def write_html_report(self):
"""
write the report as html
"""
out_folder = self.opts.outdir
my_template = Template(
filename=os.path.join(self.tool_folder, self.__class__.HTML_REPORT_TEMPLATE),
strict_undefined=True)
if os.path.exists(os.path.abspath(out_folder)):
files = [os.path.join(out_folder, x) for x in os.listdir(out_folder)
if not x.startswith('.')]
files.sort(key=lambda f: os.path.getmtime(f))
file_info = [(os.path.split(f)[-1], getFileString(os.path.split(f)[-1], self.opts.outdir))
for f in files]
else:
file_info = []
template_parameters = {
'program_name': str(self.program_name),
'timestamp' : str(timenow()),
'file_info': file_info,
'log_data' : open(self.tlogname).read().replace('\n', '\n<BR />'),
'command_string': str(self.cl)
}
f = open(self.opts.htmlout, 'w')
f.write(my_template.render(**template_parameters))
f.close()
def write_html_report(self):
"""
write the report as html
"""
out_folder = self.opts.outdir
my_template = Template(filename=os.path.join(
self.tool_folder, self.__class__.HTML_REPORT_TEMPLATE),
strict_undefined=True)
if os.path.exists(os.path.abspath(out_folder)):
files = [
os.path.join(out_folder, x) for x in os.listdir(out_folder)
if not x.startswith('.')
]
files.sort(key=lambda f: os.path.getmtime(f))
file_info = [
(os.path.split(f)[-1],
getFileString(os.path.split(f)[-1], self.opts.outdir))
for f in files
]
else:
file_info = []
template_parameters = {
'program_name': str(self.program_name),
'timestamp': str(timenow()),
'file_info': file_info,
'log_data': open(self.tlogname).read().replace('\n', '\n<BR />'),
'command_string': str(self.cl)
}
f = open(self.opts.htmlout, 'w')
f.write(my_template.render(**template_parameters))
f.close()
def makehtml(self):
"""
write the report as html
"""
logdat = open(self.tlogname,'r').readlines()
res = []
res.append(galhtmlprefix % progname)
res.append(galhtmlattr % (progname,timenow()))
res.append('<b>Your job produced the following outputs - check here for a record of what was done and any unexpected events</b><hr/>')
try:
flist = os.listdir(self.opts.outdir)
except:
flist = []
if len(flist) > 0: # show what's left
flist = [x for x in flist if not (x.startswith('.') or x == 'None')]
tlist = [(os.path.getmtime(os.path.join(self.opts.outdir,x)),x) for x in flist]
tlist.sort()
flist = [x[1] for x in tlist]
res.append('<div><b>Output files.</b><hr/>\n')
res.append('<table>\n')
for i,f in enumerate(flist):
fn = os.path.split(f)[-1]
fs = getFileString(fn,self.opts.outdir)
res.append('<tr><td><a href="%s">%s</a></td></tr>\n' % (fn,fs))
res.append('</table></div>\n')
res.append('<b>Log of activity</b><hr/>\n')
res.append('\n%s' % '<br/>'.join(logdat))
res.append('<hr/>Note: The freely available <a href="http://picard.sourceforge.net/command-line-overview.shtml">Picard software</a> \n')
res.append('generated all outputs reported here. These third party tools were')
res.append('orchestrated by the Galaxy rgEstLibComplexity wrapper and this command line from the Galaxy form:<br/>\n%s' % (self.cl))
res.append(galhtmlpostfix)
f = open(self.opts.htmlout,'w')
f.write('\n'.join(res))
f.close()
def __init__(self, opts=None, cl=[], tidy=True):
"""
"""
self.ourname = 'rgGATKRecal'
self.opts = opts
self.tidy = tidy
self.cl = ' '.join(cl) # ready for the htmlfile output
self.delme = []
killme = string.punctuation + string.whitespace
trantab = string.maketrans(killme, '_' * len(killme))
self.title = self.opts.title.translate(trantab)
self.tlogname = os.path.join(
self.opts.outdir, '%s_rg%s_Log.txt' % (self.title, self.ourname))
self.tlog = open(self.tlogname, 'w')
self.outtxt = '%s_%s_Out.txt' % (self.title, self.ourname)
self.GATK_CVFlags = opts.GATK_CVflags
self.Rscriptpath = whereis('Rscript')
self.info = '%s on %s at %s' % (self.ourname, self.title, timenow())
if self.Rscriptpath == None: # GATK wants the explicit path to Rscript which comes with R now
p = os.environ.get('PATH', '')
self.tlog.write('### Cannot find %s on %s\n' % (program, p))
self.Rscriptpath = '/share/shared/lx26-amd64/bin/Rscript'
self.pdfoutdir = os.path.join(self.opts.outdir, 'pdfplots')
self.preplotprefix = 'rgPreRecal_'
self.postplotprefix = 'rgPostRecal_'
try:
os.makedirs(self.pdfoutdir)
except:
self.tlog.write('## unable to create pdf output dir %s' %
self.pdfoutdir)
self.delme.append(self.pdfoutdir)
self.runGATK()
self.writehtml()
def __init__(self, opts=None, cl=[], tidy=True):
"""
"""
self.ourname = "rgGATKRecal"
self.opts = opts
self.tidy = tidy
self.cl = " ".join(cl) # ready for the htmlfile output
self.delme = []
killme = string.punctuation + string.whitespace
trantab = string.maketrans(killme, "_" * len(killme))
self.title = self.opts.title.translate(trantab)
self.tlogname = os.path.join(self.opts.outdir, "%s_rg%s_Log.txt" % (self.title, self.ourname))
self.tlog = open(self.tlogname, "w")
self.outtxt = "%s_%s_Out.txt" % (self.title, self.ourname)
self.GATK_CVFlags = opts.GATK_CVflags
self.Rscriptpath = whereis("Rscript")
self.info = "%s on %s at %s" % (self.ourname, self.title, timenow())
if self.Rscriptpath == None: # GATK wants the explicit path to Rscript which comes with R now
p = os.environ.get("PATH", "")
self.tlog.write("### Cannot find %s on %s\n" % (program, p))
self.Rscriptpath = "/share/shared/lx26-amd64/bin/Rscript"
self.pdfoutdir = os.path.join(self.opts.outdir, "pdfplots")
self.preplotprefix = "rgPreRecal_"
self.postplotprefix = "rgPostRecal_"
try:
os.makedirs(self.pdfoutdir)
except:
self.tlog.write("## unable to create pdf output dir %s" % self.pdfoutdir)
self.delme.append(self.pdfoutdir)
self.runGATK()
self.writehtml()
def makehtml(self):
"""
write the report as html
"""
logdat = open(self.tlogname, 'r').readlines()
res = []
res.append(galhtmlprefix % progname)
res.append(galhtmlattr % (progname, timenow()))
res.append(
'<b>Your job produced the following outputs - check here for a record of what was done and any unexpected events</b><hr/>'
)
imghref = '%s.jpg' % os.path.splitext(self.isPDF)[0] # removes .pdf
res.append('<table cellpadding="10"><tr><td>\n')
res.append(
'<a href="%s"><img src="%s" alt="%s" hspace="10" align="middle"></a>\n'
% (self.isPDF, imghref, imghref))
res.append('</tr><td></table>\n')
try:
flist = os.listdir(self.opts.outdir)
except:
flist = []
if len(
flist
) > 0: # we should clean everything up - picard doesn't tell us what it did in cleansam unfortunately
flist = [
x for x in flist if not (x.startswith('.') or x == 'None')
]
tlist = [(os.path.getmtime(os.path.join(self.opts.outdir, x)), x)
for x in flist]
tlist.sort()
