RunParallelICP: Run ICP runs parallerly

In elolab/ILoReg: ILoReg: a tool for high-resolution cell population identification from scRNA-Seq data

Run ICP runs parallerly

Description

This functions runs in parallel L ICP runs, which is the computational bottleneck of ILoReg. With ~ 3,000 cells this step should be completed in ~ 2 h and ~ 1 h with 3 and 12 logical processors (threads), respectively.

Usage

RunParallelICP.SingleCellExperiment(
  object,
  k,
  d,
  L,
  r,
  C,
  reg.type,
  max.iter,
  threads,
  icp.batch.size
)

## S4 method for signature 'SingleCellExperiment'
RunParallelICP(
  object,
  k = 15,
  d = 0.3,
  L = 200,
  r = 5,
  C = 0.3,
  reg.type = "L1",
  max.iter = 200,
  threads = 0,
  icp.batch.size = Inf
)

Arguments

object	An object of SingleCellExperiment class.
k	A positive integer greater or equal to 2, denoting the number of clusters in Iterative Clustering Projection (ICP). Decreasing k leads to smaller cell populations diversity and vice versa. Default is 15.
d	A numeric greater than 0 and smaller than 1 that determines how many cells n are down- or oversampled from each cluster into the training data (n=N/k*d), where N is the total number of cells, k is the number of clusters in ICP. Increasing above 0.3 leads greadually to smaller cell populations diversity. Default is 0.3.
L	A positive integer greater than 1 denoting the number of the ICP runs to run. Default is 200. Increasing recommended with a significantly larger sample size (tens of thousands of cells). Default is 200.
r	A positive integer that denotes the number of reiterations performed until the ICP algorithm stops. Increasing recommended with a significantly larger sample size (tens of thousands of cells). Default is 5.
C	A positive real number denoting the cost of constraints violation in the L1-regularized logistic regression model from the LIBLINEAR library. Decreasing leads to more stringent feature selection, i.e. less genes are selected that are used to build the projection classifier. Decreasing to a very low value (~ 0.01) can lead to failure to identify central cell populations. Default 0.3.
reg.type	"L1" or "L2". L2-regularization was not investigated in the manuscript, but it leads to a more conventional outcome (less subpopulations). Default is "L1".
max.iter	A positive integer that denotes the maximum number of iterations performed until ICP stops. This parameter is only useful in situations where ICP converges extremely slowly, preventing the algorithm to run too long. In most cases, reaching the number of reiterations (r=5) terminates the algorithm. Default is 200.
threads	A positive integer that specifies how many logical processors (threads) to use in parallel computation. Set 1 to disable parallelism altogether or 0 to use all available threas except one. Default is 0.
icp.batch.size	A positive integer that specifies how many cells to randomly select for each ICP run from the complete data set. This is a new feature intended to speed up the process with larger data sets. Default is Inf, which means using all cells.

Value

an object of SingleCellExperiment class

Examples

library(SingleCellExperiment)
sce <- SingleCellExperiment(assays = list(logcounts = pbmc3k_500))
sce <- PrepareILoReg(sce)
## These settings are just to accelerate the example, use the defaults.
sce <- RunParallelICP(sce,L=2,threads=1,C=0.1,r=1,k=5)

elolab/ILoReg documentation built on March 28, 2022, 1:17 a.m.