The COVID-19 Drug and Gene Set Library

Kuleshov, Maxim V.; Stein, Daniel J.; Clarke, Daniel J B; Kropiwnicki, Eryk; Jagodnik, Kathleen M.; Bartal, Alon; Evangelista, John Erol; Hom, Jason; Cheng, Minxuan; Bailey, Allison; Zhou, Abigail; Ferguson, Laura B.; Lachmann, Alexander; Ma’ayan, Avi

doi:10.1016/j.patter.2020.100090

Cited by 70 publications

(69 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, we calculated correlations in R–TF target gene links predicted by scMLnet and NicheNet for a quantitative comparison. To this end, we applied scMLnet and NicheNet to the above scRNA-seq dataset of the BALF (GSE145926) to predict upstream regulators and pathways of a COVID-19-related gene set (500 genes up-regulated in A549 cells treated with SARS-CoV-2 at both 0.2 MOI and 2MOI concentrations) that was downloaded from the COVID-19 Gene and Drug Set Library [ 27 ] (GSE147507 dataset). This gene set was used as the target gene set of interest for input of NicheNet.…”

Section: Discussionmentioning

confidence: 99%

Inferring microenvironmental regulation of gene expression from single-cell RNA sequencing data using scMLnet with an application to COVID-19

Cheng

Zhang

et al. 2020

Briefings in Bioinformatics

View full text Add to dashboard Cite

Inferring how gene expression in a cell is influenced by cellular microenvironment is of great importance yet challenging. In this study, we present a single-cell RNA-sequencing data based multilayer network method (scMLnet) that models not only functional intercellular communications but also intracellular gene regulatory networks ( https://github.com/SunXQlab/scMLnet ). scMLnet was applied to a scRNA-seq dataset of COVID-19 patients to decipher the microenvironmental regulation of expression of SARS-CoV-2 receptor ACE2 that has been reported to be correlated with inflammatory cytokines and COVID-19 severity. The predicted elevation of ACE2 by extracellular cytokines EGF, IFN-γ or TNF-α were experimentally validated in human lung cells and the related signaling pathway were verified to be significantly activated during SARS-COV-2 infection. Our study provided a new approach to uncover inter-/intra-cellular signaling mechanisms of gene expression and revealed microenvironmental regulators of ACE2 expression, which may facilitate designing anti-cytokine therapies or targeted therapies for controlling COVID-19 infection. In addition, we summarized and compared different methods of scRNA-seq based inter-/intra-cellular signaling network inference for facilitating new methodology development and applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Inferring microenvironmental regulation of gene expression from single-cell RNA sequencing data using scMLnet with an application to COVID-19

Cheng

Zhang

et al. 2020

Briefings in Bioinformatics

View full text Add to dashboard Cite

show abstract

“…Two recent sources for the coronavirus-affected sets of human genes/proteins were used in this work: The COVID-19 Drug and Gene Set Library which provides a collection of drug and gene sets related to COVID-19 research aggregated from multiple sources using natural language processing techniques (downloaded on 24 September 2020) [ 54 ]. This set of genes/proteins is further referred to as the “Aggregated” set.…”

Section: Methodsmentioning

confidence: 99%

Network machine learning maps phytochemically rich “Hyperfoods” to fight COVID-19

et al. 2021

View full text Add to dashboard Cite

In this paper, we introduce a network machine learning method to identify potential bioactive anti-COVID-19 molecules in foods based on their capacity to target the SARS-CoV-2-host gene-gene (protein-protein) interactome. Our analyses were performed using a supercomputing DreamLab App platform, harnessing the idle computational power of thousands of smartphones. Machine learning models were initially calibrated by demonstrating that the proposed method can predict anti-COVID-19 candidates among experimental and clinically approved drugs (5658 in total) targeting COVID-19 interactomics with the balanced classification accuracy of 80–85% in 5-fold cross-validated settings. This identified the most promising drug candidates that can be potentially “repurposed” against COVID-19 including common drugs used to combat cardiovascular and metabolic disorders, such as simvastatin, atorvastatin and metformin. A database of 7694 bioactive food-based molecules was run through the calibrated machine learning algorithm, which identified 52 biologically active molecules, from varied chemical classes, including flavonoids, terpenoids, coumarins and indoles predicted to target SARS-CoV-2-host interactome networks. This in turn was used to construct a “food map” with the theoretical anti-COVID-19 potential of each ingredient estimated based on the diversity and relative levels of candidate compounds with antiviral properties. We expect this in silico predicted food map to play an important role in future clinical studies of precision nutrition interventions against COVID-19 and other viral diseases.

show abstract

“…1) The COVID-19 Drug and Gene Set Library which provides a collection of drug and gene sets related to COVID-19 research aggregated from multiple sources using natural language processing techniques (downloaded on 24/09/2020) [54].…”

Section: Coronavirus Target Proteins Aggregationmentioning

confidence: 99%

Network machine learning maps phytochemically-rich “Hyperfoods” to fight COVID-19

Laponogov

Gonzalez

Shepherd

et al. 2020

Preprint

View full text Add to dashboard Cite

In this paper, we introduce a network machine learning method to identify potential bioactive anti-COVID-19 molecules in foods based on their capacity to target the SARS-CoV-2-host gene-gene (protein-protein) interactome. Our experiments were run using a supercomputing DreamLab App platform, harnessing the idle computational power of thousands of smartphones. Machine learning models were initially calibrated by demonstrating that the proposed method can predict anti-COVID-19 candidates among experimental and clinically approved drugs (5658 in total) targeting COVID-19 interactomics with the balanced classification accuracy of 80-85% in 5-fold cross-validated settings. This identified the most promising drug candidates that can be potentially “repurposed” against COVID-19 including common drugs used to combat cardiovascular and metabolic disorders, such as simvastatin, atorvastatin and metformin. A database of 7694 bioactive food-based molecules was run through the calibrated machine-learning algorithm, which identified 52 biologically active molecules, from varied chemical classes, including flavonoids, terpenoids, coumarins and indoles predicted to target SARS-CoV-2-host interactome networks. This in turn was used to construct a “food map” with the theoretical anti-COVID-19 potential of each ingredient estimated based on the diversity and relative levels of candidate compounds with antiviral properties. We expect this in-silico predicted food map to play an important role in future clinical studies of precision nutrition interventions against COVID-19 and other viral diseases.

show abstract

The COVID-19 Drug and Gene Set Library

Cited by 70 publications

References 47 publications

Inferring microenvironmental regulation of gene expression from single-cell RNA sequencing data using scMLnet with an application to COVID-19

Inferring microenvironmental regulation of gene expression from single-cell RNA sequencing data using scMLnet with an application to COVID-19

Network machine learning maps phytochemically rich “Hyperfoods” to fight COVID-19

Network machine learning maps phytochemically-rich “Hyperfoods” to fight COVID-19

Contact Info

Product

Resources

About