flist = [x[1] for x in tlist]
res.append('<div><b>Output files.</b><hr/>\n')
res.append('<table>\n')
for i, f in enumerate(flist):
fn = os.path.split(f)[-1]
fs = getFileString(fn, self.opts.outdir)
res.append('<tr><td><a href="%s">%s</a></td></tr>\n' %
(fn, fs))
res.append('</table></div>\n')
res.append('<b>Log of activity</b><hr/>\n')
res.append('\n%s' % '<br/>'.join(logdat))
res.append(
'<hr/>Note: The freely available <a href="http://picard.sourceforge.net/command-line-overview.shtml">Picard software</a> \n'
)
res.append(
'generated all outputs reported here. These third party tools were'
)
res.append(
'orchestrated by the Galaxy rgInsertSize wrapper and this command line from the Galaxy form:<br/>\n%s'
% (self.cl))
res.append(galhtmlpostfix)
f = open(self.opts.htmlout, 'w')
f.write('\n'.join(res))
f.close()
def writehtml(self):
"""
write the report as html
"""
logdat = open(self.tlogname,'r').readlines()
res = []
res.append(galhtmlprefix % progname)
res.append(galhtmlattr % (progname,timenow()))
try:
flist = os.listdir(self.opts.outdir)
except:
flist = []
if len(flist) > 0: # show what's left
flist = [x for x in flist if not (x.startswith('.') or x == 'None')]
pdfs = [x for x in flist if os.path.splitext(x)[-1].lower() == '.pdf']
tlist = [(os.path.getmtime(os.path.join(self.opts.outdir,x)),x) for x in flist]
tlist.sort()
flist = [x[1] for x in tlist]
if len(pdfs) > 0:
cells = []
pdfs.sort()
res.append('<div><table cellpadding="5" cellspacing="10">\n')
for p in pdfs:
pfname = os.path.split(p)[-1]
pfroot = os.path.splitext(pfname)[0]
imghref = '%s.jpg' % pfroot # thumbnail name from mogrify
cl = ['mogrify', '-resize x300 -write %s %s' % (imghref,pfname),]
self.run(cl)
s = '<a href="%s"><img src="%s" alt="%s" hspace="10" align="middle"></a>' % (pfname,imghref,pfname)
cells.append('<td>%s</br>%s</td>' % (pfroot,s))
ncells = len(cells)
for i in range(ncells):
if i % 2 == 1:
res.append('<tr>%s%s</tr>\n' % (cells[i-1],cells[i]))
if ncells % 2 == 0: # last one
res.append('<tr colspan="2">%s</tr>\n' % (cells[-1]))
res.append('</table></div>\n')
res.append('<div><b>Output files.</b><hr/>\n')
res.append('<table>\n')
for i,f in enumerate(flist):
fn = os.path.split(f)[-1]
fs = getFileString(fn,self.opts.outdir)
res.append('<tr><td><a href="%s">%s</a></td></tr>\n' % (fn,fs))
res.append('</table></div>\n')
res.append('<b>Your job produced the following log of activity - check here for a record of what was done and any unexpected events</b><hr/>')
res.append('\n%s' % '<br/>'.join(logdat))
res.append('<hr/>Note: The freely available <a href="http://www.broadinstitute.org/gsa/wiki/index.php/Main_Page">GATK</a> \n')
res.append('did all the work reportexampleBAM.bam ed here. GATK is an independent non-Galaxy community resource, whose third party tools were')
res.append('orchestrated by the Galaxy rgGATKRecalibrate wrapper and this command line from the Galaxy form:<br/>\n%s' % (self.cl))
res.append(galhtmlpostfix)
f = open(self.opts.htmlout,'w')
f.write('\n'.join(res))
f.close()
def writehtml(self):
"""
write the report as html
"""
logdat = open(self.tlogname,'r').readlines()
res = []
res.append(galhtmlprefix % progname)
res.append(galhtmlattr % (progname,timenow()))
try:
flist = os.listdir(self.opts.outdir)
except:
flist = []
if len(flist) > 0: # show what's left
flist = [x for x in flist if not (x.startswith('.') or x == 'None')]
pdfs = [x for x in flist if os.path.splitext(x)[-1].lower() == '.pdf']
tlist = [(os.path.getmtime(os.path.join(self.opts.outdir,x)),x) for x in flist]
tlist.sort()
flist = [x[1] for x in tlist]
if len(pdfs) > 0:
cells = []
pdfs.sort()
res.append('<div><table cellpadding="5" cellspacing="10">\n')
for p in pdfs:
pfname = os.path.split(p)[-1]
pfroot = os.path.splitext(pfname)[0]
imghref = '%s.jpg' % pfroot # thumbnail name from mogrify
cl = ['mogrify', '-resize x300 -write %s %s' % (imghref,pfname),]
self.run(cl)
s = '<a href="%s"><img src="%s" title="%s" hspace="10" align="middle"></a>' % (pfname,imghref,pfname)
cells.append('<td>%s</br>%s</td>' % (pfroot,s))
ncells = len(cells)
for i in range(ncells):
if i % 2 == 1:
res.append('<tr>%s%s</tr>\n' % (cells[i-1],cells[i]))
if ncells % 2 == 0: # last one
res.append('<tr colspan="2">%s</tr>\n' % (cells[-1]))
res.append('</table></div>\n')
res.append('<div><b>Output files.</b><hr/>\n')
res.append('<table>\n')
for i,f in enumerate(flist):
fn = os.path.split(f)[-1]
fs = getFileString(fn,self.opts.outdir)
res.append('<tr><td><a href="%s">%s</a></td></tr>\n' % (fn,fs))
res.append('</table></div>\n')
res.append('<b>Your job produced the following log of activity - check here for a record of what was done and any unexpected events</b><hr/>')
res.append('\n%s' % '<br/>'.join(logdat))
res.append('<hr/>Note: The freely available <a href="http://www.broadinstitute.org/gsa/wiki/index.php/Main_Page">GATK</a> \n')
res.append('did all the work reportexampleBAM.bam ed here. GATK is an independent non-Galaxy community resource, whose third party tools were')
res.append('orchestrated by the Galaxy rgGATKRecalibrate wrapper and this command line from the Galaxy form:<br/>\n%s' % (self.cl))
res.append(galhtmlpostfix)
f = open(self.opts.htmlout,'w')
f.write('\n'.join(res))
f.close()
def __init__(self,opts=None,cl=[],tidy=True):
"""
"""
self.ourname = 'rgSortBam'
self.opts = opts
self.tidy = tidy
self.cl = ' '.join(cl) # ready for the htmlfile output
self.delme = []
killme = string.punctuation + string.whitespace
trantab = string.maketrans(killme,'_'*len(killme))
self.title = self.opts.title.translate(trantab)
fd,self.tlogname = tempfile.mkstemp(dir=self.opts.tmpdir,suffix='rgSortBam.log')
self.tlog = open(self.tlogname,'w')
self.info = '%s on %s at %s' % (self.ourname,self.opts.title,timenow())
def __init__(self,opts=None,cl=[],tidy=False):
"""
"""
self.ourname = 'rgPicardInsertSize'
self.opts = opts
self.tidy = tidy
self.cl = ' '.join(cl) # ready for the htmlfile output
self.delme = []
killme = string.punctuation + string.whitespace
trantab = string.maketrans(killme,'_'*len(killme))
self.title = self.opts.title.translate(trantab)
self.tlogname = os.path.join(self.opts.outdir,'rgInsertSizeMetrics.txt')
self.tlog = open(self.tlogname,'w')
self.isPDF = 'InsertSizeHist.pdf'
self.info = '%s on %s at %s' % (self.ourname,self.title,timenow())
def writehtml(self):
"""
write the report as html
note complications needed to write pre and post reports - they have to be separated since gatk insists on giving them all the same names
but at least allows a separate output directory...
