def annotate_all_bin_bed(wig_f, out_f, chrom):
#Open the input and output.
wig = open(wig_f, "r")
out = open(out_f, "w")
#We choose the 97th and the 90th percentiles for promoter and enhancer, respectively.
promoter_cutoff = wsu.get_intensity_percentile(0.97, wig, 0)
enhancer_cutoff = wsu.get_intensity_percentile(0.90, wig, 0)
#Loop through the WIG file and annotate each region. Skip the first two lines, which are the header.
junk = wig.readline()
junk = wig.readline()
bin = wig.readline().split("\t")
while len(bin) > 1:
#Output the starting and ending positions.
end = str(int(bin[0]) + BIN_SIZE)
out.write("chr" + chrom + "\t" + bin[0] + "\t" + end + "\t")
#Get the annotation.
rpkm = float(bin[1])
if rpkm >= promoter_cutoff:
out.write("Promoter\n")
elif rpkm >= enhancer_cutoff:
out.write("Enhancer\n")
else:
out.write("Weak\n")
#Get the next line.
bin = wig.readline().split("\t")
#Close the input and output.
wig.close()
out.close()
def save_significant(percentages, magnitudes, wig_name, out_name, chrom, cell,
min_val):
#Get threshold to use in printing.
wig = open(wig_name, 'r')
out = open(out_name, 'w')
intensity = wsu.get_intensity_percentile(0.995, wig, min_val)
wig.close()
scale = 5.0 / intensity
perc_string = percentages.astype(str)
#Print significant magnitudes with labels.
labels = ["Promoter", "Enhancer", "Polycomb", "Weak"]
for j in range(0, percentages.shape[1]):
was_significant = False
for i in range(0, percentages.shape[0]):
other_percents = percentages[np.arange(percentages.shape[0]) != i,
j]
if labels[i] != "Polycomb" and percentages[i, j] > 0.5 and np.max(
other_percents) <= percentages[i, j] / 2:
out.write(labels[i] + "\t" + cell + "_" + chrom + "_" +
magnitudes[j] + "\t" + magnitudes[j] + "\n")
was_significant = True
if not was_significant:
out.write("Unknown" + "\t" + cell + "_" + chrom + "_" +
magnitudes[j] + "\t" + magnitudes[j] + "\n")
#Close the files.
wig.close()
out.close()
def save_significant(percentages, shape_names, shapes, wig_name, out_name,
chrom, cell, min_val, cutoff):
#Get threshold to use in printing.
wig = open(wig_name, 'r')
out = open(out_name, 'a')
perc_out = open(out_name + "_percents", 'a')
percentage_out = open(out_name + "_" + cell + "/" + chrom + "percentages",
'w')
intensity = wsu.get_intensity_percentile(0.995, wig, min_val)
print("\n")
wig.close()
scale = 5.0 / intensity
perc_string = percentages.astype(str)
#Print significant shapes with labels.
labels = ["Promoter", "Enhancer", "Polycomb", "Weak"]
for j in range(0, percentages.shape[1]):
split_clust = shapes[j].split(",")
scaled_clust = [float(i) for i in split_clust] * np.tile(
scale, len(split_clust))
scaled_clust_str = [str(i) for i in scaled_clust]
perc_str = [str(i) for i in percentages[:, j]]
joined = ','.join(scaled_clust_str)
perc_joined = ','.join(perc_str)
was_significant = False
for i in range(0, percentages.shape[0]):
other_percents = percentages[np.arange(percentages.shape[0]) != i,
j]
if labels[i] != "Polycomb" and percentages[
i, j] > cutoff and np.max(other_percents) < percentages[i,
j]:
out.write(labels[i] + "\t" + cell + "_" + chrom + "_" +
shape_names[j] + "\t" + joined)
perc_out.write(labels[i] + "\t" + cell + "_" + chrom + "_" +
shape_names[j] + "\t" + perc_joined)
if joined.find('\n') != len(joined) - 1:
perc_out.write("\n")
out.write("\n")
was_significant = True
if not was_significant:
out.write("Unknown" + "\t" + cell + "_" + chrom + "_" +
shape_names[j] + "\t" + joined)
perc_out.write("Unknown" + "\t" + cell + "_" + chrom + "_" +
shape_names[j] + "\t" + perc_joined)
if joined.find('\n') != len(joined) - 1:
perc_out.write("\n")
out.write("\n")
#Print all percentages to a file to use later.
