def step1_generate_matrix(conf_dict, logfile):
'''
generate expression matrix file
main data processing step, including mapping, generate expression matrix and QC matrix which is used in next step
for fastq format :
STAR/bowtie2 mapping
q30 filter,
for sam format:
q30 filter
'''
#t= time.time()
### generate TF overlap matrix using bed tools
wlog("generate TF overlap matrix", logfile)
init = 0
for f in conf_dict['General']['peakfilenames']:
if init == 0:
cmd = '%s intersect -a %s -b %s -c ' % (
conf_dict['General']['bedtools'],
conf_dict['General']['HMRpeak'],
conf_dict['General']['peakFolder'] + f + ".bed")
init = 1
else:
cmd += '| %s intersect -a - -b %s -c ' % (
conf_dict['General']['bedtools'],
conf_dict['General']['peakFolder'] + f + ".bed")
cmd += '> %s' % (conf_dict['General']['outname'] + "_peakov.bed")
rlogonly(cmd, logfile)
### generate HMsig
wlog("generate HMsignal matrix", logfile)
inf = open(conf_dict['General']['HMRpeak'])
outf = open(conf_dict['General']['outname'] + "_HMsig.bed", 'w')
for line in inf:
ll = line.split()
center = (int(ll[1]) + int(ll[2])) / 2
start = max(0, center - conf_dict['options']['ext'])
end = center + conf_dict['options']['ext']
addsigALL = []
for bwsigfile in conf_dict['General']['signalfile']:
addsigALL.append(
bwsigAve(bwsigfile, ll[0], start, end,
conf_dict['General']['bwsummary']))
newll = ll + addsigALL
outf.write("\t".join(map(str, newll)) + "\n")
inf.close()
outf.close()
#s1time = time.time() -t
#wlog("time for Step1: %s"%(s1time),logfile)
#conf_dict['results'] = {}
#conf_dict['results']['expmat'] = conf_dict['Step2_ExpMat']['expmat']
#conf_dict['results']['qcmat'] = conf_dict['Step2_ExpMat']['qcmat']
return conf_dict
def step0_check_data(conf_dict, logfile):
'''
step0 integrate data
check and complement parameter
'''
### check data path , format ,
if "~" in conf_dict['General']['HMRpeak']:
ewlog(
'require absolute path for HMRpeak bed file, HMRpeak file cannot contain "~", current HMRpeak file is %s'
% (conf_dict['General']['HMRpeak']), logfile)
if "~" in conf_dict['General']['signal']:
ewlog(
'require absolute path for HMsignal bigwig file, signal file cannot contain "~", current signal file(s): %s'
% (conf_dict['General']['signal']), logfile)
if not conf_dict['General']['HMRpeak'].startswith('/'):
conf_dict['General']['HMRpeak'] = conf_dict['General'][
'startdir'] + conf_dict['General']['HMRpeak']
if not os.path.isfile(conf_dict['General']['HMRpeak']):
ewlog("HMRpeak file %s not found" % (conf_dict['General']['HMRpeak']),
logfile)
if not conf_dict['General']['HMRpeak'].endswith('.bed'):
ewlog('extenion of HMR peak file is not .bed', logfile)
checkbed = checkbedformat(conf_dict['General']['HMRpeak'], 1000)
if checkbed == "fail":
ewlog("HMRpeak file is not a bed file", logfile)
elif checkbed == "lesspeak":
ewlog("HMRpeak file contains less than 1000 peaks")
conf_dict['General']['signalname'] = []
conf_dict['General']['signalfile'] = []
for bwsignalfile in conf_dict['General']['signal']:
if not bwsignalfile.startswith('/'):
bwsignalfile = conf_dict['General']['startdir'] + bwsignalfile
if not os.path.isfile(bwsignalfile):
wlog("signal bw file %s not found, ignored" % (bwsignalfile),
logfile)
continue
if bwsignalfile.endswith(".bw"):
conf_dict['General']['signalfile'].append(bwsignalfile)
conf_dict['General']['signalname'].append(
bwsignalfile.split("/")[-1][:-3])
elif bwsignalfile.endswith(".bigwig"):
conf_dict['General']['signalfile'].append(bwsignalfile)
conf_dict['General']['signalname'].append(
bwsignalfile.split("/")[-1][:-7])
else:
wlog('[WARNING] extension of signal bw file is not bw/bigwig',
logfile)