"""
logdat = open(self.tlogname, 'r').readlines()
res = []
res.append(galhtmlprefix % progname)
res.append(galhtmlattr % (progname, timenow()))
res.append(
'<font size="-2">Note: The freely available <a href="http://www.broadinstitute.org/gsa/wiki/index.php/Main_Page">GATK</a>'
)
res.append(
'did all the calculations arranged here in your Galaxy history')
try:
flist = os.listdir(self.opts.outdir)
except:
flist = []
if len(flist) > 0: # show what's left after cleanup
flist = [
x for x in flist if not (x.startswith('.') or x == 'None')
]
pdfs = [
x for x in flist if os.path.splitext(x)[-1].lower() == '.pdf'
]
tlist = [(os.path.getmtime(os.path.join(self.opts.outdir, x)), x)
for x in flist]
tlist.sort()
flist = [x[1] for x in tlist]
if len(pdfs) > 0:
res = self.writeImages(pdfs, res)
res.append('<div><b>Output files.</b><hr/>\n')
res.append('<table>\n')
for i, f in enumerate(flist):
fn = os.path.split(f)[-1]
fs = getFileString(fn, self.opts.outdir)
res.append('<tr><td><a href="%s">%s</a></td></tr>\n' %
(fn, fs))
res.append('</table></div>\n')
res.append(
'<b>Your job produced the following log of activity - check here for a record of what was done and any unexpected events</b><hr/>'
)
res.append('\n%s' % '<br/>'.join(logdat))
res.append(galhtmlpostfix)
f = open(self.opts.htmlout, 'w')
f.write('\n'.join(res))
f.close()
def __init__(self, opts=None, cl=[], tidy=False):
"""
"""
self.ourname = 'rgPicardInsertSize'
self.opts = opts
self.tidy = tidy
self.cl = ' '.join(cl) # ready for the htmlfile output
self.delme = []
killme = string.punctuation + string.whitespace
trantab = string.maketrans(killme, '_' * len(killme))
self.title = self.opts.title.translate(trantab)
self.tlogname = os.path.join(self.opts.outdir,
'rgInsertSizeMetrics.txt')
self.tlog = open(self.tlogname, 'w')
self.isPDF = 'InsertSizeHist.pdf'
self.info = '%s on %s at %s' % (self.ourname, self.title, timenow())
def __init__(self,opts=None,cl=[],tidy=True):
"""
"""
self.ourname = 'rgGATKRecal'
self.opts = opts
self.tidy = tidy
self.cl = ' '.join(cl) # ready for the htmlfile output
self.delme = []
killme = string.punctuation + string.whitespace
trantab = string.maketrans(killme,'_'*len(killme))
self.title = self.opts.title.translate(trantab)
self.tlogname = os.path.join(self.opts.outdir,'%s_rg%s_Log.txt' % (self.title,self.ourname))
self.tlog = open(self.tlogname,'w')
self.outtxt = '%s_%s_Out.txt' % (self.title,self.ourname)
self.info = '%s on %s at %s' % (self.ourname,self.title,timenow())
self.runGATK()
self.writehtml()
def __init__(self, opts=None, cl=[], tidy=True):
"""
"""
self.ourname = 'rgGATKRecal'
self.opts = opts
self.tidy = tidy
self.cl = ' '.join(cl) # ready for the htmlfile output
self.delme = []
killme = string.punctuation + string.whitespace
trantab = string.maketrans(killme, '_' * len(killme))
self.title = self.opts.title.translate(trantab)
self.tlogname = os.path.join(
self.opts.outdir, '%s_rg%s_Log.txt' % (self.title, self.ourname))
self.tlog = open(self.tlogname, 'w')
self.outtxt = '%s_%s_Out.txt' % (self.title, self.ourname)
self.info = '%s on %s at %s' % (self.ourname, self.title, timenow())
self.runGATK()
self.writehtml()
def __init__(self,opts=None,cl=[],fargs=[],tidy=True):
"""
"""
self.ourname = 'rgGATKCoverDepth'
self.fargs = fargs
self.opts = opts
self.tidy = tidy
self.cl = ' '.join(cl) # ready for the htmlfile output
self.delme = []
killme = string.punctuation + string.whitespace
trantab = string.maketrans(killme,'_'*len(killme))
self.title = self.opts.title.translate(trantab)
self.tlogname = os.path.join(self.opts.outdir,'%s_rg%s_Log.txt' % (self.title,self.ourname))
self.tlog = open(self.tlogname,'w')
self.info = '%s on %s at %s' % (self.ourname,self.title,timenow())
try:
os.makedirs(self.opts.outdir)
self.tlog.write('# made out dir %s\n' % self.opts.outdir)
except:
pass
def __init__(self,opts=None,cl=[],fargs=[],tidy=True):
"""
"""
self.ourname = 'rgGATKCoverDepth'
self.fargs = fargs
self.opts = opts
self.tidy = tidy
self.cl = ' '.join(cl) # ready for the htmlfile output
self.delme = []
killme = string.punctuation + string.whitespace
trantab = string.maketrans(killme,'_'*len(killme))
self.title = self.opts.title.translate(trantab)
self.tlogname = os.path.join(self.opts.outdir,'%s_rg%s_Log.txt' % (self.title,self.ourname))
self.tlog = open(self.tlogname,'w')
self.info = '%s on %s at %s' % (self.ourname,self.title,timenow())
try:
os.makedirs(self.opts.outdir)
self.tlog.write('# made out dir %s\n' % self.opts.outdir)
except:
pass
def writehtml(self):
"""
write the report as html
note complications needed to write pre and post reports - they have to be separated since gatk insists on giving them all the same names
but at least allows a separate output directory...
