runSTG.RdRun STG to select a set of genes that separate cells with label.1 from label.2 (other labels)
runSTG(X, X.labels, label.1, label.2 = NULL, lambda = 1.5, n.runs = 5, return.model = T, python.use = "/usr/bin/python", GPU = "")
| X | matrix, normalized expression matrix of all cells in the dataset, genes are in rows, rownames must be gene names |
|---|---|
| X.labels | numeric vector, specify labels for each cell, must be 0 or 1 |
| label.1 | cell label to define markers for |
| label.2 | second cell label to for comparison, if NULL, use all other labels |
| lambda | numeric, regularization parameter that weights the number of selected genes, a larger lambda leads to fewer genes, default 1.5 |
| n.runs | integer, number of runs to run the model, default 5 |
| return.model | a logical value to indicate whether to return the actual model of STG |
| python.use | character string, the Python to use, default "/usr/bin/python" |
| GPU | which GPU to use, default '', using CPU |
a list of results:
a list of data.frame with markers for each DA region
a numeric vector showing mean accuracy for each DA region
a list of model for each DA region, each model contains:
cell names/indices used to train the model features used to train the model the selected features of the final run the linear prediction value for each cell from the model