conf_dict['General']['signalfile'].append(bwsignalfile)
conf_dict['General']['signalname'].append(
bwsignalfile.split("/")[-1])
if len(conf_dict['General']['signalfile']) == 0:
ewlog("no signal bw file valid, exit")
elif len(conf_dict['General']['signalfile']) > 4:
ewlog(
"maximum signal bw file is limited to 4. There were %s signal file inputed, exit"
% (len(conf_dict['General']['signalfile'])))
### check TFpeak folder
if "~" in conf_dict['General']['peakFolder']:
ewlog(
'require absolute path for peak/track Folder, Folder cannot contain "~", current Folder is %s'
% (conf_dict['General']['peakFolder']), logfile)
if not conf_dict['General']['peakFolder'].startswith('/'):
conf_dict['General']['peakFolder'] = conf_dict['General'][
'startdir'] + conf_dict['General']['peakFolder']
if not conf_dict['General']['peakFolder'].endswith('/'):
conf_dict['General']['peakFolder'] += "/"
if not os.path.isdir(conf_dict['General']['peakFolder']):
ewlog("Folder %s not found" % (conf_dict['General']['peakFolder']),
logfile)
if conf_dict['General']['mode'] == "signal":
wlog("signal mode is activated", logfile)
if conf_dict['General']['bwfolder']:
wlog("bwFolder is specified, checking data for signal mode",
logfile)
if "~" in conf_dict['General']['bwfolder']:
wlog(
'require absolute path for bwFolder, bwFolder cannot contain "~", current Folder is %s, use peak mode'
% (conf_dict['General']['bwfolder']), logfile)
conf_dict['General']['mode'] = "binary"
else:
if not conf_dict['General']['bwfolder'].startswith('/'):
conf_dict['General']['bwfolder'] = conf_dict['General'][
'startdir'] + conf_dict['General']['bwfolder']
if not conf_dict['General']['bwfolder'].endswith('/'):
conf_dict['General']['bwfolder'] += "/"
if not os.path.isdir(conf_dict['General']['bwfolder']):
wlog(
"bwFolder %s not found, use binary mode" %
(conf_dict['General']['peakFolder']), logfile)
conf_dict['General']['mode'] = "binary"
else:
wlog("bwfolder is not specified, use binary mode", logfile)
conf_dict['General']['mode'] = "binary"
else:
wlog("binary mode is activaed", logfile)
wlog(
"Check the peak.bed files in the Folder, only '.bed' files with >1000 peaks are included in the following analysis",
logfile)
conf_dict['General']['peakfilenames'] = []
for f in os.listdir(conf_dict['General']['peakFolder']):
if f.endswith(".bed") and os.path.isfile(
conf_dict['General']['peakFolder'] + f):
checkbed = checkbedformat(conf_dict['General']['HMRpeak'], 1000)
if checkbed == "pass":
conf_dict['General']['peakfilenames'].append(f[:-4])
if (len(conf_dict['General']['peakfilenames']) == 0):
ewlog(
"no peak file (cofactor candidate) in (bed format & >1000peaks) are included, exit",
logfile)
if conf_dict['General']['mode'] == "signal":
conf_dict['General']['bwfilenames'] = []
for f in os.listdir(conf_dict['General']['bwfolder']):
if f.endswith(".bw") and os.path.isfile(
conf_dict['General']['bwfolder'] + f):
conf_dict['General']['bwfilenames'].append(f[:-3])
### compare the name from bwfiles and peak files
conf_dict['General']['usefilename'] = []
for name in conf_dict['General']['bwfilenames']:
if name in conf_dict['General']['peakfilenames']:
conf_dict['General']['usefilename'].append(name)
### if less than 50% peakfiles share name with bwfiles, change back to peak mode
if len(conf_dict['General']['usefilename']) < len(
conf_dict['General']['peakfilenames']) * 0.5:
conf_dict['General']['mode'] = "binary"
wlog(
"the number of shared peak&bw files is less than half of the number of peakfiles, use binary mode",
logfile)
else:
wlog("all checks for signal mode passed, use signal mode", logfile)
if conf_dict['General']['mode'] == "binary":