"""
logdat = open(self.tlogname, "r").readlines()
res = []
res.append(galhtmlprefix % progname)
res.append(galhtmlattr % (progname, timenow()))
res.append(
'<font size="-2">Note: The freely available <a href="http://www.broadinstitute.org/gsa/wiki/index.php/Main_Page">GATK</a>'
)
res.append("did all the calculations arranged here in your Galaxy history")
try:
flist = os.listdir(self.opts.outdir)
except:
flist = []
if len(flist) > 0: # show what's left after cleanup
flist = [x for x in flist if not (x.startswith(".") or x == "None")]
pdfs = [x for x in flist if os.path.splitext(x)[-1].lower() == ".pdf"]
tlist = [(os.path.getmtime(os.path.join(self.opts.outdir, x)), x) for x in flist]
tlist.sort()
flist = [x[1] for x in tlist]
if len(pdfs) > 0:
res = self.writeImages(pdfs, res)
res.append("<div><b>Output files.</b><hr/>\n")
res.append("<table>\n")
for i, f in enumerate(flist):
fn = os.path.split(f)[-1]
fs = getFileString(fn, self.opts.outdir)
res.append('<tr><td><a href="%s">%s</a></td></tr>\n' % (fn, fs))
res.append("</table></div>\n")
res.append(
"<b>Your job produced the following log of activity - check here for a record of what was done and any unexpected events</b><hr/>"
)
res.append("\n%s" % "<br/>".join(logdat))
res.append(galhtmlpostfix)
f = open(self.opts.htmlout, "w")
f.write("\n".join(res))
f.close()
def makehtml(self):
"""
write the report as html
"""
logdat = open(self.tlogname,'r').readlines()
res = []
res.append(galhtmlprefix % progname)
res.append(galhtmlattr % (progname,timenow()))
res.append('<b>Your job produced the following outputs - check here for a record of what was done and any unexpected events</b><hr/>')
imghref = '%s.jpg' % os.path.splitext(self.isPDF)[0] # removes .pdf
res.append('<table cellpadding="10"><tr><td>\n')
res.append('<a href="%s"><img src="%s" alt="%s" hspace="10" align="middle"></a>\n' % (self.isPDF,imghref,imghref))
res.append('</tr><td></table>\n')
try:
flist = os.listdir(self.opts.outdir)
except:
flist = []
if len(flist) > 0: # we should clean everything up - picard doesn't tell us what it did in cleansam unfortunately
flist = [x for x in flist if not (x.startswith('.') or x == 'None')]
tlist = [(os.path.getmtime(os.path.join(self.opts.outdir,x)),x) for x in flist]
tlist.sort()
flist = [x[1] for x in tlist]
res.append('<div><b>Output files.</b><hr/>\n')
res.append('<table>\n')
for i,f in enumerate(flist):
fn = os.path.split(f)[-1]
fs = getFileString(fn,self.opts.outdir)
res.append('<tr><td><a href="%s">%s</a></td></tr>\n' % (fn,fs))
res.append('</table></div>\n')
res.append('<b>Log of activity</b><hr/>\n')
res.append('\n%s' % '<br/>'.join(logdat))
res.append('<hr/>Note: The freely available <a href="http://picard.sourceforge.net/command-line-overview.shtml">Picard software</a> \n')
res.append('generated all outputs reported here. These third party tools were')
res.append('orchestrated by the Galaxy rgInsertSize wrapper and this command line from the Galaxy form:<br/>\n%s' % (self.cl))
res.append(galhtmlpostfix)
f = open(self.opts.htmlout,'w')
f.write('\n'.join(res))
f.close()
outfname = sys.argv[3]
logf = sys.argv[4]
logoutdir = sys.argv[5]
gffout = sys.argv[6]
topn = 1000
try:
os.makedirs(logoutdir)
except:
pass
map_file = None
me = sys.argv[0]
amapf = '%s.bim' % bfname # to decode map in xformModel
flog = file(logf,'w')
logme = []
cdir = os.getcwd()
s = 'Rgenetics %s http://rgenetics.org Galaxy Tools, rgCaCo.py started %s\n' % (myversion,timenow())
print >> sys.stdout, s # so will appear as blurb for file
logme.append(s)
if verbose:
s = 'rgCaCo.py: bfname=%s, logf=%s, argv = %s\n' % (bfname, logf, sys.argv)
print >> sys.stdout, s # so will appear as blurb for file
logme.append(s)
twd = tempfile.mkdtemp(suffix='rgCaCo') # make sure plink doesn't spew log file into the root!
tname = os.path.join(twd,name)
vcl = [plinke,'--noweb','--bfile',bfname,'--out',name,'--model']
p=subprocess.Popen(' '.join(vcl),shell=True,stdout=flog,cwd=twd)
retval = p.wait()
resf = '%s.model' % tname # plink output is here we hope
xformModel(bfname,resf,outfname,name,amapf,flog) # leaves the desired summary file
makeGFF(resf=outfname,outfname=gffout,logf=flog,twd=twd,name='rgGLM_TopTable',description=name,topn=topn)
flog.write('\n'.join(logme))
def clean():
"""
"""
if len(sys.argv) < 14:
print >> sys.stdout, '## %s expected 14 params in sys.argv, got %d - %s' % (prog,len(sys.argv),sys.argv)
print >> sys.stdout, """this script will filter a linkage format ped
and map file containing genotypes. It takes 14 parameters - the plink --f parameter and"
a new filename root for the output clean data followed by the mind,geno,hwe,maf, mef and mei"
documented in the plink docs plus the file to be returned to Galaxy
Called as:
<command interpreter="python">
rgLDIndep.py '$input_file.extra_files_path' '$input_file.metadata.base_name' '$title' '$mind'
'$geno' '$hwe' '$maf' '$mef' '$mei' '$out_file1'
'$out_file1.extra_files_path' '$window' '$step' '$r2'
</command>
"""
sys.exit(1)
plog = ['## Rgenetics: http://rgenetics.org Galaxy Tools rgLDIndep.py started %s\n' % timenow()]
inpath = sys.argv[1]
inbase = sys.argv[2]
killme = string.punctuation + string.whitespace
trantab = string.maketrans(killme,'_'*len(killme))
title = sys.argv[3].translate(trantab)
mind = sys.argv[4]
geno = sys.argv[5]
hwe = sys.argv[6]
maf = sys.argv[7]
me1 = sys.argv[8]
me2 = sys.argv[9]
outfname = sys.argv[10]
outfpath = sys.argv[11]
winsize = sys.argv[12]
step = sys.argv[13]
r2 = sys.argv[14]
output = os.path.join(outfpath,outfname)
outpath = os.path.join(outfpath,title)
outprunepath = os.path.join(outfpath,'ldprune_%s' % title)
try:
os.makedirs(outfpath)
except:
pass
bfile = os.path.join(inpath,inbase)
filterout = os.path.join(outpath,'filtered_%s' % inbase)
outf = file(outfname,'w')
outf.write(galhtmlprefix % prog)
ldin = bfile
plinktasks = [['--bfile',ldin,'--indep-pairwise %s %s %s' % (winsize,step,r2),'--out',outpath,
'--mind',mind,'--geno',geno,'--maf',maf,'--hwe',hwe,'--me',me1,me2,],
['--bfile',ldin,'--extract %s.prune.in --make-bed --out %s' % (outpath,outpath)],
['--bfile',outpath,'--recode --out',outpath]] # make map file - don't really need ped but...
# subset of ld independent markers for eigenstrat and other requirements
vclbase = [plinke,'--noweb']
prunelog = pruneld(plinktasks=plinktasks,cd=outfpath,vclbase = vclbase)
"""This generates the same output files as the first version;
the only difference is that a simple pairwise threshold is used.
The first two parameters (50 and 5) are the same as above (window size and step);
the third parameter represents the r^2 threshold.
Note: this represents the pairwise SNP-SNP metric now, not the
multiple correlation coefficient; also note, this is based on the
genotypic correlation, i.e. it does not involve phasing.
