def job__saveFig(figs):
dfig = pyutil.saveFigDict(figs, DIR='.', exts=exts, dpi=dpi)
dfig['fignames'] = [x for x in dfig['fignames'] if x.endswith('.png')]
buf = [pyutil.ppJson(dfig)]
ofname = 'figures.json'
pyutil.printlines(buf, ofname)
return dfig
def main(f, dbg=0, reCallPeak=0, gPar=None):
global shellexec
def shellexec(cmd, dbg=0):
if dbg:
print cmd
res = 'dbg'
else:
res = subprocess.check_output(cmd, shell=1)
return res
# #############################################################################################
# DEPENDENT_FILES_PATH = '/media/pw_synology3/Software/chip-summary/' # [path of chip-summary.py]
# DEFAULT_TARGET_RANGE = '3000' # [change] a string, not a number
# SUMMARY_FILE_NAME = 'summary.html'
# SUMMARY_DIR = 'summary'
# PEAK_CALL_PIPELINE_TEMPLATE = os.path.join(DEPENDENT_FILES_PATH, 'depend/script/pipeline724-t.sh')
# PEAK_SELECT_SCRIPT = os.path.join(DEPENDENT_FILES_PATH, 'depend/script/select_peaks.py')
# GENELOCUS_TO_GENENAME_SCRIPT= os.path.join(DEPENDENT_FILES_PATH, 'depend/script/genelocus2genename.py')
# #### Slowest part to be refactored???
# EXTRACT_AGI_CODE_AND_FC = os.path.join(DEPENDENT_FILES_PATH, 'depend/script/extract_AGI_code_and_fold_change.py')
# GO_ENRICHMENT_SCRIPT = os.path.join(DEPENDENT_FILES_PATH, 'depend/script/fe.sh') # install goatools (GO enrichment) and edit fe.sh
# GO_ENRICHMENT_DIFF_SCRIPT = os.path.join(DEPENDENT_FILES_PATH, 'depend/script/goterm-matrix.py')
# AGI_TO_GENE_NAMES = os.path.join(DEPENDENT_FILES_PATH, 'depend/data/AGI-to-gene-names.txt')
# ANNOTATION_FILE = os.path.join(DEPENDENT_FILES_PATH, 'depend/data/genesTAIR10.bed') # for bedmap
# GENE_DESCRIPTION = os.path.join(DEPENDENT_FILES_PATH, 'depend/data/gene_description_20140101.txt')
# MAX_FOLD_CHANGE = 10 # for number of peaks versus fold-change plot
# #############################################################################################
gPar = gPar or get_global_parameters(f)
condDict = get_conditions(f, gPar)
DIR = pyutil.dict2flat(gPar)
# os.system('mkdir -p ' + DIR); os.chdir(DIR)
if dbg == 1:
d = gPar, condDict
for dd in d:
print pyutil.ppJson(dd)
return d
# try:
if 1:
# Collect results
os.system('mkdir -p %s' % SUMMARY_DIR)
# make pipeline files for peak calling
def getPeak(k):
sname = make_peak_call_script(k, condDict,
PEAK_CALL_PIPELINE_TEMPLATE)
print('Run %s ...' % (sname))
res = subprocess.call(['bash', sname])
# return '%s_peaks.narrowPeak'%k
return res
if reCallPeak:
# check that every ChIP file is present
for k in condDict.keys():
chip_file = condDict[k]['CHIP']
input_file = condDict[k]['INPUT']
if not os.path.exists(chip_file):
print('%s dose not exist. STOP' % (chip_file))
sys.exit()
if not os.path.exists(input_file):
print('%s dose not exist. STOP' % (input_file))
sys.exit()
[getPeak(k) for k in condDict.keys()]
npkFS = ['%s_peaks.narrowPeak' % k for k in condDict.keys()]
peakSummary(npkFS)
gene_lists = {
} # a dictionary of form d = {'condition1': {'AT1G12345':'2.3', 'AT1G12346':'1.2'} }
def peakSummary(npkFS,
gPar=None,
dbg=0,
FC=1.5,
PVALUE=0.01,
QVALUE=0.0005,
maxDist=1500,
DIR='test',
ref=None,
**kwargs):
gPar = gPar or {
"FC": FC,
"PVALUE": PVALUE,
"QVALUE": QVALUE,
"PAIRWISE_COMPARE": "Y",
"TARGET_RANGE": maxDist,
"TITLE": "testRun"
}
os.system('mkdir -p %s' % DIR)
os.chdir(DIR)
cmd = '''
mkdir -p summary;
mkdir -p summary/npeaks_vs_fc_npk;
mkdir -p summary/npk;
cp -r {infiles} -t .