conf_dict['General']['usefilename'] = conf_dict['General'][
'peakfilenames']
wlog(
"%s cofactor candidates are included" %
(len(conf_dict['General']['usefilename'])), logfile)
#checkbed = checkbedformat(conf_dict['General']['HMRpeak'],1000)
#if checkbed == "pass":
#conf_dict['General']['peakfilenames'].append(f[:-3])
outf = open(
conf_dict['General']['outname'] + "_cofactor_candidate_list.txt", 'w')
for cofactor in conf_dict['General']['usefilename']:
outf.write(cofactor + "\n")
outf.close()
### check options
wlog('check option: ', logfile)
#
try:
wlog(
"extend length for HMsignal is %s bp" %
(int(conf_dict['options']['ext'])), logfile)
conf_dict['options']['ext'] = int(conf_dict['options']['ext'])
except:
wlog(
"extend length %s is not valid, use default value: 1000bp" %
(conf_dict['options']['ext']), logfile)
conf_dict['options']['ext'] = 1000
try:
wlog(
"use Pvalue = %s as cutoff" %
(str(float(conf_dict['options']['Pvalue']))), logfile)
except:
wlog(
"input Pvalue %s is not recognized, use default Pvalue=0.001" %
(conf_dict['options']['Pvalue']), logfile)
conf_dict['options']['Pvalue'] = 0.001
if float(conf_dict['options']['Pvalue']) >= 1:
wlog(
"input Pvalue %s is not valid, use default Pvalue=0.001" %
(conf_dict['options']['Pvalue']), logfile)
conf_dict['options']['Pvalue'] = 0.001
try:
usealpha = float(conf_dict['options']['Alpha'])
if usealpha >= 1:
wlog("alpha (for elastic-net) cannot be >=1, use alpha=0.5",
logfile)
conf_dict['options']['Alpha'] = 0.5
else:
wlog(
"Alpha (for elastic-net) = %s" %
(str(float(conf_dict['options']['Alpha']))), logfile)
conf_dict['options']['Alpha'] = usealpha
except:
wlog(
"input alpha (for elastic-net) %s is not valid, use alpha=0.5" %
(conf_dict['options']['Alpha']), logfile)
wlog("Lambda choice is %s" % (conf_dict['options']['Lambda']), logfile)
if conf_dict['options']['TopNcofactors'] == "all":
wlog("all significant co-factors will be output", logfile)
else:
try:
topTF = int(conf_dict['options']['TopNcofactors'])
wlog(
"the topN number %s will be output" %
(conf_dict['options']['TopNcofactors']), logfile)
conf_dict['options']['TopNcofactors'] = topTF
except:
wlog(
"the topN number %s is not valid, output top5 co-factors" %
(conf_dict['options']['TopNcofactors']), logfile)
conf_dict['options']['TopNcofactors'] = 5
OS = platform.system()
if OS == "Linux":
bwsum_software = "bigWigSummary_linux"
elif OS == "Darwin":
bwsum_software = "bigWigSummary_mac"
else:
wlog(
"detected system is nither linux nor mac, try linux version of bigWigSummary",
logfile)
bwsum_software = "bigWigSummary_linux"
conf_dict['General'][
'bwsummary'] = HMRpipe.__path__[0] + "/%s" % bwsum_software
if os.path.isfile(HMRpipe.__path__[0] + "/bedtools"):
conf_dict['General']['bedtools'] = HMRpipe.__path__[0] + "/bedtools"
else:
conf_dict['General']['bedtools'] = "bedtools"
### check Rscript
#if not 'Usage' in sperr('Rscript')[1] and not 'version' in sperr('Rscript')[1]:
# ewlog('require Rscript',logfile)
### check pdflatex
if sp('pdflatex --help')[0] == "":
wlog(
'pdflatex was not installed, ncHMR_detector is still processing but no summary report generated',
logfile)
conf_dict['General']['latex'] = 0
else:
conf_dict['General']['latex'] = 1
return conf_dict
def step3_summary(conf_dict, logfile):
'''
analysis part
mainly Rscript
dimentional reduction + clustering
'''
# start
# create section for
wlog('collect results', logfile)
# Rscript analysis.r expmat outname coverGN highvarZ selectPCcutoff rdnumber maxKnum
summarydir = 'summary/'
createDIR(summarydir)
sp("mv %s_NCsummary.txt %s" %
(conf_dict['General']['outname'], summarydir))
sp("mv %s_elnet_lambdaSelection.pdf %s" %
