.gitignore

@@ -63,6 +63,7 @@ docs/_build/
 **/doc/_build/
 
 #Data files
+/data/
 *.wig
 *.dat
 *.png

CHANGELOG.md

 # Change log
 All notable changes to this project will be documented in this file.
 
+## Version 3.0.0 2019-07-18
+#### TRANSIT:
+ - TRANSIT now supports python 3. (To use with python 2, use releases < 3.0.0)
+ - Improved speed of GSEA in Pathway Enrichment analysis.
 
 ## Version 2.5.2 2019-05-16
 #### TRANSIT:

README.md

-# TRANSIT 2.5.1
-
-[![Build Status](https://travis-ci.org/mad-lab/transit.svg?branch=master)](https://travis-ci.org/mad-lab/transit)   [![Documentation Status](https://readthedocs.org/projects/transit/badge/?version=latest)](http://transit.readthedocs.io/en/latest/?badge=latest)   [![Downloads](https://pepy.tech/badge/tnseq-transit)](https://pepy.tech/project/tnseq-transit)
+# TRANSIT
 
+[![Version](https://img.shields.io/github/tag/mad-lab/transit.svg)](https://github.com/mad-lab/transit)   [![Build Status](https://travis-ci.org/mad-lab/transit.svg?branch=master)](https://travis-ci.org/mad-lab/transit)   [![Documentation Status](https://readthedocs.org/projects/transit/badge/?version=latest)](http://transit.readthedocs.io/en/latest/?badge=latest)   [![Downloads](https://pepy.tech/badge/tnseq-transit)](https://pepy.tech/project/tnseq-transit)
+=======
 
 Welcome! This is the distribution for the TRANSIT and TPP tools developed by the [Ioerger Lab](http://orca2.tamu.edu/tom/iLab.html) at Texas A&M University.
 

debian/changelog

+tnseq-transit (3.0.0-1) UNRELEASED; urgency=medium
+
+  * New upstream version
+  * New version supports Python3
+    Closes: #931711
+  * debhelper-compat 12
+  * Standards-Version: 4.4.0
+  * Depends: s/python3-wxgtk3.0/python3-wxgtk4.0/
+  TODO: https://pypi.org/project/PyPubSub/
+
+ -- Andreas Tille <tille@debian.org>  Thu, 25 Jul 2019 21:35:41 +0200
+
 tnseq-transit (2.5.2-1) unstable; urgency=medium
 
   * New upstream version

debian/compat

-12

debian/control

@@ -3,30 +3,30 @@ Maintainer: Debian Med Packaging Team <debian-med-packaging@lists.alioth.debian.
 Uploaders: Andreas Tille <tille@debian.org>
 Section: science
 Priority: optional
-Build-Depends: debhelper (>= 12~),
+Build-Depends: debhelper-compat (= 12),
                dh-python,
-               python-dev,
-               python-setuptools,
-               python-numpy,
-               python-scipy,
-               python-pil,
-               python-matplotlib,
-               python-statsmodels,
+               python3-dev,
+               python3-setuptools,
+               python3-numpy,
+               python3-scipy,
+               python3-pil,
+               python3-matplotlib,
+               python3-statsmodels,
                bwa
-Standards-Version: 4.3.0
+Standards-Version: 4.4.0
 Vcs-Browser: https://salsa.debian.org/med-team/tnseq-transit
 Vcs-Git: https://salsa.debian.org/med-team/tnseq-transit.git
 Homepage: http://saclab.tamu.edu/essentiality/transit/
 
 Package: tnseq-transit
 Architecture: any
-Depends: ${python:Depends},
+Depends: ${python3:Depends},
          ${misc:Depends},
-         python-numpy,
-         python-scipy,
-         python-pil,
-         python-matplotlib,
-         python-wxgtk3.0,
+         python3-numpy,
+         python3-scipy,
+         python3-pil,
+         python3-matplotlib,
+         python3-wxgtk4.0,
          bwa
 Breaks: transit
 Provides: transit

