Will generate a trajectory using FateID.
ti_fateid(reclassify = TRUE, clthr = 0.9, nbfactor = 5L, q = 0.75, k = 3L, m = "tsne", minnr = 5L, minnrh = 10L, trthr = 0.4, force = FALSE)
Whether to reclassify the cell grouping. Default: TRUE. Format: logical.
Real number between zero and one. This is the threshold for the fraction of random forest votes required to assign a cell not contained within the target clusters to one of these clusters. The value of this parameter should be sufficiently high to only reclassify cells with a high-confidence assignment. Default value is 0.9. Domain: U(0.1, 1). Default: 0.9. Format: numeric.
Positive integer number. Determines the number of trees grown
for each random forest. The number of trees is given by the number of columns
of th training set multiplied by
Q real value between zero and one. This number specifies a threshold used for feature selection based on importance sampling. A reduced expression table is generated containing only features with an importance larger than the q-quantile for at least one of the classes (i. e. target clusters). Default value is 0.75. Domain: U(0, 1). Default: 0.75. Format: numeric.
Number of dimensions. Domain: U(2, 100). Default: 3. Format: integer.
Dimensionality reduction method to use. Can be tsne, cmd, dm or lle. Domain: tsne, cmd, dm, lle. Default: tsne. Format: character.
Integer number of cells per target cluster to be selected for
classification (test set) in each round of training. For each target cluster,
Integer number of cells from the training set used for
classification. From each training set, the
Real value representing the threshold of the fraction of random
forest votes required for the inclusion of a given cell for the computation of
the principal curve. If
Do not use! This is a parameter to force FateID to run on benchmark datasets where not enough end groups are present. Default: FALSE. Format: logical.
A TI method wrapper to be used together with
Herman, J.S., Sagar, Grün, D., 2018. FateID infers cell fate bias in multipotent progenitors from single-cell RNA-seq data. Nature Methods 15, 379–386.