zhangyiss/spack
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

New package - REDItools (#17703)

Browse Source 
* New package - REDItools

This PR adds the REDItools package, along with a new package dependency,
py-fisher. This contains a patch generated from the python 2to3 script
as well as some other fixes. I am not sure if the project is ready to
support python-3 yet but I submitted the other patches upstream.

* Update var/spack/repos/builtin/packages/reditools/package.py

Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>

Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
This commit is contained in:
Glenn Johnson 2020-08-07 14:40:52 -05:00 committed by GitHub
parent 11f2d01051
commit 1a11449c86
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 1042 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
var/spack/repos/builtin/packages/py-fisher/package.py Normal file
View File

@ -0,0 +1,21 @@
# Copyright 2013-2020 Lawrence Livermore National Security, LLC and other
# Spack Project Developers. See the top-level COPYRIGHT file for details.
#
# SPDX-License-Identifier: (Apache-2.0 OR MIT)
from spack import *
class PyFisher(PythonPackage):
"""Fisher's Exact Test.
Simple, fast implementation of Fisher's exact test."""
homepage = "https://github.com/brentp/fishers_exact_test"
url = "https://pypi.io/packages/source/f/fisher/fisher-0.1.9.tar.gz"
version('0.1.9', sha256='d378b3f7e488e2a679c6d0e5ea1bce17bc931c2bfe8ec8424ee47a74f251968d')
depends_on('py-setuptools', type='build')
depends_on('py-numpy', type=('build', 'run'))
depends_on('py-pytest', type='test')

11
var/spack/repos/builtin/packages/reditools/REDItoolDenovo.py.patch Normal file
View File

@ -0,0 +1,11 @@
--- a/main/REDItoolDenovo.py 2020-07-16 17:35:46.008030346 -0500
+++ b/main/REDItoolDenovo.py 2020-07-16 17:38:39.700035490 -0500
@@ -768,7 +768,7 @@
for j in ridxinfo.split('\n'): #MOD
l=(j.strip()).split('\t')
if l[0] in ['*', '']: continue #MOD
- if int(l[2])+int(l[3]) > 0: rrefs[l[0]]=int(l[1])
+ if int(l[2])+int(l[3]) > 0: rrefs[l[0]]=int(l[1])
frefs=[]
fidxinfo=open(fastafile+'.fai')
for j in fidxinfo:

41
var/spack/repos/builtin/packages/reditools/interpreter.patch Normal file
View File

@ -0,0 +1,41 @@
diff -ru a/accessory/get_DE_events.py b/accessory/get_DE_events.py
--- a/accessory/get_DE_events.py 2020-07-16 17:18:47.012982992 -0500
+++ b/accessory/get_DE_events.py 2020-07-16 17:19:47.531986703 -0500
@@ -1,3 +1,4 @@
+#!/usr/bin/env python
#################################### REDI OUT TABLE ########################################################
#Region Position Reference Strand Coverage-q30 MeanQ BaseCount[A,C,G,T] #
#AllSubs Frequency gCoverage-q30 gMeanQ gBaseCount[A,C,G,T] gAllSubs gFrequency #
diff -ru a/accessory/readPsl.py b/accessory/readPsl.py
--- a/accessory/readPsl.py 2020-07-16 17:18:47.012982992 -0500
+++ b/accessory/readPsl.py 2020-07-16 17:20:02.829987622 -0500
@@ -1,4 +1,4 @@
-
+#!/usr/bin/env python
import sys, os
import math
diff -ru a/accessory/subCount2.py b/accessory/subCount2.py
--- a/accessory/subCount2.py 2020-07-16 17:18:47.012982992 -0500
+++ b/accessory/subCount2.py 2020-07-16 17:20:22.650988801 -0500
@@ -1,3 +1,4 @@
+#!/usr/bin/env python
import sys
try:
diff -ru a/accessory/subCount.py b/accessory/subCount.py
--- a/accessory/subCount.py 2020-07-16 17:18:47.012982992 -0500
+++ b/accessory/subCount.py 2020-07-16 17:20:35.502989558 -0500
@@ -1,3 +1,4 @@
+#!/usr/bin/env python
import sys
try:
diff -ru a/main/REDItoolDenovo.py b/main/REDItoolDenovo.py
--- a/main/REDItoolDenovo.py 2020-07-16 17:18:47.012982992 -0500
+++ b/main/REDItoolDenovo.py 2020-07-16 17:21:01.018991045 -0500
@@ -1,3 +1,4 @@
+#!/usr/bin/env python
# coding=utf-8
# Copyright (c) 2013-2014 Ernesto Picardi <ernesto.picardi@uniba.it>
#

32
var/spack/repos/builtin/packages/reditools/package.py Normal file
View File

@ -0,0 +1,32 @@
# Copyright 2013-2020 Lawrence Livermore National Security, LLC and other
# Spack Project Developers. See the top-level COPYRIGHT file for details.
#
# SPDX-License-Identifier: (Apache-2.0 OR MIT)
from spack import *
class Reditools(PythonPackage):
"""REDItools: python scripts for RNA editing detection by RNA-Seq data.
REDItools are simple python scripts conceived to facilitate the
investigation of RNA editing at large-scale and devoted to research groups
that would to explore such phenomenon in own data but don't have sufficient
bioinformatics skills. They work on main operating systems (although
unix/linux-based OS are preferred), can handle reads from whatever platform
in the standard BAM format and implement a variety of filters."""
homepage = "https://github.com/BioinfoUNIBA/REDItools"
git = "https://github.com/BioinfoUNIBA/REDItools.git"
version('1.3_2020-03-20', commit='cf47f3d54f324aeb9650bcf8bfacf5a967762a55')
depends_on('py-pysam', type=('build', 'run'))
depends_on('py-fisher', type=('build', 'run'))
depends_on('blat', type='run')
depends_on('tabix', type='run')
patch('REDItoolDenovo.py.patch')
patch('interpreter.patch')
patch('setup.py.patch')
patch('python2to3.patch', when='^python@3:')

