SpectralTAD_Par {SpectralTAD} | R Documentation |
Parallelized Hierarchical Spectral Clustering of TADs
SpectralTAD_Par(cont_list, chr, levels = 1, qual_filter = FALSE, z_clust = TRUE, eigenvalues = 2, min_size = 5, resolution = "auto", grange = FALSE, gap_threshold = 1, cores = "auto", labels = NULL)
cont_list |
List of contact matrices where each is in either sparse 3 column, n x n or n x (n+3) form, where the first 3 columns are chromosome, start and end coordinates of the regions. If an x n matrix is used, the column names must correspond to the start point of the corresponding bin. Required. |
chr |
Vector of chromosomes in the same order as their corresponding contact matrices. Must be same length as cont_list. Required. |
levels |
The number of levels of the TAD hierarchy to be calculated. The default setting is 1. |
qual_filter |
Option to turn on quality filtering which removes TADs with negative silhouette scores (poorly organized TADs). Default is FALSE. |
z_clust |
Option to filter sub-TADs based on the z-score of their eigenvector gaps. Default is TRUE. |
eigenvalues |
The number of eigenvectors to be calculated. The default and suggested setting is 2. |
min_size |
The minimum allowable TAD size measured in bins. Default is 5. |
resolution |
The resolution of the contact matrix. If none selected, the resolution is estimated by taking the most common distance between bins. For n x (n+3) contact matrices, this value is automatically calculated from the first 3 columns. |
grange |
Parameter to determine whether the result should be a GRangeList object. Defaults to FALSE |
gap_threshold |
Corresponds to the percentage of zeros allowed before a column/row is removed from analysis. 1=100%, .7 = 70%, etc. Default is 1. |
cores |
Number of cores to use. Defaults to total available cores minus one. |
labels |
Vector of labels used to name each contact matrix. Must be same length as cont_list. Default is NULL. |
This is the parallelized version of the SpectralTAD() function. Given a sparse 3 column, an n x n contact matrix, or n x (n+3) contact matrix, SpectralTAD returns a list of TAD coordinates in BED format. SpectralTAD works by using a sliding window that moves along the diagonal of the contact matrix. By default we use the biologically relevant maximum TAD size of 2Mb and minimum size of 5 bins to determine the size of this window. Within each window, we calculate a Laplacian matrix and determine the location of TAD boundaries based on gaps between eigenvectors calculated from this matrix. The number of TADs in a given window is calculated by finding the number that maximize the silhouette score. A hierarchy of TADs is created by iteratively applying the function to sub-TADs. The number of levels in each hierarchy is determined by the user.
List of lists where each entry is a list of data frames or GRanges in BED format corresponding to TADs seperated by hierarchies
#Read in data data("rao_chr20_25_rep") #Make a list of matrices mat_list = list(rao_chr20_25_rep, rao_chr20_25_rep) #Make a vector of chromosomes chr = c("chr20", "chr20") #Make a vector of labels labels = c("run1", "run2") spec_table <- SpectralTAD_Par(mat_list, chr= chr, labels = labels)