Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

SignacX

Cell Type Identification and Discovery from Single Cell Gene Expression Data

An implementation of neural networks trained with flow-sorted gene expression data to classify cellular phenotypes in single cell RNA-sequencing data. See Chamberlain M et al. (2021) <doi:10.1101/2021.02.01.429207> for more details.

Functions (21)

CID.GetDistMat

Computes distance matrix from edge list

CID.IsUnique

Extracts unique elements

CID.LoadData

Load data file from directory

CID.LoadEdges

Load edges from edge list for single cell network

CID.Louvain

Detects community substructure by Louvain community detection

CID.Normalize

Library size normalize

CID.entropy

Normalized Shannon entropy-based "unclassified" assignment

CID.smooth

Smoothing function

CID.writeJSON

Writes JSON file for SPRING integration

GenerateLabels

Generates cellular phenotype labels

Genes_Of_Interest

Genes of interest for drug discovery / disease biology research

GetModels_HPCA

Loads neural network models from GitHub

GetTrainingData_HPCA

Loads bootstrapped HPCA training data from GitHub

KSoftImpute

KNN-based imputation

MASC

Mixed effect modeling

ModelGenerator

Generates an ensemble of neural network models.

SaveCountsToH5

Save count_matrix.h5 files for SPRING integration

Signac

Classification of cellular phenotypes in single cell data

SignacBoot

Generates bootstrapped single cell data

SignacFast

Fast classification of cellular phenotypes

get_colors

Get HEX colors

SignacX

Cell Type Identification and Discovery from Single Cell Gene Expression Data

v2.2.0

GPL-3

Authors

Mathew Chamberlain [aut, cre], Virginia Savova [aut], Richa Hanamsagar [aut], Frank Nestle [aut], Emanuele de Rinaldis [aut], Sanofi US [fnd]

Initial release

2021-02-24

SignacX

Functions (21)

SignacX

We don't support your browser anymore