def get_radial_statistic(R,
func=np.nanmean,
genome='hg38'):
"""
Compute a statistic on the radial data.
Params:
-------
R: lists of radial positions, indexed by chromosome
func: the function used to compute the statistic
genome: target genome, to retrieve constants
Returns:
--------
R_stat: array with a single number per chromosome, i.e. the statistic
"""
SIZES = const.get_genome_sizes(genome) #chromosome sizes
R_stat = np.zeros(len(SIZES))
for i in range(len(R)):
with warnings.catch_warnings():
warnings.simplefilter("ignore", category=RuntimeWarning)
R_stat[i] = func(R[i])
return R_stat
def get_bin_sizes(resolution, genome="hg38"):
"""
Helper function to generate a list of bin sizes corresponding to the
chromosomes in a target genome. Each bin size reflects the number of bins
that a given chromosome is discretized to at a given bin resolution.
Params:
-------
resolution: the resolution at which the chromosomes will be binned,
in basepairs
genome: genome type used to look up chromosome sizes
Returns:
--------
bin_sizes_chr: list of bin sizes corresponding to each chromosome in the
target genome.
"""
#Init constants
SIZES = const.get_genome_sizes(genome)
#Bin sizes for matrix per chromosome
chr_count = len(SIZES)
bin_sizes_chr = np.array([0])
for i in range(1, chr_count):
chr_size = SIZES[i]
num_bins = int(np.ceil(SIZES[i] / resolution))
bin_sizes_chr = np.append(bin_sizes_chr, num_bins)
return bin_sizes_chr
def get_radial_dists(cells,
genome='hg38'):
"""
Get the radial positions of all reads, indexed by chromosome.
Params:
-------
cells: a list of the single cells, dataframe
genome: target genome, to retrieve constants
Returns:
--------
R: lists of radial read positions, indexed by chromosome
"""
SIZES = const.get_genome_sizes(genome) #chromosome sizes
R = [] # to record normed radial distances
for i in range(len(SIZES)):
R.append([])
for cell in cells:
chr_nums = cell["hg38_chr"].values
radii = cell["norm_r_2D"].values
for i in range(len(chr_nums)):
R[chr_nums[i]].append(radii[i])
return R
def make_genome_wide_matrix(cells, resolution=10 * 10**6, genome="hg38"):
"""
Make a population ensemble genome wide distance matrix given a list of
single cells. For each cell, iterate over chromosomes (distinguishing
between homologs), compute pairwise distances between their corrsponding
reads, and index into population matrix to append distances.
Params:
-------
cells: list of cells, dataframe
resolution: matrix resolution, in basepairs
genome: target genome, to retreive constants
Returns:
--------
GM: the genome wide distance matrix; each pixel is a list of distances
observed at that corresponding pair of genomic positions, binned
at the input resolution.
"""
#Init constants
SIZES = const.get_genome_sizes(genome) #chromosome sizes
KEYS = const.get_genome_keys(genome) #dataframe keys
chr_count = len(SIZES)
#Bin sizes for matrix per chromosome
bin_sizes_chr = get_bin_sizes(resolution, genome)
#Total and cumulative bins
total_bins = np.sum(bin_sizes_chr)
#Init genome wide distance matrix
GM = init_empty_matrix(total_bins)
for cell in cells:
for i in range(1, chr_count):
for j in range(i, chr_count):
#Handle multiple clusters (e.g. homologs) for a chromosome
if i == j:
chro = cell.loc[cell[KEYS["chr"]] == i]
cluster_idxs = chro[KEYS["cluster"]].unique()
for idx in cluster_idxs: #get intra cluster distances
ci = chro.loc[chro[KEYS["cluster"]] == idx]
if len(ci) < 1: continue #need more than 1 read
GM = populate_tile(GM, i, j, ci, ci, resolution)
#Nonhomologous clusters
else:
ci = cell.loc[cell[KEYS["chr"]] == i]
cj = cell.loc[cell[KEYS["chr"]] == j]
if len(ci) < 1 or len(cj) < 1: continue
GM = populate_tile(GM, i, j, ci, cj, resolution)
return GM
def make_ensemble_matrix(data,
chr_num,
resolution=2.5 * 10**6,
statistic=np.nanmean,
genome="mm10"):
"""
Build an ensemble distance matrix for a particular chromosome given a
dataframe.
Params:
-------
data: the dataframe (must be prefiltered on stage, parent, and chr)
chr_num: desired chromosome number for ensemble distance
resolution: matrix resolution in base pairs
statistic: function to get distance metric
genome: species corresponding to the data
Returns:
--------
A_ensemble: the ensemble distance matrix.