debian/patches/2to3.patch

+Author: Andreas Tille <tille@debian.org>
+Last-Update: Thu, 25 Jul 2019 21:35:41 +0200
+Description: Use 2to3 to finalise Python2 -> Python3 migration
+
+--- a/src/pytransit/analysis/multitnseq.py
++++ b/src/pytransit/analysis/multitnseq.py
+@@ -9,7 +9,7 @@ try:
+ except Exception as e:
+     hasR = False
+ 
+-import base
++from . import base
+ import numpy
+ import scipy
+ import pdfkit
+@@ -18,7 +18,7 @@ import statsmodels.stats.multicomp
+ import pytransit.transit_tools as transit_tools
+ import pytransit.tnseq_tools as tnseq_tools
+ import pytransit.norm_tools as norm_tools
+-from multitnseq_helpers import def_r_samples_corrplot, def_r_clustering, def_r_make_heatmap, def_r_conditions_corrplot
++from .multitnseq_helpers import def_r_samples_corrplot, def_r_clustering, def_r_make_heatmap, def_r_conditions_corrplot
+ 
+ ###### GUI ELEMENTS ######
+ short_name = "MultiTnSeq"
+@@ -60,7 +60,7 @@ class MultiTnSeqMethod(base.AnalysisMeth
+         (args, kwargs) = transit_tools.cleanargs(rawargs)
+ 
+         if (kwargs.get('-help', False) or kwargs.get('h', False)):
+-            print(MultiTnSeqMethod.usage_string())
++            print((MultiTnSeqMethod.usage_string()))
+             sys.exit(0)
+ 
+         fna = args[0]
+@@ -130,7 +130,7 @@ class MultiTnSeqMethod(base.AnalysisMeth
+           if Samples.get(row,"Condition") == cond:
+             fname = Samples.get(row,"Filename")
+             if fname not in filenamesInCombWig:
+-              print "error: filename '%s' listed in samples metadata not found in combined wig file" % fname; sys.exit(0)
++              print("error: filename '%s' listed in samples metadata not found in combined wig file" % fname); sys.exit(0)
+             SampleIndexes.append(row)
+             wigindexes.append(filenamesInCombWig.index(fname))
+ 
+@@ -149,7 +149,7 @@ class MultiTnSeqMethod(base.AnalysisMeth
+             fname = Samples.get(row,"Filename")
+             cond2datasets[cond].append(filenamesInData.index(fname))
+         if len(cond2datasets[cond]) == 0:
+-          print "error: no samples found in metadata for condition %s" % cond; sys.exit(0)
++          print("error: no samples found in metadata for condition %s" % cond); sys.exit(0)
+ 
+       (normed, factors) = norm_tools.normalize_data(data, method='TTR')
+       Nds,Nsites = normed.shape # transposed: rows are datasets, cols are TA sites
+@@ -196,15 +196,15 @@ class MultiTnSeqMethod(base.AnalysisMeth
+ 
+ 
+       if False: # print means for each gene for each dataset
+-        print '\t'.join(filenamesInData)
+-        print '\t'.join([Samples.get(x,"Id") for x in SampleIndexes])
++        print('\t'.join(filenamesInData))
++        print('\t'.join([Samples.get(x,"Id") for x in SampleIndexes]))
+         for (start,end,Rv,gene,strand) in genes:
+           if len(TAsites[Rv])>0: # skip genes with no TA sites
+             means = []
+             for j in range(Nds):
+               obs = normed[j,TAsites[Rv]]
+               means.append(numpy.mean(obs))
+-          print '\t'.join([Rv,gene,str(len(TAsites[Rv]))]+["%0.1f" % x for x in means])
++          print('\t'.join([Rv,gene,str(len(TAsites[Rv]))]+["%0.1f" % x for x in means]))
+         #sys.exit(0)
+ 
+ 
+@@ -344,14 +344,14 @@ class MultiTnSeqMethod(base.AnalysisMeth
+             batches[batch].append(Means[Rv][r])
+             vals.append(Means[Rv][r]) ###
+           for b in "CC1 CC2 CC3 KO".split(): vals.append(numpy.mean(batches[b]))
+-          print '\t'.join([Rv,gene]+["%0.1f" % x for x in vals]) ###
++          print('\t'.join([Rv,gene]+["%0.1f" % x for x in vals])) ###
+       ###sys.exit(0)
+ 
+ 
+ 
+       # remove batch effects (subtract batch means from mean gene counts; adjust each to global mean)
+       if self.debatch and "Batch" in Conditions.headers:
+-        print "<BR>correcting means for batch effects..."
++        print("<BR>correcting means for batch effects...")
+         for (start,end,Rv,gene,strand) in genes:
+          if Rv in Means:
+           batches = {}
+@@ -372,11 +372,11 @@ class MultiTnSeqMethod(base.AnalysisMeth
+ 
+       if False: # print gene means for each condition (with batch corrections)
+         vals = ['ORF','gene']+Conditions.getcol("Condition")
+-        print '\t'.join(vals)
++        print('\t'.join(vals))
+         for (start,end,Rv,gene,strand) in genes:
+            if Rv not in Means: continue
+            vals = [Means[Rv][r] for r in range(Conditions.nrows)]
+-           print '\t'.join([Rv,gene]+["%0.1f" % x for x in vals])
++           print('\t'.join([Rv,gene]+["%0.1f" % x for x in vals]))
+         sys.exit(0)
+ 
+       ################################
+@@ -398,11 +398,11 @@ class MultiTnSeqMethod(base.AnalysisMeth
+         lfcs[Rv] = lfcvec
+ 
+       if self.stdnorm:
+-        print "<BR>applying standard normalization to LFCs"
++        print("<BR>applying standard normalization to LFCs")
+         for i,cond in enumerate(Conditions.keys):
+-          col = [row[i] for row in lfcs.values()]
++          col = [row[i] for row in list(lfcs.values())]
+           m,s = numpy.mean(col),numpy.std(col) # consider using quantiles(col,[0,0.25,0.5,0.75,1.0])
+-          for Rv in lfcs.keys():
++          for Rv in list(lfcs.keys()):
+             lfcs[Rv][i] = (lfcs[Rv][i]-m)/s
+ 
+       file = open(self.makefname("temp_LFCs.txt", self.rundir),"w")
+@@ -415,7 +415,7 @@ class MultiTnSeqMethod(base.AnalysisMeth
+         file.write('\t'.join([str(x) for x in vals])+EOL)
+         cnt += 1
+       file.close()
+-      if cnt==0: print "error: no significantly varying genes found by ANOVA"; return
++      if cnt==0: print("error: no significantly varying genes found by ANOVA"); return
+ 
+       r_conditions_corrplot = def_r_conditions_corrplot()
+       r_make_heatmap = def_r_make_heatmap()