(conf_dict['General']['outname'], summarydir))
if os.path.isfile("%s_cofactor_HMsignal.pdf" %
conf_dict['General']['outname']):
sp("mv %s_cofactor_HMsignal.pdf %s" %
(conf_dict['General']['outname'], summarydir))
tmpresult = 'tmpResults/'
createDIR(tmpresult)
sp("mv %s_HMsig.bed %s" % (conf_dict['General']['outname'], tmpresult))
sp("mv %s_peakov.bed %s" % (conf_dict['General']['outname'], tmpresult))
sp("mv %s_cofactor_candidate_list.txt %s" %
(conf_dict['General']['outname'], tmpresult))
sp("mv %s_filterNC.txt %s" % (conf_dict['General']['outname'], tmpresult))
wlog('generate summary documents', logfile)
### initiate
QCdoc = """\documentclass[11pt,a4paper]{article}
\usepackage{tabularx}
\usepackage[english]{babel}
\usepackage{array}
\usepackage{graphicx}
\usepackage{color}
\DeclareGraphicsExtensions{.eps,.png,.pdf,.ps}
\\begin{document}
\\title{Summary reports of non-classical function detection of : %s}
\\vspace{-1cm}
\maketitle
\\tableofcontents
\\newpage
\\newpage
\section{Data description}
\\begin{quotation}
Table 1 mainly describes the input files, parameters and options.
\end{quotation}
\\begin{table}[h]
\\small
\caption{parameter description}\label{bstable}
\\begin{tabularx}{\\textwidth}{ |X|l| }
""" % (strlatexformat(conf_dict['General']['outname']))
### table1 prepare parameter
NcoTF = len(conf_dict['General']['peakfilenames'])
QCdoc += """
\hline
parameter & value \\\\
\hline
output name & %s \\\\
\hline
HMRpeak(peak filename) & %s \\\\
\hline
mode & %s \\\\
\hline
HM signal(bw filename) & \\begin{tabular}[c]{@{}l@{}}%s\end{tabular} \\\\
\hline
\#cofactor candidates & %s \\\\
\hline
options & value \\\\
\hline
extend size & %sbp \\\\
\hline
Alpha (Elastic net) & %s \\\\
\hline
Pvalue cutoff & %s \\\\
\hline
topN cofactors & %s \\\\
\hline
""" % (strlatexformat(conf_dict['General']['outname']),
strlatexformat(conf_dict['General']['HMRpeak'].split("/")[-1]),
conf_dict['General']['mode'],
strlatexformat("\\\\ ".join(conf_dict['General']['signalname'])),
str(NcoTF), str(conf_dict['options']['ext']),
str(conf_dict['options']['Alpha']), str(conf_dict['options']['Pvalue']),
str(conf_dict['options']['TopNcofactors']))
QCdoc += """
\end{tabularx}
\end{table}
"""
### cross validation in elastic net
QCdoc += """
\\newpage
\\newpage
\section{ElasticNet co-factor selection}
In this step we use a feature selection (elastic-net. Zou, H. and Hastie T. (2005) to select potential co-factors which corresponded to the non-classical function. Below shows the cross-validation curve for the decison of lambda in elastic-net for each histone modification substrate.
\\begin{figure}[h]
\caption{cross-validation curve for lambda decision} \label{fig:profileunion}
\setlength{\\abovecaptionskip}{0pt}
\setlength{\\belowcaptionskip}{10pt}
\centering
{\includegraphics[width=0.8\\textwidth]{%s}}
\end{figure}
""" % (conf_dict['General']['outname'] + "_elnet_lambdaSelection.pdf")
inf_ncsummary = open("summary/" + conf_dict['General']['outname'] +
"_NCsummary.txt")
line = inf_ncsummary.readline()
if line.startswith("no non-classical function detected"):
QCdoc += """
\\newpage
\\newpage
\section{potential co-factors corresponded to non-classical function}
No significant co-factor was detected, indicating that the non-classical function of the HMR was not exist or none of the existing factor candidates act as a co-factor of the non-classical function.
"""
else:
QCdoc += """
\\newpage
\\newpage
\section{potential co-factors corresponded to non-classical function}
In summary, %s factors were predicted to potentially act as a co-factor of the non-classical function. The top%s co-factors were listed.