"""
plog += prunelog
flog = '%s.log' % outpath
flogf = open(flog,'w')
flogf.write(''.join(plog))
flogf.write('\n')
flogf.close()
globme = os.path.join(outfpath,'*')
flist = glob.glob(globme)
flist.sort()
for i, data in enumerate( flist ):
outf.write('<li><a href="%s">%s</a></li>\n' % (os.path.split(data)[-1],os.path.split(data)[-1]))
outf.write('</ol></div>\n')
outf.write("</div></body></html>")
outf.close()
def main():
u = """<command interpreter="python">
rgManQQ.py '$input_file' "$name" '$out_html' '$out_html.files_path' '$chrom_col' '$offset_col' '$pval_col'
</command>
"""
npar = 8
if len(sys.argv) < npar:
print >> sys.stdout, '## error - too few command line parameters - wanting %d' % npar
print >> sys.stdout, u
sys.exit(1)
input_fname = sys.argv[1]
title = sys.argv[2]
killme = string.punctuation + string.whitespace
trantab = string.maketrans(killme,'_'*len(killme))
ctitle = title.translate(trantab)
outhtml = sys.argv[3]
outdir = sys.argv[4]
try:
chrom_col = int(sys.argv[5])
except:
chrom_col = -1
try:
offset_col = int(sys.argv[6])
except:
offset_col = -1
p = sys.argv[7].strip().split(',')
try:
q = [int(x) for x in p]
except:
p = -1
if chrom_col == -1 or offset_col == -1: # was passed as zero - do not do manhattan plots
chrom_col = -1
offset_col = -1
grey = 0
if (sys.argv[8].lower() in ['1','true']):
grey = 1
if p == -1:
print >> sys.stderr,'## Cannot run rgManQQ - missing pval column'
sys.exit(1)
p = ['%d' % (int(x) + 1) for x in p]
rlog,flist = doManQQ(input_fname,chrom_col+1,offset_col+1,','.join(p),title,grey,ctitle,outdir)
flist.sort()
html = [galhtmlprefix % progname,]
html.append('<h1>%s</h1>' % title)
if len(flist) > 0:
html.append('<table>\n')
for row in flist:
fname,expl = row # RRun returns pairs of filenames fiddled for the log and R script
n,e = os.path.splitext(fname)
if e in ['.png','.jpg']:
pdf = '%s.pdf' % n
pdff = os.path.join(outdir,pdf)
if os.path.exists(pdff):
rval = compressPDF(inpdf=pdff)
if rval <> 0:
pdf = '%s(not_compressed)' % pdf
else:
pdf = '%s(not_found)' % pdf
s= '<tr><td><a href="%s"><img src="%s" title="%s" hspace="10" width="800"></a></td></tr>' \
% (pdf,fname,expl)
html.append(s)
else:
html.append('<tr><td><a href="%s">%s</a></td></tr>' % (fname,expl))
html.append('</table>\n')
else:
html.append('<h2>### Error - R returned no files - please confirm that parameters are sane</h1>')
html.append('<h3>R log follows below</h3><hr><pre>\n')
html += rlog
html.append('</pre>\n')
html.append(galhtmlattr % (progname,timenow()))
html.append(galhtmlpostfix)
htmlf = file(outhtml,'w')
htmlf.write('\n'.join(html))
htmlf.write('\n')
htmlf.close()
def pruneld(plinktasks=[] ,cd='./',vclbase = []):
"""
plink blathers when doing pruning - ignore
Linkage disequilibrium based SNP pruning
if a million snps in 3 billion base pairs, have mean 3k spacing
assume 40-60k of ld in ceu, a window of 120k width is about 40 snps
so lots more is perhaps less efficient - each window computational cost is
ON^2 unless the code is smart enough to avoid unecessary computation where
allele frequencies make it impossible to see ld > the r^2 cutoff threshold
So, do a window and move forward 20?
from the plink docs at http://pngu.mgh.harvard.edu/~purcell/plink/summary.shtml#prune
Sometimes it is useful to generate a pruned subset of SNPs that are in approximate linkage equilibrium with each other. This can be achieved via two commands: --indep which prunes based on the variance inflation factor (VIF), which recursively removes SNPs within a sliding window; second, --indep-pairwise which is similar, except it is based only on pairwise genotypic correlation.
Hint The output of either of these commands is two lists of SNPs: those that are pruned out and those that are not. A separate command using the --extract or --exclude option is necessary to actually perform the pruning.
The VIF pruning routine is performed:
plink --file data --indep 50 5 2
will create files
plink.prune.in
plink.prune.out
Each is a simlpe list of SNP IDs; both these files can subsequently be specified as the argument for
a --extract or --exclude command.
The parameters for --indep are: window size in SNPs (e.g. 50), the number of SNPs to shift the
window at each step (e.g. 5), the VIF threshold. The VIF is 1/(1-R^2) where R^2 is the multiple correlation coefficient for a SNP being regressed on all other SNPs simultaneously. That is, this considers the correlations between SNPs but also between linear combinations of SNPs. A VIF of 10 is often taken to represent near collinearity problems in standard multiple regression analyses (i.e. implies R^2 of 0.9). A VIF of 1 would imply that the SNP is completely independent of all other SNPs. Practically, values between 1.5 and 2 should probably be used; particularly in small samples, if this threshold is too low and/or the window size is too large, too many SNPs may be removed.
The second procedure is performed:
plink --file data --indep-pairwise 50 5 0.5
This generates the same output files as the first version; the only difference is that a
simple pairwise threshold is used. The first two parameters (50 and 5) are the same as above (window size and step); the third parameter represents the r^2 threshold. Note: this represents the pairwise SNP-SNP metric now, not the multiple correlation coefficient; also note, this is based on the genotypic correlation, i.e. it does not involve phasing.
To give a concrete example: the command above that specifies 50 5 0.5 would a) consider a
window of 50 SNPs, b) calculate LD between each pair of SNPs in the window, b) remove one of a pair of SNPs if the LD is greater than 0.5, c) shift the window 5 SNPs forward and repeat the procedure.
