scholarly journals A comprehensive comparison of association estimators for gene network inference algorithms

2014 ◽  
Vol 30 (15) ◽  
pp. 2142-2149 ◽  
Author(s):  
Zeyneb Kurt ◽  
Nizamettin Aydin ◽  
Gökmen Altay
Keyword(s):  
Gene Network ◽  
Network Inference ◽  
Gene Network Inference ◽  
Inference Algorithms ◽  
Comprehensive Comparison

scholarly journals Netmes: Assessing Gene Network Inference Algorithms by Network-Based Measures

2014 ◽  
Vol 10 ◽  
pp. EBO.S13481 ◽  
Author(s):  
Gökmen Altay ◽  
Zeyneb Kurt ◽  
Matthias Dehmer ◽  
Frank Emmert-Streib
Keyword(s):  
Gene Network ◽  
Network Inference ◽  
Gene Network Inference ◽  
Inference Algorithms

scholarly journals Interpretable deep generative models for genomics

2021 ◽  
Author(s):  
Yongin Choi ◽  
Gerald Quon
Keyword(s):  
Dimensionality Reduction ◽  
Gene Network ◽  
Network Inference ◽  
Systematic Difference ◽  
Generative Models ◽  
Underlying Structure ◽  
Gene Network Inference ◽  
Inference Algorithms ◽  
Variational Autoencoder ◽  
Reduction Methods

Deep neural networks implementing generative models for dimensionality reduction have been extensively used for the visualization and analysis of genomic data. One of their key limitations is lack of interpretability: it is challenging to quantitatively identify which input features are used to construct the embedding dimensions, thus preventing insight into why cells are organized in a particular data visualization, for example. Here we present a scalable, interpretable variational autoencoder (siVAE) that is interpretable by design: it learns feature embeddings that guide the interpretation of the cell embeddings in a manner analogous to factor loadings of factor analysis. siVAE is as powerful and nearly as fast to train as the standard VAE but achieves full interpretability of the embedding dimensions. We exploit a number of connections between dimensionality reduction and gene network inference to identify gene neighborhoods and gene hubs, without the explicit need for gene network inference. Finally, we observe a systematic difference in the gene neighborhoods identified by dimensionality reduction methods and gene network inference algorithms in general, suggesting they provide complementary information about the underlying structure of the gene co-expression network.

scholarly journals Seidr: a gene meta-network calculation toolkit

2018 ◽  
Author(s):  
Bastian Schiffthaler ◽  
Alonso Serrano ◽  
Nathaniel Street ◽  
Nicolas Delhomme
Keyword(s):  
Gene Network ◽  
Network Inference ◽  
Differential Expression Analysis ◽  
Gene Interaction ◽  
Data Sets ◽  
Multiple Gene ◽  
Gene Network Inference ◽  
Inference Algorithms ◽  
Gene Network Analysis ◽  
Inference Methods

AbstractSummaryGene network analysis is a powerful tool to identify and prioritize candidate genes, especially from data sets where experimental design renders other approaches, such as differential expression analysis, limiting or infeasible. Numerous gene network inference algorithms have been published and are commonly individually applied in transcriptomics studies. It has, however, been shown that every algorithm is biased towards identifying specific types of gene interaction and that an ensemble of inference methods can reconstruct more accurate networks. This approach has been hindered by lack of an implementation to run and combine such combinations of inference algorithms. Here, we present Seidr: a toolkit to perform multiple gene network inferences and combine their results into a unified meta-network.Availability and implementationSeidr code is open-source, available from GitHub and also compiled in docker and singularity containers. It is implemented in C++ for fast computation and supports massive parallelisation through MPI. Documentation, tutorials and exemplary use are available from https://[email protected], [email protected]

scholarly journals DepEst: an R package of important dependency estimators for gene network inference algorithms

2017 ◽  
Author(s):  
Gökmen Altay ◽  
Zeyneb Kurt ◽  
Nejla Altay ◽  
Nizamettin Aydin
Keyword(s):  
Gene Network ◽  
Network Inference ◽  
R Package ◽  
Supplementary File ◽  
Main Process ◽  
Data Sets ◽  
Gene Network Inference ◽  
Inference Algorithms ◽  
Almost All ◽  
Access Link

AbstractGene network inference algorithms (GNI) are popular in bioinformatics area. In almost all GNI algorithms, the main process is to estimate the dependency (association) scores among the genes of the dataset.We present a bioinformatics tool, DepEst (Dependency Estimators), which is a powerful and flexible R package that includes 11 important dependency score estimators that can be used in almost all GNI Algorithms. DepEst is the first bioinformatics package that includes such a large number of estimators that runs both in parallel and serial.DepEst is currently available at https://github.com/altayg/Depest. Package access link, instructions, various workflows and example data sets are provided in the supplementary file.

scholarly journals SeaBase: A Multispecies Transcriptomic Resource and Platform for Gene Network Inference

2014 ◽  
Vol 54 (2) ◽  
pp. 250-263 ◽  
Author(s):  
A. H. L. Fischer ◽  
D. Mozzherin ◽  
A. M. Eren ◽  
K. D. Lans ◽  
N. Wilson ◽  
...  
Keyword(s):  
Gene Network ◽  
Network Inference ◽  
Gene Network Inference ◽  
Transcriptomic Resource
Sign in / Sign up

Export Citation Format

Share Document