926
var/spack/repos/builtin/packages/reditools/python2to3.patch Normal file
View File

@ -0,0 +1,926 @@
diff -ru a/accessory/AnnotateTable.py b/accessory/AnnotateTable.py
--- a/accessory/AnnotateTable.py 2020-07-16 16:16:59.360014702 -0500
+++ b/accessory/AnnotateTable.py 2020-07-16 16:17:22.159013630 -0500
@@ -28,7 +28,7 @@
sys.stderr.write('Pysam version used: %s\n' %(pysamVersion))
def usage():
- print """
+ print("""
USAGE: python AnnotateTable.py [options]
Options:
-a Sorted Annotation file
@@ -44,12 +44,12 @@
-C Columns with base distribution [7,12] (in combination with -S)
-o Save lines to a file
-h Print this help
-"""
+""")
try:
opts, args = getopt.getopt(sys.argv[1:], 'i:a:o:hs:c:n:SC:uk:r:',["help"])
-except getopt.GetoptError, err:
- print str(err)
+except getopt.GetoptError as err:
+ print(str(err))
usage()
sys.exit()
@@ -101,7 +101,7 @@
a={'A':'T','T':'A','C':'G','G':'C'}
ss=''
for i in s.upper():
- if a.has_key(i): ss+=a[i]
+ if i in a: ss+=a[i]
elif i==' ': ss+=' '
elif i=='-': ss+='-'
else: ss+='N'
@@ -125,23 +125,23 @@
anns='+'
for i in res:
if i[3]=='+':
- if d['+'].has_key(i[1]):
+ if i[1] in d['+']:
if i[0] not in d['+'][i[1]][0]: d['+'][i[1]][0]=d['+'][i[1]][0]+','+i[0]
if i[2]+'-'+i[0] not in d['+'][i[1]][1]: d['+'][i[1]][1]=d['+'][i[1]][1]+','+i[2]+'-'+i[0]
else:
d['+'][i[1]]=[i[0],i[2]+'-'+i[0]]
elif i[3]=='-':
- if d['-'].has_key(i[1]):
+ if i[1] in d['-']:
if i[0] not in d['-'][i[1]][0]: d['-'][i[1]][0]=d['-'][i[1]][0]+','+i[0]
if i[2]+'-'+i[0] not in d['-'][i[1]][1]: d['-'][i[1]][1]=d['-'][i[1]][1]+','+i[2]+'-'+i[0]
else:
d['-'][i[1]]=[i[0],i[2]+'-'+i[0]]
- gip='$'.join(d['+'].keys())
- featp='$'.join([d['+'][x][0] for x in d['+'].keys()])
- tip='$'.join([d['+'][x][1] for x in d['+'].keys()])
- gim='$'.join(d['-'].keys())
- featm='$'.join([d['-'][x][0] for x in d['-'].keys()])
- tim='$'.join([d['-'][x][1] for x in d['-'].keys()])
+ gip='$'.join(list(d['+'].keys()))
+ featp='$'.join([d['+'][x][0] for x in list(d['+'].keys())])
+ tip='$'.join([d['+'][x][1] for x in list(d['+'].keys())])
+ gim='$'.join(list(d['-'].keys()))
+ featm='$'.join([d['-'][x][0] for x in list(d['-'].keys())])
+ tim='$'.join([d['-'][x][1] for x in list(d['-'].keys())])
p=[featp,gip,tip]
m=[featm,gim,tim]
pm=[(featp+'&'+featm).strip('&'),(gip+'&'+gim).strip('&'),(tip+'&'+tim).strip('&')]
@@ -187,7 +187,7 @@
elif strand=='-': res=ann[1]
else: res=ann[2]
for i in addc:
- print prinfo[i]+ res[i]
+ print(prinfo[i]+ res[i])
except: sys.exit('Error: not correct position.')
if af:
@@ -200,7 +200,7 @@
h=[i.strip()]
for k in addc: h.append(hinfo[k])
if save: o.write('\t'.join(h)+'\n')
- else: print '\t'.join(h)
+ else: print('\t'.join(h))
continue
if i.startswith(skip): continue
l=(i.strip()).split('\t')
@@ -230,7 +230,7 @@
else: res=ann[2]
for j in addc: l.append(res[j])
if save: o.write('\t'.join(l)+'\n')
- else: print '\t'.join(l)
+ else: print('\t'.join(l))
tabix.close()
if save:
o.close()
diff -ru a/accessory/FilterTable.py b/accessory/FilterTable.py
--- a/accessory/FilterTable.py 2020-07-16 16:16:59.360014702 -0500
+++ b/accessory/FilterTable.py 2020-07-16 16:17:22.209013627 -0500
@@ -30,7 +30,7 @@
pid=str(os.getpid()+random.randint(0,999999999))
def usage():
- print """
+ print("""
USAGE: python FilterTable.py [options]
Options:
-i Table file
@@ -43,12 +43,12 @@
-p Print simple statistics
-h Print this help
-"""
+""")
try:
opts, args = getopt.getopt(sys.argv[1:], 'i:o:f:hs:F:S:Ep',["help"])
-except getopt.GetoptError, err:
- print str(err)
+except getopt.GetoptError as err:
+ print(str(err))
usage()
sys.exit()
diff -ru a/accessory/get_DE_events.py b/accessory/get_DE_events.py
--- a/accessory/get_DE_events.py 2020-07-16 16:16:59.360014702 -0500
+++ b/accessory/get_DE_events.py 2020-07-16 16:17:22.646013607 -0500
@@ -104,7 +104,7 @@
#WARNING those are np arrays.
for i in range(0,edit_level_table.shape[0]):
- print i #keep track of progress
+ print(i) #keep track of progress
disease_edit_row = edit_level_table.loc[i, disease_people]
control_edit_row = edit_level_table.loc[i, control_people]
disease_cov_row = cov_table.loc[i, disease_people]
@@ -206,7 +206,7 @@
#write the full_table to output
full_table.to_csv(output_file, sep='\t', index=False)