To make a new, pruned file, then use something like (in this example, we also convert the
standard PED fileset to a binary one):
plink --file data --extract plink.prune.in --make-bed --out pruneddata
"""
logres = ['## Rgenetics %s: http://rgenetics.org Galaxy Tools rgLDIndep.py Plink pruneLD runner\n' % myversion,]
for task in plinktasks: # each is a list
fplog,plog = tempfile.mkstemp()
sto = open(plog,'w') # to catch the blather
vcl = vclbase + task
s = '## ldindep now executing %s\n' % ' '.join(vcl)
print s
logres.append(s)
x = subprocess.Popen(' '.join(vcl),shell=True,stdout=sto,stderr=sto,cwd=cd)
retval = x.wait()
sto.close()
sto = open(plog,'r') # read
try:
lplog = sto.readlines()
lplog = [x for x in lplog if x.find('Pruning SNP') == -1]
logres += lplog
logres.append('\n')
except:
logres.append('### %s Strange - no std out from plink when running command line\n%s' % (timenow(),' '.join(vcl)))
sto.close()
os.unlink(plog) # no longer needed
return logres
def main():
u = """<command interpreter="python">
rgManQQ.py '$input_file' "$name" '$out_html' '$out_html.files_path' '$chrom_col' '$offset_col' '$pval_col'
</command>
"""
print >>sys.stdout, "## rgManQQ.py. cl= \n%s" % " ".join(['"%s"' % x for x in sys.argv])
npar = 8
if len(sys.argv) < npar:
print >>sys.stdout, "## error - too few command line parameters - wanting %d" % npar
print >>sys.stdout, u
sys.exit(1)
input_fname = sys.argv[1]
title = sys.argv[2]
killme = string.punctuation + string.whitespace
trantab = string.maketrans(killme, "_" * len(killme))
ctitle = title.translate(trantab)
outhtml = sys.argv[3]
outdir = sys.argv[4]
try:
chrom_col = int(sys.argv[5]) + 1
except:
chrom_col = 0
try:
offset_col = int(sys.argv[6]) + 1
except:
offset_col = 0
p = sys.argv[7].strip().split(",")
try:
p = [int(x) + 1 for x in p]
pval_cols = "c(%s)" % ",".join(map(str, p))
except:
pval_cols = "c(0)"
if chrom_col == 1 or offset_col == 1: # was passed as zero - do not do manhattan plots
chrom_col = 0
offset_col = 0
grey = 0
if sys.argv[8].lower() in ["1", "true"]:
grey = 1
rlog, flist = doManQQ(input_fname, chrom_col, offset_col, pval_cols, title, grey, ctitle, outdir)
flist.sort()
html = [galhtmlprefix % progname]
html.append("<h1>%s</h1>" % title)
if len(flist) > 0:
html.append("<table>\n")
for row in flist:
fname, expl = row # RRun returns pairs of filenames fiddled for the log and R script
e = os.path.splitext(fname)[-1]
if e in [".png", ".jpg"]:
s = (
'<tr><td><a href="%s"><img src="%s" alt="%s hspace="10" width="400"><br>(Click to download image %s)</a></td></tr>'
% (fname, fname, expl, expl)
)
html.append(s)
else:
html.append('<tr><td><a href="%s">%s</a></td></tr>' % (fname, expl))
html.append("</table>\n")
else:
html.append("<h2>### Error - R returned no files - please confirm that parameters are sane</h1>")
html.append("<h3>R log follows below</h3><hr><pre>\n")
html += rlog
html.append("</pre>\n")
html.append(galhtmlattr % (progname, timenow()))
html.append(galhtmlpostfix)
htmlf = file(outhtml, "w")
htmlf.write("\n".join(html))
htmlf.write("\n")
htmlf.close()
logf = sys.argv[4]
logoutdir = sys.argv[5]
gffout = sys.argv[6]
topn = 1000
try:
os.makedirs(logoutdir)
except:
pass
map_file = None
me = sys.argv[0]
amapf = '%s.bim' % bfname # to decode map in xformModel
flog = file(logf, 'w')
logme = []
cdir = os.getcwd()
s = 'Rgenetics %s http://rgenetics.org Galaxy Tools, rgCaCo.py started %s\n' % (
myversion, timenow())
print >> sys.stdout, s # so will appear as blurb for file
logme.append(s)
if verbose:
s = 'rgCaCo.py: bfname=%s, logf=%s, argv = %s\n' % (bfname, logf,
sys.argv)
print >> sys.stdout, s # so will appear as blurb for file
logme.append(s)
twd = tempfile.mkdtemp(
suffix='rgCaCo'
) # make sure plink doesn't spew log file into the root!
tname = os.path.join(twd, name)
vcl = [plinke, '--noweb', '--bfile', bfname, '--out', name, '--model']
p = subprocess.Popen(' '.join(vcl), shell=True, stdout=flog, cwd=twd)
retval = p.wait()
resf = '%s.model' % tname # plink output is here we hope
def doIBS(n=100):
"""parse parameters from galaxy
expect 'input pbed path' 'basename' 'outpath' 'title' 'logpath' 'n'
<command interpreter="python">
rgGRR.py $i.extra_files_path/$i.metadata.base_name "$i.metadata.base_name"
'$out_file1' '$out_file1.files_path' "$title1" '$n' '$Z'
</command>
"""
u = """<command interpreter="python">
rgGRR.py $i.extra_files_path/$i.metadata.base_name "$i.metadata.base_name"
'$out_file1' '$out_file1.files_path' "$title1" '$n' '$Z'
</command>
"""
if len(sys.argv) < 7:
print >> sys.stdout, 'Need pbed inpath, basename, out_htmlname, outpath, title, logpath, nSNP, Zcutoff on command line please'
print >> sys.stdout, u
sys.exit(1)
ts = '%s%s' % (string.punctuation, string.whitespace)
ptran = string.maketrans(ts, '_' * len(ts))
inpath = sys.argv[1]
ldinpath = os.path.split(inpath)[0]
basename = sys.argv[2]
outhtml = sys.argv[3]
newfilepath = sys.argv[4]
title = sys.argv[5].translate(ptran)
logfname = 'Log_%s.txt' % title
logpath = os.path.join(
newfilepath,
logfname) # log was a child - make part of html extra_files_path zoo
n = int(sys.argv[6])
try:
Zcutoff = float(sys.argv[7])
except:
Zcutoff = 2.0
try:
os.makedirs(newfilepath)
except:
pass
logf = file(logpath, 'w')
efp, ibase_name = os.path.split(
inpath) # need to use these for outputs in files_path
ped = plinkbinJZ.BPed(inpath)
ped.parse(quick=True)
if ped == None:
print >> sys.stderr, '## doIBSpy problem - cannot open %s or %s - cannot run' % (
ldreduced, basename)
sys.exit(1)
newfiles, explanations, repOut = doIBSpy(ped=ped,
basename=basename,
outdir=newfilepath,
logf=logf,
nrsSamples=n,
title=title,
pdftoo=0,
Zcutoff=Zcutoff)
logf.close()
logfs = file(logpath, 'r').readlines()
lf = file(outhtml, 'w')
lf.write(galhtmlprefix % PROGNAME)
# this is a mess. todo clean up - should each datatype have it's own directory? Yes
# probably. Then titles are universal - but userId libraries are separate.
s = '<div>Output from %s run at %s<br>\n' % (PROGNAME, timenow())
lf.write('<h4>%s</h4>\n' % s)
fixed = ["'%s'" % x for x in sys.argv] # add quotes just in case
s = 'If you need to rerun this analysis, the command line was\n<pre>%s</pre>\n</div>' % (
' '.join(fixed))
lf.write(s)
