NetMix: A Network-Structured Mixture Model for Reduced-Bias Estimation of Altered Subnetworks

Reyna, Matthew A.; Chitra, Uthsav; Elyanow, Rebecca; Raphael, Benjamin J.

doi:10.1007/978-3-030-45257-5_11

Cited by 2 publications

(3 citation statements)

References 78 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous works reported that the scheme used by the popular jActiveModule algorithm to score active modules is biased toward large modules and suggested ways to alleviate this bias (Nikolayeva et al , 2018) (preprint: Reyna et al , 2020). Our study reports on a different bias that is prevalent in AMI solutions: their tendency to report non‐specific GO terms.…”

Section: Discussionmentioning

confidence: 99%

“…This additional layer of condition‐specific information is then used to detect modules that are relevant to the analyzed molecular profile (Mitra et al , 2013). A prominent class of such algorithms seek subnetworks that show a marked over‐representation of accrued node scores (Ideker et al , 2002; Mitra et al , 2013; preprint: Reyna et al , 2020). Modules detected by such methods are often called “ active modules ,” and following this terminology we refer to nodes’ scores as “ activity scores” and to the task of detecting active modules using such scores as Active Module Identification (AMI).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DOMINO: a network‐based active module identification algorithm with reduced rate of false calls

Levi

Elkon

Shamir

2021

Molecular Systems Biology

View full text Add to dashboard Cite

Algorithms for active module identification (AMI) are central to analysis of omics data. Such algorithms receive a gene network and nodes' activity scores as input and report subnetworks that show significant over-representation of accrued activity signal ("active modules"), thus representing biological processes that presumably play key roles in the analyzed conditions. Here, we systematically evaluated six popular AMI methods on gene expression and GWAS data. We observed that GO terms enriched in modules detected on the real data were often also enriched on modules found on randomly permuted data. This indicated that AMI methods frequently report modules that are not specific to the biological context measured by the analyzed omics dataset. To tackle this bias, we designed a permutation-based method that empirically evaluates GO terms reported by AMI methods. We used the method to fashion five novel AMI performance criteria. Last, we developed DOMINO, a novel AMI algorithm, that outperformed the other six algorithms in extensive testing on GE and GWAS data.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

DOMINO: a network‐based active module identification algorithm with reduced rate of false calls

Levi

Elkon

Shamir

2021

Molecular Systems Biology

View full text Add to dashboard Cite

show abstract

“…Conversely, methods for community detection are less established. There are a plethora of methods that detect cancer-associated submodules, that are connected subset of genes driving cancer [9,30], but they do not explain the structure of all the nodes that are not implicated in cancer. However, for completeness, we compared SBM-GNN performance with Hierarchical Hotnet (HHotNet) [9] to explore the performance of this class of methods (see Supplementary Materials).…”

Section: Comparison With State-of-the-art Cancer Driver Prediction Methodsmentioning

confidence: 99%

Discovering cancer driver genes and pathways using stochastic block model graph neural networks

Fanfani

Lió

et al. 2021

Preprint

View full text Add to dashboard Cite

The identification of genes and pathways responsible for the transformation of normal cellsinto malignant ones represents a pivotal step to understand the aetiology of cancer, to characterise progression and relapse, and to ultimately design targeted therapies. The advent of high-throughput omic technologies has enabled the discovery of a significant number of cancer driver genes, but recent genomic studies have shown these to be only necessary but not sufficient to trigger tumorigenesis. Since most biological processes are the results of the interaction of multiple genes, it is then conceivable that tumorigenesis is likely the result of the action of networks of cancer driver and non-driver genes. Here we take advantage of recent advances in graph neural networks, combined with well established statistical models of network structure, to build a new model, called Stochastic Block Model Graph Neural Network (SBM-GNN), which predicts cancer driver genes and cancer mediating pathways directly from high-throughput omic experiments. Experimental analysis of synthetic datasets showed that our model can correctly predict genes associated with cancer and recover relevant pathways, while outperforming other state-of-the-art methods. Finally, we used SBM-GNN to perform a pan-cancer analysis, where we found genes and pathways directly involved with the hallmarks of cancer controlling genome stability, apoptosis, immune response, and metabolism.

show abstract

NetMix: A Network-Structured Mixture Model for Reduced-Bias Estimation of Altered Subnetworks

Cited by 2 publications

References 78 publications

DOMINO: a network‐based active module identification algorithm with reduced rate of false calls

DOMINO: a network‐based active module identification algorithm with reduced rate of false calls

Discovering cancer driver genes and pathways using stochastic block model graph neural networks

Contact Info

Product

Resources

About