iCTC: iCTC-identification of CTC

In krishan57gupta/iCTC: Identification of CTC in Blood Streams

iCTC-identification of CTC

Description

this package stats::predicts whether – is a CTC or not using various preprocessing techniques and machine learning

Usage

iCTC(cell_samples, cases = c(4, 5, 6))

Arguments

cell_samples,

can contain any number of peripheral blood cells, with atleast desired genes either in row or column

cases,

can contain any subset of (1,2,3,4,5,6,7,8,9) numbers, meaning of these numbers given below: 1-> Harmony_NB, 2-> Harmony_RF, 3-> Harmony_GBM 4-> PCA_NB, 5-> PCA_RF, 6-> PCA_GBM 7-> Original_NB, 8-> Original_RF, 9-> Original_GBM Harmony-> projects cells into a shared embedding in which cells group by cell type rather than dataset-specific conditions. PCA-> Principal component analysis (PCA) is a technique used to emphasize variation and bring out strong patterns in a dataset. Original means none of (Harmony, PCA). NB-> Naive Bayes(ML Model) RF-> Random Forest(ML Model) GBM-> Gradient Boosting Machine(ML Model)

Value

results, will retrun table of samples and predicted values corresponding cases which have given row conatins cases and column with sample names

Examples

library(devtools)
install_github("immunogenomics/harmony")
library(harmony)
cell_samples<-iCTC::raw_test_data$Clearcell_Polaris_sample_test
results<-iCTC(cell_samples=cell_samples, cases = c(4,5,6))
results$CTC_probabilistic_score

krishan57gupta/iCTC documentation built on Dec. 31, 2022, 12:33 p.m.