\subsection{summary of co-factors}
\\begin{quotation}
The corresponded histone modification substrate (HMsubstrate), empirical P-value, R-square (ordered) and the number of non-classical (NC) sites for each potential co-factor were listed below. The empirical P-value was calculated based on the comparison of foreground (observed) R-square and background R-square (distribution of random R-square generated from the 1,000 permutations of co-binding events) for each potential co-factor. The non-classical (NC) sites were defined by lower HMsubstrate signal (using Otus' method) and co-binding events of each potential co-factor.
\end{quotation}
\\begin{table}[h]
\\small
\caption{cofactor summary}\label{bstable}
\\begin{tabular}{ |l|l|l|l|l| }
\hline
co-factor & HMsubstrate & Pval & Rsquare & NCsites \\\\
""" % (int(
sp("wc -l tmpResults/%s_filterNC.txt" %
(conf_dict['General']['outname']))[0].split()[0]) - 1,
int(
sp("wc -l summary/%s_NCsummary.txt" %
(conf_dict['General']['outname']))[0].split()[0]) - 1)
for line in inf_ncsummary:
if line.startswith("TFname"):
continue
ll = line.split()
this_doc = """\hline
%s & %s & %s & %s & %s \\\\
""" % (strlatexformat(ll[0]), strlatexformat(
ll[1]), ll[2], round(float(ll[3]), 3), ll[5])
QCdoc += this_doc
inf_ncsummary.close()
QCdoc += """
\hline
\end{tabular}
\end{table}
\\newpage
\\newpage
\subsection{Boxplot of HM on non-classical and classic sites}
\\begin{quotation}
Boxplot was generated to compare the difference of the histone mark (HM) signal on either non-classical or classic sites(peak). The non-classical sites were defined by lower HM signal (using Otus' method) and co-binding events of each potential co-factor. The boxplot corresponded to top co-factors were displayed.
\end{quotation}
\\begin{figure}[h]
\caption{boxplot cofactor HMsignal} \label{fig:profileunion}
\setlength{\\abovecaptionskip}{0pt}
\setlength{\\belowcaptionskip}{10pt}
\centering
{\includegraphics[width=0.8\\textwidth]{%s}}
\end{figure}
""" % ((conf_dict['General']['outname'] + "_cofactor_HMsignal.pdf"))
QCdoc += """
\\newpage
\\newpage
\section{Output list}
\\begin{quotation}
All the main output files were described in the following table
\end{quotation}
\\begin{table}[h]
\\small
\caption{output list}\label{bstable}
\\begin{tabular}{ |l|l| }
\hline
description & filename \\\\
\hline
summary table of non-classical (NC) function & summary/%s \\\\
\hline
summary report (this doc) & summary/%s \\\\
\hline
cobinding matrix on HMR peaks & tmpResults/%s \\\\
\hline
histone mark signal on HMR peaks & tmpResults/%s \\\\
\hline
\end{tabular}
\end{table}
\end{document}
""" % (strlatexformat(conf_dict['General']['outname'] + "_NCsummary.txt"),
strlatexformat(conf_dict['General']['outname'] + "_summary.pdf"),
strlatexformat(conf_dict['General']['outname'] + "_peakov.bed"),
strlatexformat(conf_dict['General']['outname'] + "_HMsig.bed"))
latexfile = conf_dict['General']['outname'] + '_summary.tex'
outf = open(summarydir + latexfile, 'w')
outf.write(QCdoc)
outf.close()
cmd = "pdflatex %s" % (latexfile)
cmd2 = 'cp %s ../' % (conf_dict['General']['outname'] + '_summary.pdf')
if conf_dict['General']['latex'] == 1:
wlog(
'pdflatex was detected in default PATH, generate summary report %s'
% (conf_dict['General']['outname'] + '_summary.pdf'), logfile)
os.chdir(summarydir)
tmpobj = sp(cmd)
tmpobj = sp(cmd)
tmpobj = sp(cmd2)
tmpobj = sp("rm %s_summary.aux" % conf_dict['General']['outname'])
tmpobj = sp("rm %s_summary.log" % conf_dict['General']['outname'])
tmpobj = sp("rm %s_summary.toc" % conf_dict['General']['outname'])