- print "job completed\n"
+ print("job completed\n")
@@ -225,12 +225,12 @@
def Sample_percentage(row):
"""Percentage of samples from each type"""
- percentage = (len(filter(lambda x: x!= '-', row))/float(len(row)))*100
+ percentage = (len([x for x in row if x!= '-'])/float(len(row)))*100
return round(percentage)
def Sample_count(row):
"""Number of samples from each type"""
- count = len(filter(lambda x: x!= '-', row))
+ count = len([x for x in row if x!= '-'])
return count
def get_bh(pvalue,siglevel):
@@ -269,7 +269,7 @@
if(row_a[-1] != '-' and row_a[-1] != 0.0 and row_a[-1] <= 0.05):
row = row[0].split('_') + row[2:]
row.insert(2, 'A.to.G')
- print '\t'.join(map(str,row))
+ print('\t'.join(map(str,row)))
def tuple_replace(i):
if type(i) == tuple:
@@ -292,11 +292,11 @@
with open(samples_informations_file, 'r') as f:
for line in f:
if line.startswith('SRR'):
- line = map(str.strip, line.split(','))
+ line = list(map(str.strip, line.split(',')))
sample_informations.setdefault(line[0], line[1])
-cwd = filter(os.path.isdir, os.listdir(os.getcwd()))
+cwd = list(filter(os.path.isdir, os.listdir(os.getcwd())))
all_available_sites = []
sample_edited_sites = {}
for directory in cwd:
@@ -306,7 +306,7 @@
with open(table,'r') as a:
for line in a:
if line.startswith('chr'):
- s = map(str.strip, line.split("\t"))
+ s = list(map(str.strip, line.split("\t")))
if s[7] == 'AG':
site, freq, coverage = s[0] + "_" + s[1], s[8], s[4]
freq_gnum_cov = '%s^%s^%s' %(s[8],eval(s[6])[2],s[4])
@@ -314,14 +314,14 @@
if (int(coverage) >= min_coverage) and (float(freq) >= min_edit_frequency):
sample_edited_sites.setdefault((directory, site), []).append((freq, freq_gnum_cov))
-table_columns = map(lambda x: x + '_' + sample_informations[x], sorted(sample_informations.keys()))
+table_columns = [x + '_' + sample_informations[x] for x in sorted(sample_informations.keys())]
disease = [i for i in table_columns if i.upper().find('DIS') != -1]
controls = [i for i in table_columns if i.upper().find('CTRL') != -1]
if enable_linear_model:
outtable=''
- header = ['chromosome', 'position', 'type_editing'] + map(remove_underscore, controls) + map(remove_underscore, disease)
+ header = ['chromosome', 'position', 'type_editing'] + list(map(remove_underscore, controls)) + list(map(remove_underscore, disease))
outtable += '\t'.join(header)
outtable += '\n'
#print '\t'.join(header)
@@ -329,13 +329,13 @@
row = [chrom]
for col in header[2:]:#header.index('[num_controls/num_disease]')]:
row.append(sample_edited_sites.get((col.split('_')[0],chrom), ['-'])[0])
- ctrls = zip(*(zip(controls,row[1:])))[1]
- dss = zip(*(zip(disease,row[len(ctrls)+1:])))[1]
- ctrls_freq = map(tuple_replace, ctrls)
- dss_freq = map(tuple_replace, dss)
+ ctrls = list(zip(*(list(zip(controls,row[1:])))))[1]
+ dss = list(zip(*(list(zip(disease,row[len(ctrls)+1:])))))[1]
+ ctrls_freq = list(map(tuple_replace, ctrls))
+ dss_freq = list(map(tuple_replace, dss))
row.append(str([Sample_count(ctrls), Sample_count(dss)]))
- row_b = map(tuple_replace_bis, row)
+ row_b = list(map(tuple_replace_bis, row))
row_b = row_b[0].split('_') + row_b[2:]
row_b.insert(2, 'A.to.G')
final_list = row_b[:-1]
@@ -359,20 +359,20 @@
if pvalue_correction == 2:
header += ['pvalue BH corrected']
- print '\t'.join(header)
+ print('\t'.join(header))
for chrom in sorted(all_available_sites, key = lambda x: Set_Chr_Nr(x)):
row = [chrom]
for col in header[3:header.index('[num_controls/num_disease]')]:
row.append(sample_edited_sites.get((col.split('_')[0],chrom), ['-'])[0])
- ctrls = zip(*(zip(controls,row[1:])))[1]
- dss = zip(*(zip(disease,row[len(ctrls)+1:])))[1]
- ctrls_freq = map(tuple_replace, ctrls)
- dss_freq = map(tuple_replace, dss)
+ ctrls = list(zip(*(list(zip(controls,row[1:])))))[1]
+ dss = list(zip(*(list(zip(disease,row[len(ctrls)+1:])))))[1]
+ ctrls_freq = list(map(tuple_replace, ctrls))
+ dss_freq = list(map(tuple_replace, dss))
row.append(str([Sample_count(ctrls), Sample_count(dss)]))
if (Sample_percentage(ctrls) >= min_sample_testing) and (Sample_percentage(dss) >= min_sample_testing):
- ctrls_mean = sum(map(float, filter(lambda x: x!= '-', ctrls_freq)))/len(filter(lambda x: x!= '-', ctrls_freq))
