import sys
sys.path.append("..")
import data_tools as dt
import plotting as plot
import numpy as np
plot.plot_cluster_interactive(
dt.clusterFromFile("hic_data/GM12878_combined_22_10kb_mmds_coords.tsv"),
out_path="Fig9A.png")
plot.plot_cluster_interactive(
dt.clusterFromFile("hic_data/GM12878_combined_22_10kb_cmds_coords.tsv"),
out_path="Fig9B.png")
plot.plot_cluster_interactive(
dt.clusterFromFile("hic_data/GM12878_combined_22_10kb_minimds_coords.tsv"),
out_path="Fig9C.png")
plot.plot_coords_interactive(np.loadtxt(
"MOGEN/examples/hiC/output/GM12878_combined_22_10kb_rep1_coords.tsv"),
out_path="Fig9D.png")
import array_tools as at
import misc
#"true" distance matrix
cluster = dt.clusterFromBed(bedpath, None, None)
contactMat = dt.matFromBed(bedpath, cluster)
distMat = at.contactToDist(contactMat)
at.makeSymmetric(distMat)
for j in range(len(distMat)): #remove diagonal
distMat[j, j] = 0
chromthreed_distMat = misc.distsFromCoords(
"Chromosome3D/output/chr22_100kb/chr22_100kb_coords.tsv")
chromthreed_r = misc.pearson(distMat, chromthreed_distMat)
mmds_distMat = dt.clusterFromFile(
"hic_data/GM12878_combined_22_10kb_mmds_coords.tsv").distMat()
mmds_r = misc.pearson(distMat, mmds_distMat)
cmds_distMat = dt.clusterFromFile(
"hic_data/GM12878_combined_22_10kb_cmds_coords.tsv").distMat()
cmds_r = misc.pearson(distMat, cmds_distMat)
minimds_distMat = dt.clusterFromFile(
"hic_data/GM12878_combined_22_10kb_minimds_coords.tsv").distMat()
minimds_r = misc.pearson(distMat, minimds_distMat)
mogen_distMat = misc.distsFromCoords(
"MOGEN/examples/hiC/output/GM12878_combined_22_10kb_rep1_coords.tsv")
mogen_r = misc.pearson(distMat, mogen_distMat)
hsa_distMat = misc.distsFromCoords("hsa/GM12878_combined_22_100kb_coords.tsv")
import sys
sys.path.append("..")
import plotting as plot
import data_tools as dt
chroms = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, "X"]
clusters = [dt.clusterFromFile("hic_data/GM12878_combined_{}_10kb_cluster.tsv".format(chrom)) for chrom in chroms]
plot.plot_clusters_interactive(clusters)
mmds_rs = np.zeros(n)
cmds_rs = np.zeros(n)
minimds_rs = np.zeros(n)
mogen_rs = np.zeros(n)
for i, chrom in enumerate(chroms):
#"true" distance matrix
bedpath = "hic_data/GM12878_combined_{}_10kb.bed".format(chrom)
cluster = dt.clusterFromBed(bedpath, None, None)
contactMat = dt.matFromBed(bedpath, cluster)
distMat = at.contactToDist(contactMat)
at.makeSymmetric(distMat)
for j in range(len(distMat)): #remove diagonal
distMat[j,j] = 0
mmds_distMat = dt.clusterFromFile("hic_data/GM12878_combined_{}_10kb_mmds_coords.tsv".format(chrom)).distMat()
mmds_rs[i] = misc.pearson(distMat, mmds_distMat)
cmds_distMat = dt.clusterFromFile("hic_data/GM12878_combined_{}_10kb_cmds_coords.tsv".format(chrom)).distMat()
cmds_rs[i] = misc.pearson(distMat, cmds_distMat)
minimds_distMat = dt.clusterFromFile("hic_data/GM12878_combined_{}_10kb_minimds_coords.tsv".format(chrom)).distMat()
minimds_rs[i] = misc.pearson(distMat, minimds_distMat)
mogen_distMat = misc.distsFromCoords("MOGEN/examples/hiC/output/GM12878_combined_{}_10kb_rep1_coords.tsv".format(chrom))
mogen_rs[i] = misc.pearson(distMat, mogen_distMat)
chrom_sizes = np.loadtxt("chrom_sizes_10kb.txt")
fig = plt.figure()
ax = fig.add_subplot(111, frameon=False)
return misc.pearson(dists1, dists2)
#labels = ("Chromosome3D", "mMDS", "miniMDS", "MOGEN", "HSA", "ChromSDE")
labels = ("mMDS", "miniMDS", "MOGEN", "HSA")
n = len(labels)
rs = np.zeros(n)
#Chromosome3D
#coords1 = np.loadtxt("Chromosome3D/output_models/chr22_10kb_rep1/rep1_coords.tsv")
#coords2 = np.loadtxt("Chromosome3D/output_models/chr22_10kb_rep1/rep2_coords.tsv")
#rs[0] = rep_correlation(coords1, coords2)
#mMDS
coords1 = dt.clusterFromFile("hic_data/GM12878_combined_22_10kb_mmds_rep1.tsv").getCoords()
coords2 = dt.clusterFromFile("hic_data/GM12878_combined_22_10kb_mmds_rep2.tsv").getCoords()
#rs[1] = rep_correlation(coords1, coords2)
rs[0] = rep_correlation(coords1, coords2)
#miniMDS
coords1 = dt.clusterFromFile("hic_data/GM12878_combined_22_10kb_minimds_rep1.tsv").getCoords()
coords2 = dt.clusterFromFile("hic_data/GM12878_combined_22_10kb_minimds_rep2.tsv").getCoords()
#rs[2] = rep_correlation(coords1, coords2)
rs[1] = rep_correlation(coords1, coords2)
#MOGEN
coords1 = np.loadtxt("MOGEN/examples/hiC/output/GM12878_combined_22_10kb_rep1_coords.tsv")
coords2 = np.loadtxt("MOGEN/examples/hiC/output/GM12878_combined_22_10kb_rep2_coords.tsv")
#rs[3] = rep_correlation(coords1, coords2)
rs[2] = rep_correlation(coords1, coords2)
import sys
sys.path.append("..")
import plotting as plot
import data_tools as dt
chroms = [
1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21,
22, "X"
]
clusters = [
dt.clusterFromFile(
"hic_data/GM12878_combined_chr{}_10kb_cluster.tsv".format(chrom))
for chrom in chroms
]
plot.plot_clusters_interactive(clusters, out_path="Fig10.png")
import sys
sys.path.append("..")
import data_tools as dt
res_kb = int(sys.argv[1])
with open("chrom_sizes_{}kb.txt".format(res_kb), "w") as out:
for chrom in [
1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19,
20, 21, 22, "X"
]:
cluster = dt.clusterFromFile(
"hic_data/GM12878_combined_chr{}_{}kb_cluster.tsv".format(
chrom, res_kb))
out.write(str(len(cluster.getPoints())) + "\n")
out.close()