# for files in os.listdir(plot_folder):
# if os.path.isfile(files) and files[-12:-4] == "_summary":
# if not files[-4:] in ['.tex','.pdf',',png','.txt']:
# cmd = "rm %s"%(files)
# rwlog(cmd,logfile)
else:
wlog(
'pdflatex was not detected in default PATH, generate summary report .tex file in summary/ folder, you can move the whole summary/ folder to the environment with pdflatex installed and run cmd in the summary/ folder: "pdflatex %s"'
% (conf_dict['General']['outname'] + '_summary.tex'), logfile)
#if conf_dict['clean']:
# wlog('--clean pararmeter was turned on, remove internal files with large size',logfile)
# rwlog("rm %s "%(conf_dict['General']['outputdirectory'] + 'expmatrix/' + conf_dict['General']['outname']+'_on_symbol.bed'),logfile)
# rwlog("rm %s "%(conf_dict['General']['outputdirectory'] + 'expmatrix/' + conf_dict['General']['outname']+'_on_cds.bed'),logfile)
# rwlog("rm %s "%(conf_dict['General']['outputdirectory'] + 'expmatrix/' + conf_dict['General']['outname']+'_on_3utr.bed'),logfile)
# rwlog("rm %s "%(conf_dict['General']['outputdirectory'] + 'expmatrix/' + conf_dict['General']['outname']+'_on_5utr.bed'),logfile)
# rwlog("rm %s "%(conf_dict['General']['outputdirectory'] + 'expmatrix/' + conf_dict['General']['outname']+'_on_TTSdis.bed'),logfile)
# rwlog("rm %s "%(conf_dict['General']['outputdirectory'] + 'expmatrix/' + conf_dict['General']['outname']+'_combined.bed'),logfile)
# rwlog("rm %s "%(conf_dict['General']['outputdirectory'] + 'expmatrix/' + conf_dict['General']['outname']+'_barcode_reform.txt'),logfile)
#
os.chdir("../")
wlog('Step3 summary DONE, check %s for final outputs' % (summarydir),
logfile)
return conf_dict
def step0_check_data(conf_dict, logfile):
'''
step0 integrate data
check and complement parameter
'''
### check data path , format ,
if "~" in conf_dict['General']['HMRpeak']:
ewlog(
'require absolute path for HMRpeak bed file, HMRpeak file cannot contain "~", current HMRpeak file is %s'
% (conf_dict['General']['HMRpeak']), logfile)
if "~" in conf_dict['General']['signal']:
ewlog(
'require absolute path for HMsignal bigwig file, signal file cannot contain "~", current signal file is %s'
% (conf_dict['General']['signal']), logfile)
if not conf_dict['General']['HMRpeak'].startswith('/'):
conf_dict['General']['HMRpeak'] = conf_dict['General'][
'startdir'] + conf_dict['General']['HMRpeak']
if not conf_dict['General']['signal'].startswith('/'):
conf_dict['General']['signal'] = conf_dict['General'][
'startdir'] + conf_dict['General']['signal']
if not os.path.isfile(conf_dict['General']['HMRpeak']):
ewlog("HMRpeak file %s not found" % (conf_dict['General']['HMRpeak']),
logfile)
if not os.path.isfile(conf_dict['General']['signal']):
ewlog("signal bw file %s not found" % (conf_dict['General']['signal']),
logfile)
if not conf_dict['General']['HMRpeak'].endswith('.bed'):
ewlog('extenion of HMR peak file is not .bed', logfile)
checkbed = checkbedformat(conf_dict['General']['HMRpeak'], 1000)
if checkbed == "fail":
ewlog("HMRpeak file is not a bed file", logfile)
elif checkbed == "lesspeak":
ewlog("HMRpeak file contains less than 1000 peaks")
if conf_dict['General']['signal'].endswith('.bw'):
conf_dict['General']['signalname'] = conf_dict['General'][
'signal'].split("/")[-1][:-3]
elif conf_dict['General']['signal'].endswith('.bigwig'):
conf_dict['General']['signalname'] = conf_dict['General'][
'signal'].split("/")[-1][:-7]
else:
wlog('[WARNING] extension of signal bw file is not bw/bigwig', logfile)
### check TFpeak folder
if "~" in conf_dict['General']['peakFolder']:
ewlog(
'require absolute path for peakFolder, peakFolder cannot contain "~", current peakFolder is %s'
% (conf_dict['General']['peakFolder']), logfile)
if not conf_dict['General']['peakFolder'].startswith('/'):