- dss_mean = sum(map(float, filter(lambda x: x!= '-', dss_freq)))/len(filter(lambda x : x!= '-', dss_freq))
+ ctrls_mean = sum(map(float, [x for x in ctrls_freq if x!= '-']))/len([x for x in ctrls_freq if x!= '-'])
+ dss_mean = sum(map(float, [x for x in dss_freq if x!= '-']))/len([x for x in dss_freq if x!= '-'])
delta_diff = abs(ctrls_mean - dss_mean)
pvalue=stats.mannwhitneyu(ctrls_freq, dss_freq, alternative='two-sided')
row.append(round(delta_diff, 3))
@@ -388,12 +388,12 @@
row += ['-', '-']
else:
row += ['-', '-', '-']
- row_a = map(tuple_replace, row)
- row_b = map(tuple_replace_bis, row)
+ row_a = list(map(tuple_replace, row))
+ row_b = list(map(tuple_replace_bis, row))
if pvalue_correction != 0 and only_significants == 'yes':
only_sig(row_a,row_b)
else:
row_b = row_b[0].split('_') + row_b[2:]
row_b.insert(2, 'A.to.G')
- print '\t'.join(map(str,row_b))
+ print('\t'.join(map(str,row_b)))
diff -ru a/accessory/GFFtoTabix.py b/accessory/GFFtoTabix.py
--- a/accessory/GFFtoTabix.py 2020-07-16 16:16:59.360014702 -0500
+++ b/accessory/GFFtoTabix.py 2020-07-16 16:17:22.264013625 -0500
@@ -31,7 +31,7 @@
pid=str(os.getpid()+random.randint(0,999999999))
def usage():
- print """
+ print("""
USAGE: python GFFtoTabix.py [options]
Options:
-i GFF file
@@ -41,7 +41,7 @@
-u Save an uncompressed GFF copy (add _copy suffix)
-h Print this help
-"""
+""")
try:
opts, args = getopt.getopt(sys.argv[1:], "i:Sb:t:hu",["help"])
@@ -49,7 +49,7 @@
usage()
sys.exit(2)
except getopt.GetoptError as err:
- print str(err) # will print something like "option -a not recognized"
+ print(str(err)) # will print something like "option -a not recognized"
usage()
sys.exit(2)
diff -ru a/accessory/rediportal2recoding.py b/accessory/rediportal2recoding.py
--- a/accessory/rediportal2recoding.py 2020-07-16 16:16:59.360014702 -0500
+++ b/accessory/rediportal2recoding.py 2020-07-16 16:17:22.709013604 -0500
@@ -41,4 +41,4 @@
gff_row = line[0] + '\t'+ valore + '\t' + 'ed' + '\t' + line[1] + \
'\t' + line[1] + '\t' + '.' + '\t' + line[4] + '\t' + '.' + '\t' + \
'gene_id' + ' ' + '"ed_%s";' %(i) + ' ' + 'transcript_id' + ' ' + '"ed_%s";' %(i)
- print gff_row
+ print(gff_row)
diff -ru a/accessory/SearchInTable.py b/accessory/SearchInTable.py
--- a/accessory/SearchInTable.py 2020-07-16 16:16:59.360014702 -0500
+++ b/accessory/SearchInTable.py 2020-07-16 16:17:22.309013623 -0500
@@ -25,7 +25,7 @@
#pid=str(os.getpid()+random.randint(0,999999999))
def usage():
- print """
+ print("""
USAGE: python SearchInTable.py [options]
Options:
-i Sorted table file (first col=reference; second col=coordinate 1 based)
@@ -42,7 +42,7 @@
-o Save found/not found positions on file
-h Print this help
-"""
+""")
#-k skip first INT lines [0]
try:
@@ -51,7 +51,7 @@
usage()
sys.exit(2)
except getopt.GetoptError as err:
- print str(err) # will print something like "option -a not recognized"
+ print(str(err)) # will print something like "option -a not recognized"
usage()
sys.exit(2)
diff -ru a/accessory/selectPositions.py b/accessory/selectPositions.py
--- a/accessory/selectPositions.py 2020-07-16 16:16:59.360014702 -0500
+++ b/accessory/selectPositions.py 2020-07-16 16:17:22.833013598 -0500
@@ -25,7 +25,7 @@
pid=str(os.getpid()+random.randint(0,999999999))
def usage():
- print """
+ print("""
USAGE: python selectPositions.py [options]
Options:
-i Table file from REDItools
@@ -44,7 +44,7 @@
-o Save selected positions on outTable_%s
-h Print this help
-"""%(pid)
+"""%(pid))
try:
opts, args = getopt.getopt(sys.argv[1:], "i:c:C:v:s:f:F:euo:hrd:RV:",["help"])
@@ -52,7 +52,7 @@
usage()
sys.exit(2)
except getopt.GetoptError as err:
- print str(err) # will print something like "option -a not recognized"
+ print(str(err)) # will print something like "option -a not recognized"
usage()
sys.exit(2)
diff -ru a/accessory/SortGFF.py b/accessory/SortGFF.py
--- a/accessory/SortGFF.py 2020-07-16 16:16:59.360014702 -0500
+++ b/accessory/SortGFF.py 2020-07-16 16:17:22.357013620 -0500
@@ -35,7 +35,7 @@
pid=str(os.getpid()+random.randint(0,999999999))
def usage():
- print """
+ print("""
USAGE: python SortGFF.py [options]
Options:
-i GFF file
@@ -44,7 +44,7 @@
-t Temporary directory to use (multiple -t may be used)
-h Print this help
-"""%(pid)
+"""%(pid))
try:
