FSCseq_predict_workflow: Minimal workflow for FSCseq_predict

In DavidKLim/FSCseq: Feature Selection and Clustering of RNA-seq Count Data

Description

Full FSCseq workflow based on minimal working defaults

Usage

FSCseq_predict_workflow(
  res,
  X_covar_train = NULL,
  cts_train,
  SF_train = NULL,
  batch_train = NULL,
  X_covar_pred = NULL,
  cts_pred,
  batch_pred = NULL,
  coding = "reference"
)

Arguments

res	Fitted FSCseq result object.
X_covar_train	Optional covariate matrix for training samples (optional additional covariates, except batch)
cts_train	Counts matrix of training samples.
SF_train	Size factors of training samples (optional. If not supplied, can be accessed from res)
batch_train	Batch information for training samples (optional).
X_covar_pred	Optional covariate matrix for prediction samples (optional additional covariates, except batch)
cts_pred	Counts matrix of prediction samples. Should be same dimension as cts_train
batch_pred	Batch information for prediction samples (optional). In estimating the new prediction batch effect, we recommend users to have at least 3-5 samples per cluster per batch for accurate estimation.
coding	Coding scheme for batch (categorical). Default is reference coding.

Value

list with processed.dat.pred (processed prediction data), and prediction results

Author(s)

David K. Lim, [e-mail]

References

https://github.com/DavidKLim/FSCseq

Examples

sim.dat = simulateData(B=1, g=10000, K=2, n=50, LFCg=1, pDEg=0.05, beta0=12, phi0=0.35, nsims=1, save_file=F)[[1]]
## Not run: res = FSCseq_workflow(cts=sim.dat$cts, K_search=c(2:3), lambda_search=c(1.0, 1.5), alpha_search=c(0.1, 0.2))
## Not run: pred_results = FSCseq_predict_workflow(res=res, cts_train=sim.dat$cts_train, batch_train=batch, cts_pred=sim.dat$cts_pred, batch_pred=batch_pred)

DavidKLim/FSCseq documentation built on Dec. 12, 2021, 3:46 a.m.