percentage_out.write(','.join(perc_string[:, j]) + "\n")
#Close the files.
wig.close()
out.close()
percentage_out.close()
def main():
#Read in the bed file and shape data.
bed = np.genfromtxt(sys.argv[1], delimiter='\t', dtype=str)
output = sys.argv[3]
wig = sys.argv[4]
chromosome = sys.argv[5]
cell = sys.argv[6]
anno_file = sys.argv[7]
min_val = float(sys.argv[8])
#shape annotations are in column 3. Biological annotations are in column 4.
shape_col = 3
bio_col = 8
shape_start = 1
shape_end = 2
bio_start = 6
bio_end = 7
bio_len = 9
#Get list of shapes.
shapes = []
shape_file = open(sys.argv[2], 'r')
next_clust = shape_file.readline()
while next_clust:
shapes.append(next_clust)
next_clust = shape_file.readline()
unique_clusts = sorted(list(set(bed[:, shape_col])),
key=lambda x: float(x))
#Get percentage of each shape and each chromHMM annotation and each chromHMM annotation per shape.
wig_file = open(wig, "r")
threshold = wsu.get_intensity_percentile(0.75, wig_file, min_val)
wig_file.close()
total_percent_shapes = get_shape_percentages(shape_col, shape_start,
shape_end, unique_clusts, bed)
total_percent_anno = get_anno_percentages(bio_col, shape_start, shape_end,
bio_len, bed)
[total_percent_all, total_sums_all
] = get_all_percentage_pairs(shape_col, bio_col, shape_start, shape_end,
bio_start, bio_end, bio_len, unique_clusts,
bed, threshold, anno_file, shapes)
#Print all shapes with significant annotations, along with their annotations.
save_significant(total_percent_all, unique_clusts, shapes, wig, output,
chromosome, cell, min_val)
def get_all_precision_or_recall(bed, sig, wig, chrom):
#Get actual annotation and ground truth for all annotations and for all unannotated regions.
threshold = wsu.get_intensity_percentile(0.75, open(wig, 'r'), 0)
annotations = ["Promoter", "Enhancer", "Weak"]
length = len(annotations)
#Get precision and recall for each type.
[pred, gt] = ppr.get_labels_and_ground_truth(bed, sig, wig, annotations, threshold)
precision = dict()
recall = dict()
if len(pred) > 0:
for i in range(length):
precision[i] = precision_score(gt[:, i], pred[:, i])
recall[i] = recall_score(gt[:, i], pred[:, i])
return [chrom, precision, recall]
def main():
file_path = sys.argv[1]
output_path = sys.argv[2]
bin_size = int(sys.argv[3])
region_size = int(sys.argv[4])
wig_file = open(sys.argv[5], 'r')
percentile = 0.995
fine = bool(sys.argv[6])
minimum_intensity = float(sys.argv[7])
threshold = wsu.get_intensity_percentile(percentile, wig_file, minimum_intensity, fine)
print(str(threshold))
shiftRegions(file_path, output_path, bin_size, region_size, threshold, minimum_intensity)
#Print message to user.
print("Shifting complete for all windows.")
def get_all_precision_and_recall(bed, sig, wig, chrom):
#Get actual annotation and ground truth for all annotations and for all unannotated regions.
threshold = wsu.get_intensity_percentile(0.75, open(wig, 'r'), BIN_SIZE)
annotations = ["Promoter", "Enhancer", "Weak"]
length = len(annotations)
ground_truth_list = []
predicted_list = []
#Get precision and recall for each type.