opts, args = getopt.getopt(sys.argv[1:], "i:o:b:t:h",["help"])
@@ -52,7 +52,7 @@
usage()
sys.exit(2)
except getopt.GetoptError as err:
- print str(err) # will print something like "option -a not recognized"
+ print(str(err)) # will print something like "option -a not recognized"
usage()
sys.exit(2)
diff -ru a/accessory/SortTable.py b/accessory/SortTable.py
--- a/accessory/SortTable.py 2020-07-16 16:16:59.360014702 -0500
+++ b/accessory/SortTable.py 2020-07-16 16:17:22.411013618 -0500
@@ -35,7 +35,7 @@
pid=str(os.getpid()+random.randint(0,999999999))
def usage():
- print """
+ print("""
USAGE: python SortTable.py [options]
Options:
-i Table file
@@ -50,7 +50,7 @@
-t Temporary directory to use (multiple -t may be used)
-h Print this help
-"""%(pid)
+"""%(pid))
try:
opts, args = getopt.getopt(sys.argv[1:], "i:o:b:t:hd:s:c:e:m:O",["help"])
@@ -58,7 +58,7 @@
usage()
sys.exit(2)
except getopt.GetoptError as err:
- print str(err) # will print something like "option -a not recognized"
+ print(str(err)) # will print something like "option -a not recognized"
usage()
sys.exit(2)
diff -ru a/accessory/subCount2.py b/accessory/subCount2.py
--- a/accessory/subCount2.py 2020-07-16 16:16:59.360014702 -0500
+++ b/accessory/subCount2.py 2020-07-16 16:17:22.854013597 -0500
@@ -28,5 +28,5 @@
for i in s:
try: v=(s[i]/float(all))*100
except: v=0.0
- print i,s[i],all,v
+ print(i,s[i],all,v)
diff -ru a/accessory/subCount.py b/accessory/subCount.py
--- a/accessory/subCount.py 2020-07-16 16:16:59.360014702 -0500
+++ b/accessory/subCount.py 2020-07-16 16:17:22.844013597 -0500
@@ -30,5 +30,5 @@
for i in s:
try: v=(s[i]/float(all))*100
except: v=0.0
- print i,s[i],all,v
+ print(i,s[i],all,v)
diff -ru a/accessory/TableToGFF.py b/accessory/TableToGFF.py
--- a/accessory/TableToGFF.py 2020-07-16 16:16:59.360014702 -0500
+++ b/accessory/TableToGFF.py 2020-07-16 16:17:22.474013615 -0500
@@ -29,7 +29,7 @@
pid=str(os.getpid()+random.randint(0,999999999))
def usage():
- print """
+ print("""
USAGE: python TableToGFF.py [options]
Options:
-i Table file from REDItools
@@ -40,7 +40,7 @@
-o Outfile [outTable_%s.gff]
-h Print this help
-"""%(pid)
+"""%(pid))
try:
opts, args = getopt.getopt(sys.argv[1:], "i:o:sthT:b:",["help"])
@@ -48,7 +48,7 @@
usage()
sys.exit(2)
except getopt.GetoptError as err:
- print str(err) # will print something like "option -a not recognized"
+ print(str(err)) # will print something like "option -a not recognized"
usage()
sys.exit(2)
diff -ru a/accessory/tableToTabix.py b/accessory/tableToTabix.py
--- a/accessory/tableToTabix.py 2020-07-16 16:16:59.360014702 -0500
+++ b/accessory/tableToTabix.py 2020-07-16 16:17:22.913013594 -0500
@@ -31,7 +31,7 @@
pid=str(os.getpid()+random.randint(0,999999999))
def usage():
- print """
+ print("""
USAGE: python tableToTabix.py [options]
Options:
-i TAB-delimited file
@@ -46,7 +46,7 @@
-u Save an uncompressed GFF copy (add _copy suffix)
-h Print this help
-"""
+""")
try:
opts, args = getopt.getopt(sys.argv[1:], "i:Sb:t:hus:c:e:m:0",["help"])
@@ -54,7 +54,7 @@
usage()
sys.exit(2)
except getopt.GetoptError as err:
- print str(err) # will print something like "option -a not recognized"
+ print(str(err)) # will print something like "option -a not recognized"
usage()
sys.exit(2)
diff -ru a/main/REDItoolDenovo.py b/main/REDItoolDenovo.py
--- a/main/REDItoolDenovo.py 2020-07-16 16:16:59.360014702 -0500
+++ b/main/REDItoolDenovo.py 2020-07-16 16:17:21.265013672 -0500
@@ -75,7 +75,7 @@
return 1
numerator = 1
denominator = 1
- for i in xrange(s+1, population + 1):
+ for i in range(s+1, population + 1):
numerator *= i
denominator *= (i - s)
return numerator/denominator
@@ -275,7 +275,7 @@
try: import pysam
except: sys.exit('Pysam module not found.')
from multiprocessing import Process, Queue
-from Queue import Empty
+from queue import Empty
try:
from fisher import pvalue
exfisher=1
@@ -292,7 +292,7 @@
pid=str(os.getpid()+random.randint(0,999999999))
def usage():
- print """
+ print("""
USAGE: python REDItoolDenovo.py [options]
Options:
-i BAM file
@@ -343,12 +343,12 @@
- For Tophat2 use 50
- For GSNAP use 30
-"""%(pid)
+"""%(pid))
try:
opts, args = getopt.getopt(sys.argv[1:], "b:f:k:t:o:c:q:m:O:s:edpuT:B:v:n:EP:r:hHa:i:lIU:V:w:XG:K:F:g:x:W")
except getopt.GetoptError as err:
- print str(err) # will print something like "option -a not recognized"
+ print(str(err)) # will print something like "option -a not recognized"
usage()
sys.exit(2)
@@ -474,7 +474,7 @@
annfile=a
uann=1
else:
- print o
+ print(o)
assert False, "Unhandled Option"
#######
@@ -532,7 +532,7 @@
return False
try:
os.kill(pid, 0)
- except OSError, e:
+ except OSError as e:
return e.errno == errno.EPERM
else:
return True
@@ -637,9 +637,9 @@
subs=[]
subv=[]
for i in seq.upper():
- if b.has_key(i): b[i]+=1
+ if i in b: b[i]+=1
for i in b:
- if not b.has_key(ref): continue
+ if ref not in b: continue
if b[i]!=0 and i!=ref:
vv=float(b[i])/(b[i]+b[ref])
subv.append((b[i],vv,ref+i))
@@ -690,7 +690,7 @@
a={'A':'T','T':'A','C':'G','G':'C'}
ss=''
for i in s.upper():
- if a.has_key(i): ss+=a[i]
+ if i in a: ss+=a[i]
else: ss+='N'
return ss
@@ -777,7 +777,7 @@
frefs.append(l[0])
fidxinfo.close()
rnof=[]
-for i in rrefs.keys():
+for i in list(rrefs.keys()):
if i not in frefs: sys.stderr.write('WARNING: Region %s in RNA-Seq not found in reference file.\n' %(i))
#####################
@@ -817,8 +817,8 @@
#mainbam=pysam.Samfile(bamfile,"rb")
#regions=mainbam.references
#mainbam.close()
-dicregions=dict(rrefs.items())
-chrs=[x for x in dicregions.keys() if x not in nochrs]
+dicregions=dict(list(rrefs.items()))
+chrs=[x for x in list(dicregions.keys()) if x not in nochrs]
sys.stderr.write('Analysis on %i regions.\n' %(len(chrs)))
if infolder!='': outfolder=os.path.join(outfolder_,'denovo_%s_%s' %(infolder,pid))
@@ -906,7 +906,7 @@
if pileupread.alignment.has_tag('SA'): continue
#s,q,t,qq=pileupread.alignment.seq[pileupread.qpos].upper(),ord(pileupread.alignment.qual[pileupread.qpos])-QVAL,'*',pileupread.alignment.qual[pileupread.qpos]
# escludi posizioni introniche nei pressi di splice sites
- if exss and di.has_key(pileupcolumn.reference_pos+1): continue #MOD
+ if exss and pileupcolumn.reference_pos+1 in di: continue #MOD
# multiple hit
if exh: #MOD
if pileupread.alignment.is_secondary: continue #MOD
@@ -998,7 +998,7 @@
elif pileupread.alignment.is_read2: rt=2
else: rt=0
rname=pileupread.alignment.query_name+'_%i'%(rt) #MOD
- if d.has_key(rname): blatc+='0' #continue
+ if rname in d: blatc+='0' #continue
else: blatc+='1'
# se la base e' diversa dal reference
# se in regione omopolimerica scarta
@@ -1032,7 +1032,7 @@
if not custsub:
ni='ACGT'
for b in range(4):
- if dsubs.has_key(ref.upper()+ni[b]):
+ if ref.upper()+ni[b] in dsubs:
dsubs[ref.upper()+ni[b]]+=bcomp[b]
if expos:
if chr in extabix.contigs:
diff -ru a/main/REDItoolDnaRna.py b/main/REDItoolDnaRna.py
--- a/main/REDItoolDnaRna.py 2020-07-16 16:16:59.360014702 -0500
+++ b/main/REDItoolDnaRna.py 2020-07-16 16:17:21.757013649 -0500
@@ -23,7 +23,7 @@
try: import pysam
except: sys.exit('Pysam module not found.')
from multiprocessing import Process, Queue
-from Queue import Empty
+from queue import Empty
import gzip
pysamVersion=pysam.__version__
@@ -34,7 +34,7 @@
pid=str(os.getpid()+random.randint(0,999999999))
def usage():
- print """
+ print("""
USAGE: python REDItoolDnaRNA.py [options]
Options:
-i RNA-Seq BAM file
@@ -103,7 +103,7 @@
- For Tophat2 use 50
- For GSNAP use 30
-"""%(pid)
+"""%(pid))
#option --fastq Fastq to get reads [requires --reads], separated by comma [if paired] NOT IMPLEMENTED
#option --rmOver Remove overlapping reads NOT IMPLEMENTED
@@ -111,7 +111,7 @@
try:
opts, args = getopt.getopt(sys.argv[1:], "i:f:k:t:o:c:q:m:O:s:edpuA:a:B:b:lLv:n:EPr:hHIXG:K:j:C:JDUzw:N:ZW:RVMT:F:x:g:SY:",["help","gzip","reads","addP","rmIndels"])
except getopt.GetoptError as err:
- print str(err) # will print something like "option -a not recognized"
+ print(str(err)) # will print something like "option -a not recognized"
usage()
sys.exit(2)
@@ -325,7 +325,7 @@
params.append('Analysis ID: %s\n' %(pid))
params.append('Analysis time: %s\n' %(script_time))
params.append('-i --> RNA-Seq BAM file: %s\n' %(bamfile))
-params.append('-j --> DNA-Seq BAM file(s): %s\n' %(','.join(dgbamfile.keys())))
+params.append('-j --> DNA-Seq BAM file(s): %s\n' %(','.join(list(dgbamfile.keys()))))
params.append('-I --> Sort RNA-Seq BAM file: %i\n' %(sortbam))
params.append('-J --> Sort DNA-Seq BAM file: %i\n' %(sortgbam))