debian/patches/series

 skip_test_requiring_non_existing_input_data.patch
+2to3.patch

debian/rules

@@ -6,7 +6,7 @@ export LC_ALL=C.UTF-8
 include /usr/share/dpkg/default.mk
 
 %:
-	dh $@ --with python2 --buildsystem=pybuild
+	dh $@ --with python3 --buildsystem=pybuild
 
 override_dh_install:
 	dh_install

setup.py

@@ -61,6 +61,7 @@ class UploadCommand(Command):
         if not self.yes_or_no("Have you done the following? \n" +
                     "- Updated README/Documentation?\n"
                     "- Are in the master branch, and have you merged version branch into master?\n"
+                    "- Have you run the tests ('pytest tests/')?\n"
                     "- Have you updated CHANGELOG?\n"
                     "- Have you updated Transit Essentiality page?\n"
                     "- Updated version in src/pytransit/__init__.py (used to set git tag)?\n"
@@ -111,12 +112,14 @@ setup(
 
     # Choose your license
     license='GNU GPL',
-
+    python_requires='>=3.6',
     # See https://pypi.python.org/pypi?%3Aaction=list_classifiers
+
     classifiers=[
         #'Development Status :: 3 - Alpha',
         'Development Status :: 5 - Production/Stable',
-        'Programming Language :: Python :: 2.7',
+        'Programming Language :: Python',
+        'Programming Language :: Python :: 3',
         'Intended Audience :: Science/Research',
         'License :: OSI Approved :: GNU General Public License v3 (GPLv3)',
         'Operating System :: OS Independent',
@@ -144,7 +147,7 @@ setup(
     # your project is installed. For an analysis of "install_requires" vs pip's
     # requirements files see:
     # https://packaging.python.org/en/latest/requirements.html
-    install_requires=['setuptools', 'numpy~=1.15', 'scipy~=1.2', 'matplotlib~=2.2', 'pillow~=5.0', 'statsmodels~=0.9'],
+    install_requires=['setuptools', 'numpy~=1.16', 'scipy~=1.2', 'matplotlib~=3.0', 'pillow~=6.0', 'statsmodels~=0.9'],
 