"""
#Get all chromosome copies
matrices, clusters = [], []
chr_data = data.loc[data["chr"] == chr_num]
cell_indexes = data["cell_index"].unique()
for ci in cell_indexes:
cell = chr_data.loc[chr_data["cell_index"] == ci]
cluster = cell.loc[cell["chr"] == chr_num]
if len(cluster) > 0: clusters.append(cluster)
#Get matrix parameters
SIZES = const.get_genome_sizes(genome)
chr_size = SIZES[chr_num]
num_bins = int(np.ceil(chr_size / resolution))
#Make the ensemble matrix by concatenating all the single cell matrices
A_ensemble = init_empty_matrix(num_bins)
for cluster in clusters:
A = make_distance_matrix(cluster, resolution=resolution, flatten=False)
for i in range(len(A)):
for j in range(len(A)):
A_ensemble[i][j] = np.concatenate((A_ensemble[i][j], A[i][j]))
#Flatten the matrix using distance metric function
A_ensemble = flatten_matrix(A_ensemble, func=statistic)
return A_ensemble
def make_distance_matrix(cluster,
resolution=2.5 * 10**6,
statistic=np.nanmean,
flatten=True,
genome="mm10"):
"""
Function to generate a distance matrix from a chromosome cluster.
Params:
-------
cluster: pandas dataframe with chromosome cluster information
resolution: matrix resolution in base pairs
statistic: function implementing desired distance matrix
flatten: If true, apply the distance function,
if false, return matrix with variable length
genome: human or mouse genome, string
Returns:
--------
A: distance matrix as defined by the statistic
"""
chr_num = cluster["chr"].unique()[0]
if type(chr_num) != np.int64:
raise ValueError("Cluster includes multiple chromosomes.")
SIZES = const.get_genome_sizes(genome)
KEYS = const.get_genome_keys(genome)
chr_size = SIZES[chr_num]
num_bins = int(np.ceil(chr_size / resolution))
A = init_empty_matrix(num_bins)
B = np.arange(0, num_bins + 1) #bin vector
#Get spatial position vector and genomic position vector
R = np.array([
cluster[KEYS["x"]].values, cluster[KEYS["y"]].values,
cluster[KEYS["z"]].values
]).T
P = np.array(cluster[KEYS["pos"]].values)
#Bin position vector, then populate binned matrix from unbinned matrix of
#pdists using binned indices
P_inds = np.digitize(P, B * resolution) - 1
R_pdist = distance.pdist(R)
R_sf = distance.squareform(R_pdist)
#Do the matrix binning
for i in range(len(P_inds)):
for j in range(i + 1, len(P_inds)):
ii, jj = P_inds[i], P_inds[j]
A[ii][jj].append((R_sf[i][j]))
A[jj][ii].append((R_sf[i][j]))
if flatten:
#Now flatten lists into 2D matrix according to some statistic
A = flatten_matrix(A, func=statistic)
return A
def draw_genome_wide_matrix(A,
xlabel="\nGenomic Coordinate [Mb]",
clabel='\nSpatial Distance [um]',
resolution=10 * 10**6,
q=0.01,
genome='hg38'):
"""
Draw a genome wide distance matrix.
Params:
-------
A: distance matrix
xlabel, clabel: x-axis and colorbar labels
resolution: matrix resolution in basepairs
q: percentile cutoff for clim
genome: target genome, to retreive constants
Returns:
--------
fig, ax: the figure and axes where the matrix is drawn
"""
fig, ax = plt.subplots()
SIZES = const.get_genome_sizes(genome) #chromosome sizes, bp
chr_count = len(SIZES)
#Bin sizes for matrix per chromosome
bin_sizes_chr = get_bin_sizes(resolution)
total_bins = np.sum(bin_sizes_chr)
sum_sizes = np.cumsum(bin_sizes_chr)
clim = get_clims([A], q) #clim = qth and 1-qth percentile values
clim = (0, clim[1]) #start linear scale at 0
#Draw outline around chromosome territories
for i in range(2, chr_count + 1):
offset0 = np.sum(bin_sizes_chr[:i - 1])
offset1 = np.sum(bin_sizes_chr[:i])
ax.hlines(offset0 - 1, offset0, offset1, lw=1, color='black')
ax.hlines(offset1 - 1, offset0, offset1, lw=1, color='black')
ax.vlines(offset0, offset0 - 1, offset1 - 1, lw=1, color='black')
ax.vlines(offset1, offset0 - 1, offset1 - 1, lw=1, color='black')
cmap = plt.get_cmap('seismic_r')
cmap.set_bad(color='lightgrey') #handle unmapped regions
#Draw the matrix and interpolate adjacent unmapped regions
cax = ax.imshow(A, cmap=cmap, interpolation='nearest')
cax.set_clim(clim)
cbar = fig.colorbar(cax, label=clabel)
#Handle tick labels
x_tick_labels = ["Chr 1 "]
y_tick_labels = ["1"]
for i in range(2, chr_count):
if i == 23:
x_tick_labels.append("X")
y_tick_labels.append("X")
elif i == 24:
x_tick_labels.append("Y")
y_tick_labels.append("Y")
elif i > 1 and i < 9:
x_tick_labels.append(str(i))
y_tick_labels.append(str(i))
elif i == 10:
x_tick_labels.append(str(" ⋯ "))
y_tick_labels.append(str(""))
else:
x_tick_labels.append(str(""))
y_tick_labels.append(str(""))
plt.xticks(sum_sizes)
plt.yticks(sum_sizes)
ax.set_xticklabels(x_tick_labels)
ax.set_yticklabels(y_tick_labels)
ax.set_xlabel(xlabel)
ax.set_xlim(0, total_bins)
ax.set_ylim(total_bins, 0)
plt.tight_layout()
plt.show()
return fig, ax