params.append('-f --> Reference file: %s\n' %(fastafile))
@@ -483,9 +483,9 @@
subs=[]
subv=[]
for i in seq.upper():
- if b.has_key(i): b[i]+=1
+ if i in b: b[i]+=1
for i in b:
- if not b.has_key(ref): continue
+ if ref not in b: continue
if b[i]!=0 and i!=ref:
vv=float(b[i])/(b[i]+b[ref])
subv.append((b[i],vv,ref+i))
@@ -537,7 +537,7 @@
a={'A':'T','T':'A','C':'G','G':'C'}
ss=''
for i in s.upper():
- if a.has_key(i): ss+=a[i]
+ if i in a: ss+=a[i]
elif i==' ': ss+=' '
elif i=='-': ss+='-'
else: ss+='N'
@@ -682,7 +682,7 @@
if l.count(i[0])==2:
s='='
if i[1]!=i[2]: s='!'
- if us.has_key(i[0]): us[i[0]].append((x,s))
+ if i[0] in us: us[i[0]].append((x,s))
else: us[i[0]]=[(x,s)]
x+=1
for i in us:
@@ -753,7 +753,7 @@
pysam.faidx(fastafile)
###########################################################
# Check reference for name consistency
-grefs=dgdic.keys()
+grefs=list(dgdic.keys())
rrefs={}
ridxinfo=pysam.idxstats(bamfile)
for j in ridxinfo.split('\n'): #MOD
@@ -769,7 +769,7 @@
fidxinfo.close()
# in rna-seq
rnof=[]
-for i in rrefs.keys():
+for i in list(rrefs.keys()):
if i not in frefs: sys.stderr.write('WARNING: Region %s in RNA-Seq not found in reference file.\n' %(i))
if len(gbamfile)!=0:
for i in grefs:
@@ -833,9 +833,9 @@
#regions=mainbam.references
#regionslens=mainbam.lengths
#mainbam.close()
-dicregions=dict(rrefs.items())
+dicregions=dict(list(rrefs.items()))
#dicregions=dict([(regions[x],regionslens[x]) for x in range(len(regions))])
-chrs=[x for x in dicregions.keys() if x not in nochrs]
+chrs=[x for x in list(dicregions.keys()) if x not in nochrs]
if fworkR: sys.stderr.write('Analysis on region %s:%i-%i.\n' %(workR[0],workR[1][0],workR[1][1]))
else: sys.stderr.write('Analysis on %i regions.\n' %(len(chrs)))
###########################################################
@@ -883,7 +883,7 @@
isgbam=1
inputs=myinput.split('$')
chr,bamfile,start_region,lenregion,suff_=inputs[0],inputs[1],int(inputs[2]),int(inputs[3]),inputs[4]
- if not dgdic.has_key(chr): isgbam=0
+ if chr not in dgdic: isgbam=0
outfile=os.path.join(outfolder,'table_%s'%(suff_))
if slist:
if gziptab: outrna=gzip.open(os.path.join(outfolder,'pileupRNA_%s.gz'%(suff)),'wb')
@@ -1024,7 +1024,7 @@
if pileupread.alignment.is_read1: rt=1
elif pileupread.alignment.is_read2: rt=2
rname=pileupread.alignment.query_name+'_%i'%(rt)
- if gd.has_key(rname): gblatc+='0' #continue
+ if rname in gd: gblatc+='0' #continue
else: gblatc+='1'
# se la base e' diversa dal reference
# se in regione omopolimerica scarta
@@ -1079,7 +1079,7 @@
#s,q,t,qq=pileupread.alignment.query_sequence[pileupread.query_position].upper(),pileupread.alignment.query_qualities[pileupread.query_position],'*',pileupread.alignment.qual[pileupread.query_position]
#s,q,t,qq=pileupread.alignment.seq[pileupread.qpos].upper(),ord(pileupread.alignment.qual[pileupread.qpos])-QVAL,'*',pileupread.alignment.qual[pileupread.qpos]
# escludi posizioni introniche nei pressi di splice sites
- if exss and di.has_key(pileupcolumn.reference_pos+1): continue
+ if exss and pileupcolumn.reference_pos+1 in di: continue
# multiple hit
if exh:
if pileupread.alignment.is_secondary: continue
@@ -1179,7 +1179,7 @@
elif pileupread.alignment.is_read2: rt=2
else: rt=0
rname=pileupread.alignment.query_name+'_%i'%(rt)
- if d.has_key(rname): blatc+='0' #continue
+ if rname in d: blatc+='0' #continue
else: blatc+='1'
# se la base e' diversa dal reference
# se in regione omopolimerica scarta
@@ -1213,7 +1213,7 @@
else: addpos=(pileupread.alignment.query_name,'-',pileupread.alignment.reference_name,'-',pileupread.alignment.reference_start,pileupread.alignment.reference_end,0 , 0)
rqname_comp=rqname+'$'+pileupread.alignment.reference_name+'$'+str(pileupcolumn.reference_pos+1)
#addpos=(chr+'_'+str(pileupcolumn.reference_pos+1),pileupcolumn.reference_pos+1)
- if not grdb.has_key(rqname):
+ if rqname not in grdb:
#print rqname reference_start
outreads.write('>'+rqname_comp+'\n'+rseqname+'\n')
#grdb[rqname]=[addpos]
@@ -1221,7 +1221,7 @@
# if addpos not in grdb[rqname]:
# grdb[rqname].append(addpos)
if addP:
- if not grdb2.has_key(rname): grdb2[rname]=addpos
+ if rname not in grdb2: grdb2[rname]=addpos
if seq.strip()!='':
#print seq,qual,squal
if rmIndel:
@@ -1268,7 +1268,7 @@