     #dependency_links = [
     #	"git+https://github.com/wxWidgets/wxPython.git#egg=wxPython"

src/pytpp/__main__.py

@@ -30,8 +30,8 @@ import shutil
 import platform
 import gzip
 
-from tpp_tools import *
-from tpp_gui import *
+from pytpp.tpp_tools import *
+from pytpp.tpp_gui import *
 
 
 def run_main():
@@ -67,9 +67,9 @@ def main(*args, **kwargs):
             pass
 
     elif not args and not kwargs and not hasWx:
-        print "Please install wxPython to run in GUI Mode."
-        print "To run in Console Mode please follow these instructions:"
-        print ""
+        print("Please install wxPython to run in GUI Mode.")
+        print("To run in Console Mode please follow these instructions:")
+        print("")
         show_help()
 
     else:
@@ -85,7 +85,7 @@ def main(*args, **kwargs):
                            "window-size", "bwa-alg", "replicon-ids","primer-start-window"])
         unknown_flags = set(kwargs.keys()) - known_flags
         if unknown_flags:
-            print "error: unrecognized flags:", ", ".join(unknown_flags)
+            print("error: unrecognized flags:", ", ".join(unknown_flags))
             show_help()
             sys.exit()
 

src/pytpp/tpp_gui.py

@@ -36,7 +36,7 @@ try:
 except Exception as e:
     hasWx = False
 
-from tpp_tools import *
+from pytpp.tpp_tools import *
 
 if hasWx:
 
@@ -339,7 +339,7 @@ The Mme1 protocol generally assumes reads do NOT include the primer prefix, and
 #
 
         def OnChanged(self, str_path):
-            print "changed"
+            print("changed")
             value = os.path.basename(str_path).split('.')[0]
             if '_R1' in value or '_R2':
                 value = value.split('_')[0]
@@ -405,7 +405,7 @@ The Mme1 protocol generally assumes reads do NOT include the primer prefix, and
           if dlg.ShowModal() == wx.ID_OK:
               paths = dlg.GetPaths()
               for path in paths:
-                print "analyzing dataset:",path
+                print("analyzing dataset:",path)
                 analyze_dataset(path)
           dlg.Destroy()
           self.update_dataset_list()
@@ -452,7 +452,7 @@ The Mme1 protocol generally assumes reads do NOT include the primer prefix, and
 #
 
         def OnQuit(self, e):
-            print "Quitting TPP.  Good bye."
+            print("Quitting TPP.  Good bye.")
             self.vars.action = "quit"
             self.Close()
             return 0

src/pytpp/tpp_tools.py

@@ -266,7 +266,7 @@ def extract_staggered(infile,outfile,vars):
   if vars.window_size!=-1: message("Looking for start of Tn prefix with P,Q = %d,%d (origin = %d, window size = %d)" % (P,Q,origin,vars.window_size)) # [RJ] Outputting P,Q values and origin/window size
   else: message("Looking for start of Tn prefix within P,Q = [%d,%d]" % (P,Q))
   tot = 0
-  #print infile
+  #print(infile)
   if vars.barseq_catalog_out!=None:
     barcodes_file = vars.base+".barseq" # I could define this in vars
     catalog = open(barcodes_file,"w")
@@ -274,7 +274,7 @@ def extract_staggered(infile,outfile,vars):
     barseq2 = "CGTACGCTGCAGGTCGACGGCCGG"
     barseq1len,barseq2len = len(barseq1),len(barseq2)
   for line in open(infile):
-    #print line
+    #print(line)
     line = line.rstrip()
     if not line: continue
     if line[0]=='>': header = line; continue
@@ -313,7 +313,7 @@ def extract_staggered(infile,outfile,vars):
 
 
 def message(s):
-  #print "[tn_preprocess]",s
+  #print("[tn_preprocess]",s)
   #sys.stdout.flush()
   sys.stderr.write("[tn_preprocess] "+s+"\n")
 
