Arisdakessian, C. | bioRxiv Science

bioRxiv2018

GranatumX: A community engaging and flexible software environment for single-cell analysis

We present GranatumX, a next-generation software environment for single-cell data analysis. GranatumX is inspired by the interactive web tool Granatum. It enables biologists to access the latest single-cell bioinformatics methods in a web-based graphical environment. It also offers software developers the opportunity to rapidly promote their own tools with others in customizable pipelines. The architecture of GranatumX allows for easy inclusion of plugin modules, named Gboxes, that wrap around bioinformatics tools written in various programming languages and on various platforms. GranatumX can be run on the cloud or private servers and generate reproducible results. It is a community-engaging, flexible, and evolving software ecosystem for scRNA-Seq analysis, connecting developers with bench scientists. GranatumX is freely accessible at http://garmiregroup.org/granatumx/app.

bioinformatics↗

bioRxiv2018

DeepImpute: an accurate, fast and scalable deep neural network method to impute single-cell RNA-Seq data

BackgroundSingle-cell RNA sequencing (scRNA-seq) offers new opportunities to study gene expression of tens of thousands of single cells simultaneously. However, a significant problem of current scRNA-seq data is the large fractions of missing values or \"dropouts\" in gene counts. Incorrect handling of dropouts may affect downstream bioinformatics analysis. As the number of scRNA-seq datasets grows drastically, it is crucial to have accurate and efficient imputation methods to handle these dropouts.\n\nMethodsWe present DeepImpute, a deep neural network based imputation algorithm. The architecture of DeepImpute efficiently uses dropout layers and loss functions to learn patterns in the data, allowing for accurate imputation.\n\nResultsOverall DeepImpute yields better accuracy than other publicly available scRNA-Seq imputation methods on experimental data, as measured by mean squared error or Pearsons correlation coefficient. Moreover, its efficient implementation provides significantly higher performance over the other methods as dataset size increases. Additionally, as a machine learning method, DeepImpute allows to use a subset of data to train the model and save even more computing time, without much sacrifice on the prediction accuracy.\n\nConclusionsDeepImpute is an accurate, fast and scalable imputation tool that is suited to handle the ever increasing volume of scRNA-seq data. The package is freely available at https://github.com/lanagarmire/DeepImpute

bioinformatics↗