if exinv and subs=='-': continue
if not checkSubs(subs): continue
#print out rna-seq info + dna-seq
- if gdic.has_key(pileupcolumn.reference_pos): # abbiamo l'informazione genomica
+ if pileupcolumn.reference_pos in gdic: # abbiamo l'informazione genomica
if exnonh and not gdic[pileupcolumn.reference_pos][1]: continue
if mystrand=='0':
gdic[pileupcolumn.reference_pos][0][2]=comp2(eval(gdic[pileupcolumn.reference_pos][0][2]))
diff -ru a/main/REDItoolKnown.py b/main/REDItoolKnown.py
--- a/main/REDItoolKnown.py 2020-07-16 16:16:59.360014702 -0500
+++ b/main/REDItoolKnown.py 2020-07-16 16:17:22.063013634 -0500
@@ -23,7 +23,7 @@
try: import pysam
except: sys.exit('Pysam module not found.')
from multiprocessing import Process, Queue
-from Queue import Empty
+from queue import Empty
pysamVersion=pysam.__version__
@@ -34,7 +34,7 @@
pid=str(os.getpid()+random.randint(0,999999999))
def usage():
- print """
+ print("""
USAGE: python REDItoolKnown.py [options]
Options:
-i BAM file
@@ -82,12 +82,12 @@
- For Tophat2 use 50
- For GSNAP use 30
-"""%(pid)
+"""%(pid))
try:
opts, args = getopt.getopt(sys.argv[1:], "i:f:k:t:o:c:q:m:O:s:edpuT:B:Sv:n:EP:r:hHIXG:K:l:C:F:x:g:U")
except getopt.GetoptError as err:
- print str(err) # will print something like "option -a not recognized"
+ print(str(err)) # will print something like "option -a not recognized"
usage()
sys.exit(2)
@@ -257,7 +257,7 @@
return False
try:
os.kill(pid, 0)
- except OSError, e:
+ except OSError as e:
return e.errno == errno.EPERM
else:
return True
@@ -361,9 +361,9 @@
subs=[]
subv=[]
for i in seq.upper():
- if b.has_key(i): b[i]+=1
+ if i in b: b[i]+=1
for i in b:
- if not b.has_key(ref): continue
+ if ref not in b: continue
if b[i]!=0 and i!=ref:
vv=float(b[i])/(b[i]+b[ref])
subv.append((b[i],vv,ref+i))
@@ -414,7 +414,7 @@
a={'A':'T','T':'A','C':'G','G':'C'}
ss=''
for i in s.upper():
- if a.has_key(i): ss+=a[i]
+ if i in a: ss+=a[i]
else: ss+='N'
return ss
@@ -524,7 +524,7 @@
fidxinfo.close()
# in rna-seq
rnof=[]
-for i in rrefs.keys():
+for i in list(rrefs.keys()):
if i not in frefs: sys.stderr.write('WARNING: Region %s in RNA-Seq not found in reference file.\n' %(i))
##################################
@@ -568,8 +568,8 @@
#mainbam.close()
#dicregions=dict([(regions[x],regionslens[x]) for x in range(len(regions))])
#chrs=[x for x in regions if x not in nochrs]
-dicregions=dict(rrefs.items())
-chrs=[x for x in dicregions.keys() if x not in nochrs]
+dicregions=dict(list(rrefs.items()))
+chrs=[x for x in list(dicregions.keys()) if x not in nochrs]
sys.stderr.write('Analysis on %i regions.\n' %(len(chrs)))
if infolder!='': outfolder=os.path.join(outfolder_,'known_%s_%s' %(infolder,pid))
@@ -654,7 +654,7 @@
# else explore bam to find exact positions
for pileupcolumn in bam.pileup(chr,startk,endk,stepper='nofilter', max_depth=MAX_DEPTH):
if not startk<=pileupcolumn.reference_pos<=endk: continue
- if not kdic.has_key(pileupcolumn.reference_pos+1): continue
+ if pileupcolumn.reference_pos+1 not in kdic: continue
ref=fasta.fetch(chr,pileupcolumn.reference_pos,pileupcolumn.reference_pos+1).upper()
seq,qual,strand,squal,blatc='',0,'',[],''
if rmsh:
@@ -668,7 +668,7 @@
if pileupread.alignment.is_supplementary: continue
if pileupread.alignment.has_tag('SA'): continue
# escludi posizioni introniche nei pressi di splice sites
- if exss and di.has_key(pileupcolumn.reference_pos+1): continue
+ if exss and pileupcolumn.reference_pos+1 in di: continue
# multiple hit
if exh:
if pileupread.alignment.is_secondary: continue
@@ -754,7 +754,7 @@
elif pileupread.alignment.is_read2: rt=2
else: rt=0
rname=pileupread.alignment.query_name+'_%i'%(rt)
- if d.has_key(rname): blatc+='0' #continue
+ if rname in d: blatc+='0' #continue
else: blatc+='1'
# se la base e' diversa dal reference
# se in regione omopolimerica scarta

11
var/spack/repos/builtin/packages/reditools/setup.py.patch Normal file
View File

@ -0,0 +1,11 @@
--- a/setup.py 2020-07-16 14:01:48.601449013 -0500
+++ b/setup.py 2020-07-16 14:02:31.547441668 -0500
@@ -33,7 +33,7 @@
'Operating System :: POSIX',
'Programming Language :: Python',
],
- long_description=open('README').read(),
+ long_description=open('README_1.md').read(),
platforms=['Linux','Unix','MacOS']
)