[pred, gt] = get_labels_and_ground_truth(bed, sig, wig, annotations, threshold)
precision = dict()
recall = dict()
fpr = dict()
for i in range(length):
precision[i] = precision_score(gt[:, i], pred[:, i])
recall[i] = recall_score(gt[:, i], pred[:, i])
fp = len(np.where((pred[:, i] == 1) & (gt[:, i] == 0))[0])
tn = len(np.where((pred[:, i] == 0) & (gt[:, i] == 0))[0])
fpr[i] = fp / (fp + tn)
return [precision, recall, pred.shape[0], threshold, pred, gt, fpr]
def main():
#Read in the bed file and shape data.
bed = np.genfromtxt(sys.argv[1], delimiter='\t', dtype=str)
output = sys.argv[2]
wig = sys.argv[3]
chromosome = sys.argv[4]
cell = sys.argv[5]
anno_file = sys.argv[6]
min_val = float(sys.argv[7])
#magnitude annotations are in column 3. Biological annotations are in column 4.
magnitude_col = 3
bio_col = 7
magnitude_start = 1
magnitude_end = 2
bio_start = 5
bio_end = 6
bio_len = 8
#Get list of magnitudes.
unique_magnitudes = sorted(list(set(bed[:, magnitude_col])),
key=lambda x: float(x))
print(unique_magnitudes)
#Get percentage of each shape and each chromHMM annotation and each chromHMM annotation per shape.
wig_file = open(wig, "r")
threshold = wsu.get_intensity_percentile(0.75, wig_file, min_val)
wig_file.close()
[total_percent_all, total_sums_all
] = get_all_percentage_pairs(magnitude_col, bio_col, magnitude_start,
magnitude_end, bio_start, bio_end, bio_len,
unique_magnitudes, bed, threshold, anno_file)
#Print all shapes with significant annotations, along with their annotations.
save_significant(total_percent_all, unique_magnitudes, wig, output,
chromosome, cell, min_val)
def get_all_precision_and_recall(bed, sig, tss_bed, tss_sig, or_bed, or_sig,
and_bed, and_sig, rpkm_bed, rpkm_sig, wig,
chrom, cell):
#Get actual annotation and ground truth for all annotations and for all unannotated regions.
threshold = wsu.get_intensity_percentile(0.75, open(wig, 'r'), 0)
annotations = ["Promoter", "Enhancer", "Weak"]
length = len(annotations)
ground_truth_list = []
predicted_list = []
#Get precision and recall for each type.
[pred, gt] = get_labels_and_ground_truth(bed, sig, wig, annotations,
threshold)
precision = dict()
recall = dict()
fpr = dict()
for i in range(length):
precision[i] = precision_score(gt[:, i], pred[:, i])
recall[i] = recall_score(gt[:, i], pred[:, i])
fp = len(np.where((pred[:, i] == 1) & (gt[:, i] == 0))[0])
tn = len(np.where((pred[:, i] == 0) & (gt[:, i] == 0))[0])
fpr[i] = fp / (fp + tn)
#Get precision and recall for TSS-based promoters.
[pred_promoter, gt_promoter
] = get_tss_labels_and_ground_truth(tss_bed, tss_sig, wig,
["Promoter", "Not_Promoter"],
threshold)
precision["tss"] = precision_score(gt_promoter[:, 0], pred_promoter[:, 0])
recall["tss"] = recall_score(gt_promoter[:, 0], pred_promoter[:, 0])
fp = len(
np.where((pred_promoter[:, 0] == 1) & (gt_promoter[:, 0] == 0))[0])
tn = len(
np.where((pred_promoter[:, 0] == 0) & (gt_promoter[:, 0] == 0))[0])
fpr["tss"] = fp / (fp + tn)
#Get precision and recall for combined annotations (OR).
[pred_or, gt_or] = get_labels_and_ground_truth(or_bed, or_sig, wig,
annotations, threshold)
precision_or = dict()
recall_or = dict()
fpr_or = dict()
for i in range(length):
precision_or[i] = precision_score(gt_or[:, i], pred_or[:, i])
recall_or[i] = recall_score(gt_or[:, i], pred_or[:, i])
fp = len(np.where((pred_or[:, i] == 1) & (gt_or[:, i] == 0))[0])
tn = len(np.where((pred_or[:, i] == 0) & (gt_or[:, i] == 0))[0])
fpr_or[i] = fp / (fp + tn)
#Get precision and recall for combined annotations (AND).