conf_dict['General']['peakFolder'] = conf_dict['General'][
'startdir'] + conf_dict['General']['peakFolder']
if not conf_dict['General']['peakFolder'].endswith('/'):
conf_dict['General']['peakFolder'] += "/"
if not os.path.isdir(conf_dict['General']['peakFolder']):
ewlog("peakFolder %s not found" % (conf_dict['General']['peakFolder']),
logfile)
wlog(
"Check the peak.bed files in the peakFolder, only '.bed' files with >1000 peaks are included in the following analysis",
logfile)
conf_dict['General']['peakfilenames'] = []
for f in os.listdir(conf_dict['General']['peakFolder']):
if f.endswith(".bed") and os.path.isfile(
conf_dict['General']['peakFolder'] + f):
checkbed = checkbedformat(conf_dict['General']['HMRpeak'], 1000)
if checkbed == "pass":
conf_dict['General']['peakfilenames'].append(f[:-4])
if (len(conf_dict['General']['peakfilenames']) == 0):
ewlog(
"no peak file (cofactor candidate) in bed format & >1000peaks are included, exit",
logfile)
else:
wlog(
"%s peak files (cofactor candidates) are included" %
(len(conf_dict['General']['peakfilenames'])), logfile)
outf = open(
conf_dict['General']['outname'] + "_cofactor_candidate_list.txt", 'w')
for cofactor in conf_dict['General']['peakfilenames']:
outf.write(cofactor + "\n")
outf.close()
### check options
wlog('check option: ', logfile)
try:
wlog("extend length is %s bp" % (int(conf_dict['options']['ext'])),
logfile)
conf_dict['options']['ext'] = int(conf_dict['options']['ext'])
except:
wlog(
"extend length %s is not valid, use default value: 1000bp" %
(conf_dict['options']['ext']), logfile)
conf_dict['options']['ext'] = 1000
try:
wlog(
"use Pvalue = %s as cutoff" %
(str(float(conf_dict['options']['Pvalue']))), logfile)
except:
wlog(
"input Pvalue %s is not recognized, use default Pvalue=0.001" %
(conf_dict['options']['Pvalue']), logfile)
conf_dict['options']['Pvalue'] = 0.001
if float(conf_dict['options']['Pvalue']) >= 1:
wlog(
"input Pvalue %s is not valid, use default Pvalue=0.001" %
(conf_dict['options']['Pvalue']), logfile)
conf_dict['options']['Pvalue'] = 0.001
try:
usealpha = float(conf_dict['options']['Alpha'])
if usealpha >= 1:
wlog("alpha cannot be >=1, use alpha=0.5", logfile)
conf_dict['options']['Alpha'] = 0.5
else:
wlog("Alpha = %s" (str(float(conf_dict['options']['Alpha']))),
logfile)
conf_dict['options']['Alpha'] = usealpha
except:
wlog(
"input alpha %s is not valid, use alpha=0.5" %
(conf_dict['options']['Alpha']), logfile)
wlog("Lambda choice is %s" % (conf_dict['options']['Lambda']), logfile)
if conf_dict['options']['TopNcofactors'] == "all":
wlog("all significant co-factors will be output", logfile)
else:
try:
topTF = int(conf_dict['options']['TopNcofactors'])
wlog(
"the topN number %s will be output" %
(conf_dict['options']['TopNcofactors']), logfile)
conf_dict['options']['TopNcofactors'] = topTF
except:
wlog(
"the topN number %s is not valid, output top5 co-factors" %
(conf_dict['options']['TopNcofactors']), logfile)
conf_dict['options']['TopNcofactors'] = 5
OS = platform.system()
if OS == "Linux":
bwsum_software = "bigWigSummary_linux"
elif OS == "Darwin":
bwsum_software = "bigWigSummary_mac"
else:
wlog("detected system is nither linux nor mac, try linux version",
logfile)
bwsum_software = "bigWigSummary_linux"
conf_dict['General']['software'] = bwsum_software
### check Rscript
#if not 'Usage' in sperr('Rscript')[1] and not 'version' in sperr('Rscript')[1]:
# ewlog('require Rscript',logfile)
### check pdflatex
if sp('pdflatex --help')[0] == "":
wlog(
'pdflatex was not installed, HMR is still processing but no summary report generated',
logfile)
conf_dict['General']['latex'] = 0
else:
conf_dict['General']['latex'] = 1
return conf_dict