'''.format(infiles=' '.join(npkFS))
os.system(cmd)
# f = functools.partial(process,gPar = gPar)
f = lambda x: process(npkFile=x, gPar=gPar, dbg=dbg, ANNOTATION_FILE=ref)
condRes = res = map(f, npkFS)
if dbg:
with open('condRes.dbg', 'w') as f:
print >> f, pyutil.ppJson(condRes)
if dbg == 2:
return condRes
dfs = [pd.read_table(x['file_bedmap']).set_index('hit') for x in res]
# for df in dfs:
# print df.head(10)
# print [type(df) for df in dfs]
indAll = pd.concat(dfs, axis=1, join='outer').index
print '[db1]', dfs[0].head()
df = pd.concat([df.reindex(indAll) for df in dfs], axis=0)
df = df.reset_index()
# df..reset_index()
# df = df.set_index('hit')
print '[db2]', df.head()
cols = df.columns.to_series()
cols[0] = 'index'
df.columns = cols
print '[db3]', df.head()
df_fc = df.pivot_table(columns='condition', values='FC',
index='index').fillna(0)
sanitise = lambda x: x.split('.', 1)[0]
df_fc.index = map(sanitise, df_fc.index)
# index = scount.vstack([dfs],as_index=1,how = 'outer')
getPM = lambda lst: ''.join(['+' if x != 0 else '-' for x in lst])
vals = df_fc.apply(getPM, axis=1)
df_fc.insert(0, 'pmSummary', vals)
print df_fc.head(10)
df_fc.to_csv('FoldChange_table.csv')
##### write html summary report
print('... make html page %s' % (SUMMARY_FILE_NAME))
f = open(SUMMARY_FILE_NAME, 'w')
TITLE = 'test'
# TITLE = gPar['TITLE']
f.write('<html>')
f.write('<head>')
f.write('<title>%s</title>' % (TITLE))
f.write(
'<style> body {font-family:\"HelveticaNeue-Light\", \"Helvetica Neue Light\", \"Helvetica neue\"} </style>'
)
f.write('</head>')
f.write('<body>')
f.write('<h2>%s</h2>' % (TITLE))
#####################################################################
f.write(
'<h3>Target genes and (Not implemented "associated GO terms")</h3>')
f.write('<p><a href=\"{0}\">[{0}]</a></p>'.format('FoldChange_table.csv'))
table_string = '<table><tr><td>Sample</td><td>Target gene list</td><td>#target genes</td><td>GO enrichment</td><td>Peak selection thresholds</td><td>#peaks plot</td></tr>'
rowFmt = '''
<tr><td>{key}</td>
<td><a href="{glst_filename}">target genes</a></td>
<td align=right>{nGene:d}</td>
<td><a href="{goenrich_filename}">enrichment</a></td>
<td><a href="{peak_file}">{param}</a></td>
<td><a href="{plot_file}">plot</a></td></tr>
'''
for d in res:
table_string += rowFmt.format(**d)
table_string += '</table>'
f.write(table_string)
# #####################################################################
# f.write('<h3>Enriched GO terms associated to target genes in different conditions</h3>')
# f.write('<p>Most shared GO terms across conditions are on the top in the following table.</p>')
# filename = make_goenrichment_diff([d['goenrich_filename'] for d in res],
# SUMMARY_DIR)
# f.write('<a href=\"%s\">Each row is a GO term. Each column is a condition.</a>' % (filename))
# #####################################################################
# # if gPar['PAIRWISE_COMPARE'].lower().startswith('y'):
# # f.write('<h3>Pairwise comparison between conditions</h3>')
# # f.write('<p>Each cell in the following table contains three numbers, X, Y and Z. X is the number of target genes that are in condition A but not in condition B. Z is the number of target genes that are in condition B but not in condition A. Y is the number of target genes that are in both conditions.</p>')
# # make_comparison_table(f, gene_lists, agi2genename_dict, SUMMARY_DIR)
# #####################################################################
# f.write('<h3>Binding to target genes in different conditions</h3>')
# f.write('<p><b>Note:</b> In the following, \'+\' means binding near a target gene in a particular experimental condition, and \'-\' means non-binding.</p>')
# f.write('<p>The columns are:<br/><br/>')
# colName = ['AGI_locus_name'] + [d['key'] for d in res] + ['gene_name (if available)']
# f.write( '<br/>'.join(colName))
# f.write('</p>')
f.write('</body>')
f.write('</html>')
f.close()
# clean up
print('Done.')
default=pyutil.os.environ.get('GTF', 'none') + '.cds')
parser.add_argument('-c', '--cdsFile', default=None)
parser.add_argument('-g',
'--GSIZE',
default=pyutil.os.environ.get('GSIZE', None))
parser.add_argument('-o', '--DIR', default=None)
parser.add_argument('-j',
'--NCORE',
default=pyutil.os.environ.get(4, None),
type=int)
parser.add_argument('-s', '--center_summit', default=0, type=int)
parser.add_argument('-d', '--debug', default=0, type=int)
parser.add_argument('-f', '--figsize', default=[14, 14], type=int, nargs=2)
# parser.add_argument('-y','--ylim',
# default=[0., 10.], type=float,nargs=2)
parser.add_argument('-y', '--ylim', default=None, type=float, nargs=2)
defaults = {act.dest: act.default for act in parser._actions}
for key in ['bedFile', 'bwFiles']:
defaults.pop(key)
main = pyutil.functools.partial(main, **defaults)
# argparser
if __name__ == '__main__':
args = parser.parse_args()
pars = vars(args)
assert pars['bedFile'] is not None
print(pyutil.ppJson(pars))
main(**pars)
stderrLine('[Done]')