[pred_and, gt_and] = get_labels_and_ground_truth(and_bed, and_sig, wig,
annotations, threshold)
precision_and = dict()
recall_and = dict()
fpr_and = dict()
for i in range(length):
precision_and[i] = precision_score(gt_and[:, i], pred_and[:, i])
recall_and[i] = recall_score(gt_and[:, i], pred_and[:, i])
fp = len(np.where((pred_and[:, i] == 1) & (gt_and[:, i] == 0))[0])
tn = len(np.where((pred_and[:, i] == 0) & (gt_and[:, i] == 0))[0])
fpr_and[i] = fp / (fp + tn)
#Get precision and recall for RPKM annotations.
[pred_rpkm, gt_rpkm] = get_labels_and_ground_truth(rpkm_bed, rpkm_sig, wig,
annotations, threshold)
precision_rpkm = dict()
recall_rpkm = dict()
fpr_rpkm = dict()
for i in range(length):
precision_rpkm[i] = precision_score(gt_rpkm[:, i], pred_rpkm[:, i])
recall_rpkm[i] = recall_score(gt_rpkm[:, i], pred_rpkm[:, i])
fp = len(np.where((pred_rpkm[:, i] == 1) & (gt_rpkm[:, i] == 0))[0])
tn = len(np.where((pred_rpkm[:, i] == 0) & (gt_rpkm[:, i] == 0))[0])
fpr_rpkm[i] = fp / (fp + tn)
return [
precision, recall, precision_or, recall_or, precision_and, recall_and,
precision_rpkm, recall_rpkm, pred.shape[0], threshold, pred, gt,
pred_and, gt_and, fpr, fpr_or, fpr_and, fpr_rpkm
]
def match_shapes_cutoff(in_file_name, shape_file_name, out_dir, wig_name,
cutoff):
#Get threshold to use in printing.
wig = open(wig_name, 'r')
intensity = wsu.get_intensity_percentile(0.995, wig, 0)
if intensity == 0:
intensity = 0.1
print("\n")
wig.close()
scale = 5.0 / intensity
#Open input and shape files.
in_file = open(in_file_name, "r")
shape_file = open(shape_file_name, "r")
#Open output files.
out_file = open(out_dir, "w")
out_clust = open(out_dir + "clust", "w")
#Read in shape data.
shapes = []
shape_anno = []
shape_name = []
next_shape = shape_file.readline()
counter = 0
while next_shape:
split_tabs = next_shape.split("\t")
shape_anno.append(split_tabs[1])
shape_name.append(split_tabs[0])
shapes.append([float(i) for i in split_tabs[2].split(",")])
next_shape = shape_file.readline()
shape_file.close()
#Read in each line in the file and map it.
if (len(shapes) > 1):
next_line = in_file.readline()
while (next_line):
#Get the chromosome and position info to print to the output file.
#Get the input signal to match with the shapes.
inputStr = []
labels = []
split_line = next_line.split(",")
labels = list(split_line[0:3])
inputStr = list(split_line[3:len(split_line)])
input = [float(i) for i in inputStr]
input_scaled = input * np.tile(scale, len(input))
#Match the data to the nearest shape and obtain the match and the ambiguity metric.
[match, ambig, crosscorr,
out_str] = match_region(input_scaled, shapes, shape_anno)
#If the cross-correlation is within the threshold, assign the label as the correct label for the region.
#Otherwise, assign it as unknown.
anno_label = "Unknown"
anno_name = "Unknown"
if crosscorr >= cutoff and match != -1:
anno_label = shape_anno[match]
anno_name = shape_name[match]
#Print match to BED file. Format is:
#chrom start end shape_num 1 - ambiguity
#Score is the opposite of the ambiguity metric.
out_file.write("chr" + labels[0] + "\t" + labels[1] + "\t" +
labels[2] + "\t" + anno_label + "\t" +
str(1 - ambig) + "\t" + out_str + "\n")
out_clust.write("chr" + labels[0] + "\t" + labels[1] + "\t" +
labels[2] + "\t" + anno_name + "\t" +
str(1 - ambig) + "\t" + out_str + "\n")
#Read the next line in the file.
next_line = in_file.readline()
#Print a message to the user.
print("Files done")
else:
print("Only one shape. No annotation performed.")
out_file.close()
out_clust.close()
in_file.close()