@@ -338,7 +338,7 @@ def select_reads(goodreads,infile,outfile):
       header = line
       id = get_id(line)
     else:
-      if hash.has_key(id):
+      if id in hash:
         output.write(header)
         output.write(line)
   output.close()
@@ -515,11 +515,11 @@ def template_counts(ref,sam,bcfile,vars):
       else:
         pos = i+1
         h = hits[replicon_names[replicon_index]].get(pos,[])
-        f = filter(lambda x: x[0]=='F',h)
-        r = filter(lambda x: x[0]=='R',h)
+        f = list(filter(lambda x: x[0]=='F',h))
+        r = list(filter(lambda x: x[0]=='R',h))
         u = list(set(h))
-        uf = filter(lambda x: x[0]=='F',u)
-        ur = filter(lambda x: x[0]=='R',u)
+        uf = list(filter(lambda x: x[0]=='F',u))
+        ur = list(filter(lambda x: x[0]=='R',u))
         data = [pos,len(f),len(uf),len(r),len(ur),len(f)+len(r),len(uf)+len(ur)]
         sites.append(data)    
     sites_list.append(sites)
@@ -847,10 +847,10 @@ def bwa_subprocess(command, outfile):
     #process.wait()
     (pout,perr) = process.communicate()
     #for line in iter(process.stderr.readline, ''):
-    for line in perr.split('\n'): # returned by communicate()
-        if "Permission denied" in line:
+    for line in perr.split(b'\n'): # returned by communicate()
+        if b"Permission denied" in line:
             raise IOError("Error: BWA encountered a permissions error: \n\n%s" % line)
-        if "invalid option" in line:
+        if b"invalid option" in line:
             raise ValueError("Error: Unrecognized flag for BWA: %s" % (line.split()[-1]))
         sys.stderr.write("%s\n" % line.strip())
 
@@ -935,7 +935,7 @@ def get_read_length(filename):
    i = 0
    for line in fil:
       if i == 1:
-         #print "reads1 line: " + line
+         #print("reads1 line: " + line)
          return len(line.strip())
       i+=1
 
@@ -1006,9 +1006,9 @@ def create_barseq_catalog(vars, replicon_index):
   goodbc = {}
   for bc,sites2 in mapsto.items(): 
     pop = popularity(sites2) # make a table of locations at which the barcode appears
-    #print bc,pop
+    #print(bc,pop)
     if len(pop)==1: goodbc[bc] = 1
-  #for x in sorted(sites.items()): print x[0],genome[x[0]-1:x[0]+1],popularity(x[1])
+  #for x in sorted(sites.items()): print(x[0],genome[x[0]-1:x[0]+1],popularity(x[1]))
 
   file = open(vars.barseq_catalog_out[replicon_index],"w")  
   file.write("# Barseq (stats are at the bottom): reads = %s, ref = %s\n" % (vars.fq1,vars.ref))
@@ -1070,7 +1070,7 @@ def generate_output(vars):
     cur_tc = sum(cur_tcounts)
     cur_ratio = cur_rc/float(cur_tc) if (cur_rc != 0 and cur_tc !=0) else 0
     cur_ta_sites = len(cur_rcounts)
-    cur_tas_hit = len(filter(lambda x: x>0,cur_rcounts))
+    cur_tas_hit = len(list(filter(lambda x: x>0,cur_rcounts)))
     cur_density = cur_tas_hit/float(cur_ta_sites) if cur_tas_hit != 0 else 0
     counts[replicon_index].sort(key=lambda x: x[-1])
     cur_max_tc = counts[replicon_index][-1][6]
@@ -1202,17 +1202,17 @@ def generate_output(vars):
   infile = open(vars.stats)
   for line in infile:
       if '#' in line:
-          print line.rstrip()
+          print(line.rstrip())
   infile.close()
 
 #############################################################################
 
 def error(s):
-  print "error:",s
+  print("error:",s)
   sys.exit(0)
 
 def warning(s):
-  print "warning:",s
+  print("warning:",s)
 
 
 
@@ -1308,7 +1308,7 @@ def verify_inputs(vars):
         error('cannot find BWA executable. Please include the full executable name as well as its directory.')
 
