#!/usr/bin/env python
# Copyright (c) Tuomo Hartonen, 2015-2016
#
# THIS PROGRAM COMES WITH ABSOLUTELY NO WARRANTY!
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see http://www.gnu.org/licenses/.
import argparse
import csv
from glob import glob
def createHTMLoutput():
########################
#Command line arguments#
########################
parser = argparse.ArgumentParser()
#MANDATORY PARAMETERS
parser.add_argument("outfile",help="Full path to the output HTML-file.",type=str)
parser.add_argument("indir",help="Full path to the directory containing the PeakXus-results.",type=str)
parser.add_argument("N",help="Total number of peaks analyzed.",type=int)
#OPTIONAL PARAMETERS
parser.add_argument("--motifFigs",help="If 1, also the motif-match images were produced by PeakXus and are embedded to the html-page, otherwise 0 (default).",type=int,choices=[0,1],default=0)
parser.add_argument("--umifigs",help="If 1, the UMI-histograms were produced by PeakXus and are embedded to the html-page, otherwise 0 (default).",type=int,choices=[0,1],default=0)
args = parser.parse_args()
f = open(args.outfile,'wb')
###########################
#The required declarations#
###########################
f.write("\n\n")
############
#Page style#
############
f.write('\n')
#########
#Heading#
#########
f.write('')
f.write("
PEAKXUS RESULTS
")
f.write('')
########################
#Summary of the results#
########################
#reading in the summary results from PeakXus output
totreads = 0.0
totumis = 0.0
totpeaks = 0.0
with open(args.indir+"PeakXus_summary.txt",'rb') as csvfile:
r = csv.reader(csvfile,delimiter=" ")
for row in r:
if len(row)<4: continue
if row[0].count("Total")>0:
if row[3].count("reads")>0: totreads = float(row[-1])
elif row[3].count("UMIs")>0: totumis = float(row[-1])
elif row[3].count("peaks")>0: totpeaks = float(row[-1])
f.write('')
f.write("
SUMMARY
")
f.write('')
f.write('')
f.write('')
f.write("Total number of peaks (no FDR-cutoff) | ")
f.write("= | ")
f.write(""+str(totpeaks)+" | ")
f.write("
")
f.write("")
f.write("Total number of reads | ")
f.write("= | ")
f.write(""+str(totreads)+" | ")
f.write("
")
f.write("")
f.write("Total number of UMIs | ")
f.write("= | ")
f.write(""+str(totumis)+" | ")
f.write("
")
f.write("")
f.write("Reads/UMIs | ")
f.write("= | ")
f.write(""+str(totreads/totumis)+" | ")
f.write("
")
fastqcname = glob("FastQC/*.html")
if len(fastqcname)==0: fastqcname = "none.html"
else: fastqcname = fastqcname[0]
f.write('Quality control results from FastQC for the input library.
')
f.write('')
f.write("")
f.write("The best MEME-motif: | ")
f.write(' | ')
f.write(' | ')
f.write("
")
f.write("
")
f.write('Full MEME-results
')
######################
#Peak size statistics#
######################
#This is always produced
f.write('')
f.write('
PEAK SIZE STATISTICS
')
f.write('')
f.write('')
f.write("")
f.write(' | ')
f.write(' | ')
f.write("
")
f.write('')
f.write('Histogram of peak scores for all reported peaks. | ')
f.write('Histogram of unique read 5\'-end counts within peak borders (Reads pointing towards peak summit minus reads pointing away from peak summit). If UMIs were not used in the analysis, raw read counts are reported. | ')
f.write('
')
f.write("
")
######################
#UMI-count histograms#
######################
#This is optional and works only if UMI-histograms are created by PeakXus
if args.umifigs==1:
f.write('')
f.write('
HISTOGRAM OF UMI-COUNTS
')
f.write('')
f.write('')
f.write("")
f.write(' | ')
f.write(' | ')
f.write("
")
f.write('')
f.write('Histogram of UMI-counts per position on the sense strand. | ')
f.write('Histogram of UMI-counts per position on the antisense strand. | ')
f.write('
')
f.write("
")
#########################
#Images of the top peaks#
#########################
#Images of top N peaks are always produced
f.write('')
f.write('
BREAKDOWN OF TOP '+str(args.N)+' PEAKS
')
f.write('')
f.write('')
f.write("")
f.write('+'.png) | ')
f.write('+'.png) | ')
f.write("
")
f.write('')
f.write('Average read 5\'-end count around the top '+str(args.N)+' peaks. Red curve corresponds to read 5\'-end counts on the sense strand, and blue on the antisense strand, respectively. | ')
f.write('Heatmap presentation of the same peaks shown on the left. Red color marks the sense strand read 5\'-end count, and blue the antisense strand, respectively. | ')
f.write('
')
if args.motifFigs==1:
f.write("")
f.write('+'.png) | ')
f.write('+'.png) | ')
f.write("
")
f.write('')
f.write('Average read 5\'-end count around the top '+str(args.N)+' peaks with an underlying High-Affinity Recognition Sequence (HARS) hit. The read counts are oriented according to the HARS-match so that the red peak corresponds to the 5\'-side of the motif. The green shading indicates the width of the HARS. The red and blue shadings correspond to half of the standard deviation over the top '+str(args.N)+' peaks. | ')
f.write('Heatmap presentation of the same peaks shown on the left. The read counts are oriented according to the HARS-match so that the red peak corresponds to the 5\'-side of the motif. | ')
f.write('
')
f.write("
")
#####################
#Images of all peaks#
#####################
#These are optional and require a list of PWM-hits as input for PeakXus
if args.motifFigs==1:
motifsperpeakname = glob("motifsPerPeak*.png")[0]
distfrommotifname = glob("dist_from_motif*.png")[0]
f.write('')
f.write('
PEAK POSITIONING RELATIVE TO PWM-HITS (HARS-SITES)
')
f.write('')
f.write('')
f.write("")
f.write(' | ')
f.write(' | ')
f.write("
")
f.write('')
f.write('Number of HARS-sites overlapping with a peak as a function of the number of peaks analyzed. Peaks are ranked according to peak score. | ')
f.write('Cumulative fraction of the top '+str(args.N)+' peaks that are within a distance indicated on the x-axis from the nearest HARS. The topmost subfigure shows the distances between left border of the peak and left edge of the HARS, the subfigure in the middle the distances between the summit of the peak and the center of the HARS and the bottom subfigure the distance between the right border of the peak and the right edge of the HARS. | ')
f.write('
')
f.write("
")
##################
#Input parameters#
##################
f.write('')
f.write('
INPUT PARAMETERS FOR PEAKXUS
')
f.write('')
arguments = ""
g = open(args.indir+"/log.txt",'rb')
for row in g:
if row.count('Namespace(')>0:
arguments = row[10:-1]
arguments = arguments.split(', ')
f.write('\n')
for a in arguments: f.write(a+'
\n')
f.write('
')
f.write('')
f.write('
If you use PeakXus in your work, please cite:
Hartonen, T., Sahu, B., Dave, K., Kivioja, T., & Taipale, J. (2016). PeakXus: comprehensive transcription factor binding site discovery from ChIP-Nexus and ChIP-Exo experiments. Bioinformatics, 32(17), i629-i638.
')
f.write('
