract

SPaRTAN, a computational framework for linking cell-surface receptors to transcriptional regulators

Cited by 3 publications

References 52 publications

Multiple institutions’ research findings using the National Mesothelioma Virtual Bank

Multiple institutions’ research findings using the National Mesothelioma Virtual Bank

COVID-19db linkage maps of cell surface proteins and transcription factors in immune cells

Interpretable deep learning for chromatin-informed inference of transcriptional programs driven by somatic alterations across cancers

Contact Info

Product

Resources

About