# various ways of displaying svg - experiments related to missing svg mimetype on test (!)
#s = """<object data="%s" type="image/svg+xml" width="%d" height="%d">
# <embed src="%s" type="image/svg+xml" width="%d" height="%d" />
# </object>""" % (newfiles[0],PLOT_WIDTH,PLOT_HEIGHT,newfiles[0],PLOT_WIDTH,PLOT_HEIGHT)
s = """ <embed src="%s" type="image/svg+xml" width="%d" height="%d" />""" % (
newfiles[0], PLOT_WIDTH, PLOT_HEIGHT)
#s = """ <iframe src="%s" type="image/svg+xml" width="%d" height="%d" />""" % (newfiles[0],PLOT_WIDTH,PLOT_HEIGHT)
lf.write(s)
lf.write(
'<div><h4>Click the links below to save output files and plots</h4><br><ol>\n'
)
for i in range(len(newfiles)):
if i == 0:
lf.write('<li><a href="%s" type="image/svg+xml" >%s</a></li>\n' %
(newfiles[i], explanations[i]))
else:
lf.write('<li><a href="%s">%s</a></li>\n' %
(newfiles[i], explanations[i]))
flist = os.listdir(newfilepath)
for fname in flist:
if not fname in newfiles:
lf.write('<li><a href="%s">%s</a></li>\n' % (fname, fname))
lf.write('</ol></div>')
lf.write('<div>%s</div>' %
('\n'.join(repOut))) # repOut is a list of tables
lf.write(
'<div><hr><h3>Log from this job (also stored in %s)</h3><pre>%s</pre><hr></div>'
% (logfname, ''.join(logfs)))
lf.write('</body></html>\n')
lf.close()
logf.close()
def doIBS(n=100):
"""parse parameters from galaxy
expect 'input pbed path' 'basename' 'outpath' 'title' 'logpath' 'n'
<command interpreter="python">
rgGRR.py $i.extra_files_path/$i.metadata.base_name "$i.metadata.base_name"
'$out_file1' '$out_file1.files_path' "$title1" '$n' '$Z'
</command>
"""
u="""<command interpreter="python">
rgGRR.py $i.extra_files_path/$i.metadata.base_name "$i.metadata.base_name"
'$out_file1' '$out_file1.files_path' "$title1" '$n' '$Z'
</command>
"""
if len(sys.argv) < 7:
print >> sys.stdout, 'Need pbed inpath, basename, out_htmlname, outpath, title, logpath, nSNP, Zcutoff on command line please'
print >> sys.stdout, u
sys.exit(1)
ts = '%s%s' % (string.punctuation,string.whitespace)
ptran = string.maketrans(ts,'_'*len(ts))
inpath = sys.argv[1]
ldinpath = os.path.split(inpath)[0]
basename = sys.argv[2]
outhtml = sys.argv[3]
newfilepath = sys.argv[4]
title = sys.argv[5].translate(ptran)
logfname = 'Log_%s.txt' % title
logpath = os.path.join(newfilepath,logfname) # log was a child - make part of html extra_files_path zoo
n = int(sys.argv[6])
try:
Zcutoff = float(sys.argv[7])
except:
Zcutoff = 2.0
try:
os.makedirs(newfilepath)
except:
pass
logf = file(logpath,'w')
efp,ibase_name = os.path.split(inpath) # need to use these for outputs in files_path
ped = plinkbinJZ.BPed(inpath)
ped.parse(quick=True)
if ped == None:
print >> sys.stderr, '## doIBSpy problem - cannot open %s or %s - cannot run' % (ldreduced,basename)
sys.exit(1)
newfiles,explanations,repOut = doIBSpy(ped=ped,basename=basename,outdir=newfilepath,
logf=logf,nrsSamples=n,title=title,pdftoo=0,Zcutoff=Zcutoff)
logf.close()
logfs = file(logpath,'r').readlines()
lf = file(outhtml,'w')
lf.write(galhtmlprefix % PROGNAME)
# this is a mess. todo clean up - should each datatype have it's own directory? Yes
# probably. Then titles are universal - but userId libraries are separate.
s = '<div>Output from %s run at %s<br>\n' % (PROGNAME,timenow())
lf.write('<h4>%s</h4>\n' % s)
fixed = ["'%s'" % x for x in sys.argv] # add quotes just in case
s = 'If you need to rerun this analysis, the command line was\n<pre>%s</pre>\n</div>' % (' '.join(fixed))
lf.write(s)
# various ways of displaying svg - experiments related to missing svg mimetype on test (!)
#s = """<object data="%s" type="image/svg+xml" width="%d" height="%d">
# <embed src="%s" type="image/svg+xml" width="%d" height="%d" />
# </object>""" % (newfiles[0],PLOT_WIDTH,PLOT_HEIGHT,newfiles[0],PLOT_WIDTH,PLOT_HEIGHT)
s = """ <embed src="%s" type="image/svg+xml" width="%d" height="%d" />""" % (newfiles[0],PLOT_WIDTH,PLOT_HEIGHT)
#s = """ <iframe src="%s" type="image/svg+xml" width="%d" height="%d" />""" % (newfiles[0],PLOT_WIDTH,PLOT_HEIGHT)
lf.write(s)
lf.write('<div><h4>Click the links below to save output files and plots</h4><br><ol>\n')
for i in range(len(newfiles)):
if i == 0:
lf.write('<li><a href="%s" type="image/svg+xml" >%s</a></li>\n' % (newfiles[i],explanations[i]))
else:
lf.write('<li><a href="%s">%s</a></li>\n' % (newfiles[i],explanations[i]))
flist = os.listdir(newfilepath)
for fname in flist:
if not fname in newfiles:
lf.write('<li><a href="%s">%s</a></li>\n' % (fname,fname))
lf.write('</ol></div>')
lf.write('<div>%s</div>' % ('\n'.join(repOut))) # repOut is a list of tables
lf.write('<div><hr><h3>Log from this job (also stored in %s)</h3><pre>%s</pre><hr></div>' % (logfname,''.join(logfs)))
lf.write('</body></html>\n')
lf.close()
logf.close()
alogf = options.logf # absolute paths
od = os.path.split(alogf)[0]
try:
os.path.makedirs(od)
except:
pass
aoutf = options.outfname # absolute paths
od = os.path.split(aoutf)[0]
try:
os.path.makedirs(od)
except:
pass
vcl = [plinke,'--noweb', '--bfile',options.bfname,'--out',title,'--mind','0.5','--tdt']
logme = []
if verbose:
s = 'Rgenetics %s http://rgenetics.org Galaxy Tools rgTDT.py started %s\n' % (myversion,timenow())
print >> sys.stdout,s
logme.append(s)
s ='rgTDT.py: bfname=%s, logf=%s, argv = %s\n' % (options.bfname,alogf, sys.argv)
print >> sys.stdout,s
logme.append(s)
s = 'rgTDT.py: vcl=%s\n' % (' '.join(vcl))
print >> sys.stdout,s
logme.append(s)
twd = tempfile.mkdtemp(suffix='rgTDT') # make sure plink doesn't spew log file into the root!
tname = os.path.join(twd,title)
p=subprocess.Popen(' '.join(vcl),shell=True,cwd=twd)
retval = p.wait()
shutil.copy('%s.log' % tname,alogf)
sto = file(alogf,'a')
sto.write('\n'.join(logme))
def main():
u = """<command interpreter="python">
rgManQQ.py '$input_file' "$name" '$out_html' '$out_html.files_path' '$chrom_col' '$offset_col' '$pval_col'
</command>
"""
npar = 8
if len(sys.argv) < npar:
print >> sys.stdout, '## error - too few command line parameters - wanting %d' % npar
print >> sys.stdout, u
sys.exit(1)
input_fname = sys.argv[1]
title = sys.argv[2]
killme = string.punctuation + string.whitespace
trantab = string.maketrans(killme, '_' * len(killme))
ctitle = title.translate(trantab)
outhtml = sys.argv[3]
outdir = sys.argv[4]
try:
chrom_col = int(sys.argv[5])
except:
chrom_col = -1
try:
offset_col = int(sys.argv[6])
except:
offset_col = -1
p = sys.argv[7].strip().split(',')
try:
q = [int(x) for x in p]
except:
p = -1
if chrom_col == -1 or offset_col == -1: # was passed as zero - do not do manhattan plots
chrom_col = -1
offset_col = -1
grey = 0
if (sys.argv[8].lower() in ['1', 'true']):
grey = 1
if p == -1:
print >> sys.stderr, '## Cannot run rgManQQ - missing pval column'
sys.exit(1)
p = ['%d' % (int(x) + 1) for x in p]
rlog, flist = doManQQ(input_fname, chrom_col + 1, offset_col + 1,
','.join(p), title, grey, ctitle, outdir)
flist.sort()
html = [
galhtmlprefix % progname,
]
html.append('<h1>%s</h1>' % title)
if len(flist) > 0:
html.append('<table>\n')
for row in flist:
fname, expl = row # RRun returns pairs of filenames fiddled for the log and R script
n, e = os.path.splitext(fname)
if e in ['.png', '.jpg']:
pdf = '%s.pdf' % n
pdff = os.path.join(outdir, pdf)
if os.path.exists(pdff):
rval = compressPDF(inpdf=pdff)
if rval <> 0:
pdf = '%s(not_compressed)' % pdf
else:
pdf = '%s(not_found)' % pdf
s= '<tr><td><a href="%s"><img src="%s" title="%s" hspace="10" width="800"></a></td></tr>' \
% (pdf,fname,expl)
html.append(s)
else:
html.append('<tr><td><a href="%s">%s</a></td></tr>' %
(fname, expl))
html.append('</table>\n')
else:
html.append(
'<h2>### Error - R returned no files - please confirm that parameters are sane</h1>'
)
html.append('<h3>R log follows below</h3><hr><pre>\n')
html += rlog
html.append('</pre>\n')
html.append(galhtmlattr % (progname, timenow()))
html.append(galhtmlpostfix)
htmlf = file(outhtml, 'w')
htmlf.write('\n'.join(html))
htmlf.write('\n')
htmlf.close()
def runEigen():
""" run the smartpca prog - documentation follows
smartpca.perl -i fakeped_100.eigenstratgeno -a fakeped_100.map -b fakeped_100.ind -p fakeped_100 -e fakeped_100.eigenvals -l
fakeped_100.eigenlog -o fakeped_100.eigenout
DOCUMENTATION OF smartpca.perl program:
This program calls the smartpca program (see ../POPGEN/README).