 def initialize_globals(vars, args=[], kwargs={}):
-    vars.fq1,vars.fq2,vars.ref,vars.bwa,vars.bwa_alg,vars.replicon_ids,vars.base,vars.maxreads = "","","","","","","",""
+    vars.fq1,vars.fq2,vars.ref,vars.bwa,vars.bwa_alg,vars.replicon_ids,vars.base,vars.maxreads = "","","","","","","",-1
     vars.mm1 = 1 # mismatches allowed in Tn prefix AND adapter prefix on read2
     vars.transposon = 'Himar1'
     vars.protocol = "Sassetti"
@@ -1433,20 +1433,20 @@ def save_config(vars):
   f.close()
 
 def show_help():
-  #print 'usage: python PATH/src/tpp.py -bwa <EXECUTABLE_WITH_PATH> -ref <fasta-file|comma_separated_list> -reads1 <FASTQ_OR_FASTA_FILE> [-reads2 <FASTQ_OR_FASTA_FILE>] -output <BASE_FILENAME> [-maxreads <N>] [-mismatches <N>] [-flags "<STRING>"] [-tn5|-himar1] [-primer <seq>] [-primer-start-window INT,INT] [-window-size INT] [-barseq_catalog_in|_out <file>] [-replicon-ids <comma_separated_list_of_names>]'
-
-  print 'usage: python PATH/src/tpp.py -bwa <EXECUTABLE_WITH_PATH> -ref <fasta-file|comma_separated_list> -reads1 <FASTQ_OR_FASTA_FILE> [-reads2 <FASTQ_OR_FASTA_FILE>] -output <BASE_FILENAME> [OPTIONAL ARGS]'
-  print '  OPTIONAL ARGS:'
-  print '    -protocol [Sassetti|Tn5|Mme1] # which sample prep protocol was used?; sassetti protocol is the default; this sets the default transposon and primer sequence'
-  print '    -primer <seq>      # prefix of reads corresponding to end of transposon at junction with genomic sequence; can override default seq' 
-  print '    -maxreads <INT>'
-  print '    -mismatches <INT>  # when searching for constant regions in reads 1 and 2; default is 1'
-  print '    -flags "<STRING>"  # args to pass to BWA'
-  print '    -primer-start-window INT,INT # position in read to search for start of primer; default is [0,20]'
-  print '    -window-size INT   # automatic method to set window'
-  print '    -barseq_catalog_in|-barseq_catalog_out <file>'
-  print '    -replicon-ids <comma_separated_list_of_names> # if multiple replicons/genomes/contigs/sequences were provided in -ref, give them names.'
-  print '                                                  # Enter \'auto\' for autogenerated ids.'
+  #print('usage: python PATH/src/tpp.py -bwa <EXECUTABLE_WITH_PATH> -ref <fasta-file|comma_separated_list> -reads1 <FASTQ_OR_FASTA_FILE> [-reads2 <FASTQ_OR_FASTA_FILE>] -output <BASE_FILENAME> [-maxreads <N>] [-mismatches <N>] [-flags "<STRING>"] [-tn5|-himar1] [-primer <seq>] [-primer-start-window INT,INT] [-window-size INT] [-barseq_catalog_in|_out <file>] [-replicon-ids <comma_separated_list_of_names>]')
+
+  print('usage: python PATH/src/tpp.py -bwa <EXECUTABLE_WITH_PATH> -ref <fasta-file|comma_separated_list> -reads1 <FASTQ_OR_FASTA_FILE> [-reads2 <FASTQ_OR_FASTA_FILE>] -output <BASE_FILENAME> [OPTIONAL ARGS]')
+  print('  OPTIONAL ARGS:')
+  print('    -protocol [Sassetti|Tn5|Mme1] # which sample prep protocol was used?; sassetti protocol is the default; this sets the default transposon and primer sequence')
+  print('    -primer <seq>      # prefix of reads corresponding to end of transposon at junction with genomic sequence; can override default seq' )
+  print('    -maxreads <INT>')
+  print('    -mismatches <INT>  # when searching for constant regions in reads 1 and 2; default is 1')
+  print('    -flags "<STRING>"  # args to pass to BWA')
+  print('    -primer-start-window INT,INT # position in read to search for start of primer; default is [0,20]')
+  print('    -window-size INT   # automatic method to set window')
+  print('    -barseq_catalog_in|-barseq_catalog_out <file>')
+  print('    -replicon-ids <comma_separated_list_of_names> # if multiple replicons/genomes/contigs/sequences were provided in -ref, give them names.')
+  print('                                                  # Enter \'auto\' for autogenerated ids.')
 