For this to work, the bin directory containing smartpca MUST be in your path.
See ./example.perl for a toy example.
../bin/smartpca.perl
-i example.geno : genotype file in EIGENSTRAT format (see ../CONVERTF/README)
-a example.snp : snp file (see ../CONVERTF/README)
-b example.ind : indiv file (see ../CONVERTF/README)
-k k : (Default is 10) number of principal components to output
-o example.pca : output file of principal components. Individuals removed
as outliers will have all values set to 0.0 in this file.
-p example.plot : prefix of output plot files of top 2 principal components.
(labeling individuals according to labels in indiv file)
-e example.eval : output file of all eigenvalues
-l example.log : output logfile
-m maxiter : (Default is 5) maximum number of outlier removal iterations.
To turn off outlier removal, set -m 0.
-t topk : (Default is 10) number of principal components along which
to remove outliers during each outlier removal iteration.
-s sigma : (Default is 6.0) number of standard deviations which an
individual must exceed, along one of topk top principal
components, in order to be removed as an outlier.
now uses https://www.bx.psu.edu/cgi-bin/trac.cgi/galaxy/changeset/1832
All files can be viewed however, by making links in the primary (HTML) history item like:
<img src="display_child?parent_id=2&designation=SomeImage?" alt="Some Image"/>
<a href="display_child?parent_id=2&designation=SomeText?">Some Text</a>
<command interpreter="python">
rgEigPCA.py "$i.extra_files_path/$i.metadata.base_name" "$title" "$out_file1"
"$out_file1.files_path" "$k" "$m" "$t" "$s" "$pca"
</command>
"""
if len(sys.argv) < 9:
print 'Need an input genotype file root, a title, a temp id and the temp file path for outputs,'
print ' and the 4 integer tuning parameters k,m,t and s in order. Given that, will run smartpca for eigensoft'
sys.exit(1)
else:
print >> sys.stdout, 'rgEigPCA.py got %s' % (' '.join(sys.argv))
skillme = ' %s' % string.punctuation
trantab = string.maketrans(skillme,'_'*len(skillme))
ofname = sys.argv[5]
progname = os.path.basename(sys.argv[0])
infile = sys.argv[1]
infpath,base_name = os.path.split(infile) # now takes precomputed or autoconverted ldreduced dataset
title = sys.argv[2].translate(trantab) # must replace all of these for urls containing title
outfile1 = sys.argv[3]
newfilepath = sys.argv[4]
try:
os.mkdirs(newfilepath)
except:
pass
op = os.path.split(outfile1)[0]
try: # for test - needs this done
os.makedirs(op)
except:
pass
eigen_k = sys.argv[5]
eigen_m = sys.argv[6]
eigen_t = sys.argv[7]
eigen_s = sys.argv[8]
eigpca = sys.argv[9] # path to new dataset for pca results - for later adjustment
eigentitle = os.path.join(newfilepath,title)
explanations=['Samples plotted in first 2 eigenvector space','Principle components','Eigenvalues',
'Smartpca log (contents shown below)']
rplotname = 'PCAPlot.pdf'
eigenexts = [rplotname, "pca.xls", "eval.xls"]
newfiles = ['%s_%s' % (title,x) for x in eigenexts] # produced by eigenstrat
rplotout = os.path.join(newfilepath,newfiles[0]) # for R plots
eigenouts = [x for x in newfiles]
eigenlogf = '%s_log.txt' % title
newfiles.append(eigenlogf) # so it will also appear in the links
lfname = outfile1
lf = file(lfname,'w')
lf.write(galhtmlprefix % progname)
try:
os.makedirs(newfilepath)
except:
pass
smartCL = '%s -i %s.bed -a %s.bim -b %s.fam -o %s -p %s -e %s -l %s -k %s -m %s -t %s -s %s' % \
(smartpca,infile, infile, infile, eigenouts[1],'%s_eigensoftplot.pdf' % title,eigenouts[2],eigenlogf, \
eigen_k, eigen_m, eigen_t, eigen_s)
env = os.environ
p=subprocess.Popen(smartCL,shell=True,cwd=newfilepath)
retval = p.wait()
# copy the eigenvector output file needed for adjustment to the user's eigenstrat library directory
elog = file(os.path.join(newfilepath,eigenlogf),'r').read()
eeigen = os.path.join(newfilepath,'%s.evec' % eigenouts[1]) # need these for adjusting
try:
eigpcaRes = file(eeigen,'r').read()
except:
eigpcaRes = ''
file(eigpca,'w').write(eigpcaRes)
makePlot(eigpca=eigpca,pdfname=newfiles[0],title=title,nfp=newfilepath,rexe=rexe)
s = 'Output from %s run at %s<br/>\n' % (progname,timenow())
lf.write('<h4>%s</h4>\n' % s)
lf.write('newfilepath=%s, rexe=%s' % (newfilepath,rexe))
lf.write('(click on the image below to see a much higher quality PDF version)')
thumbnail = '%s.png' % newfiles[0] # foo.pdf.png - who cares?
if os.path.exists(os.path.join(newfilepath,thumbnail)):
lf.write('<table border="0" cellpadding="10" cellspacing="10"><tr><td>\n')
lf.write('<a href="%s"><img src="%s" alt="%s" hspace="10" align="left" /></a></td></tr></table><br/>\n' \
% (newfiles[0],thumbnail,explanations[0]))
allfiles = os.listdir(newfilepath)
allfiles.sort()
sizes = [getfSize(x,newfilepath) for x in allfiles]
lallfiles = ['<li><a href="%s">%s %s</a></li>\n' % (x,x,sizes[i]) for i,x in enumerate(allfiles)] # html list
lf.write('<div class="document">All Files:<ol>%s</ol></div>' % ''.join(lallfiles))
lf.write('<div class="document">Log %s contents follow below<p/>' % eigenlogf)
lf.write('<pre>%s</pre></div>' % elog) # the eigenlog
s = 'If you need to rerun this analysis, the command line used was\n%s\n<p/>' % (smartCL)
lf.write(s)
lf.write(galhtmlpostfix) # end galhtmlprefix div
lf.close()