 class Globals:
   pass

src/pytransit/__init__.py

@@ -2,6 +2,6 @@
 __all__ = ["transit_tools", "tnseq_tools", "norm_tools", "stat_tools"]
 
 
-__version__ = "v2.5.2"
+__version__ = "v3.0.0"
 prefix = "[TRANSIT]"
 

src/pytransit/__main__.py

@@ -18,7 +18,7 @@ if hasWx:
 
 
 import pytransit
-import pytransit.transit_tools as transit_tools
+from pytransit import transit_tools
 import pytransit.analysis
 import pytransit.export
 import pytransit.convert
@@ -50,20 +50,20 @@ def main(*args, **kwargs):
         kwargs.pop("-debug")
 
     if (not args and ('v' in kwargs or '-version' in kwargs)):
-        print "Version: {0}".format(pytransit.__version__)
+        print("Version: {0}".format(pytransit.__version__))
         sys.exit(0)
     if (not args and ('h' in kwargs or '-help' in kwargs)):
-        print "For commandline mode, please use one of the known methods (or see documentation to add a new one):"
+        print("For commandline mode, please use one of the known methods (or see documentation to add a new one):")
         print("Analysis methods: ")
         for m in all_methods:
             ## TODO :: Move normalize to separate subcommand?
             if (m == "normalize"): continue
-            print "\t - %s" % m
+            print("\t - %s" % m)
         print("Other functions: ")
         print("\t - normalize")
         print("\t - convert")
         print("\t - export")
-        print "Usage: python %s <method>" % sys.argv[0]
+        print("Usage: python %s <method>" % sys.argv[0])
         sys.exit(0)
 
     # Check if running in GUI Mode
@@ -87,13 +87,13 @@ def main(*args, **kwargs):
 
     # Tried GUI mode but has no wxPython
     elif not (args or kwargs) and not hasWx:
-        print "Please install wxPython to run in GUI Mode."
-        print "To run in Console Mode please follow these instructions:"
-        print ""
-        print "Usage: python %s <method>" % sys.argv[0]
-        print "List of known methods:"
+        print("Please install wxPython to run in GUI Mode.")
+        print("To run in Console Mode please follow these instructions:")
+        print("")
+        print("Usage: python %s <method>" % sys.argv[0])
+        print("List of known methods:")
         for m in methods:
-            print "\t - %s" % m
+            print("\t - %s" % m)
     # Running in Console mode
     else:
         import matplotlib
@@ -106,11 +106,11 @@ def main(*args, **kwargs):
                     export_method_name = args[1]
 
                 if export_method_name not in export_methods:
-                    print "Error: Need to specify the export method."
-                    print "Please use one of the known methods (or see documentation to add a new one):"
+                    print("Error: Need to specify the export method.")
+                    print("Please use one of the known methods (or see documentation to add a new one):")
                     for m in export_methods:
-                        print "\t - %s" % m
-                    print "Usage: python %s export <method>" % sys.argv[0]
+                        print("\t - %s" % m)
+                    print("Usage: python %s export <method>" % sys.argv[0])
                 else:
                     methodobj = export_methods[export_method_name].method.fromconsole()
                     methodobj.Run()
@@ -120,20 +120,20 @@ def main(*args, **kwargs):
                     convert_method_name = args[1]
 
                 if convert_method_name not in convert_methods:
-                    print "Error: Need to specify the convert method."
-                    print "Please use one of the known methods (or see documentation to add a new one):"
+                    print("Error: Need to specify the convert method.")
+                    print("Please use one of the known methods (or see documentation to add a new one):")
                     for m in convert_methods:
-                        print "\t - %s" % m
-                    print "Usage: python %s convert <method>" % sys.argv[0]
+                        print("\t - %s" % m)
+                    print("Usage: python %s convert <method>" % sys.argv[0])
                 else:
                     methodobj = convert_methods[convert_method_name].method.fromconsole()
                     methodobj.Run()
             else:
-                print "Error: The '%s' method is unknown." % method_name
-                print "Please use one of the known methods (or see documentation to add a new one):"
+                print("Error: The '%s' method is unknown." % method_name)
+                print("Please use one of the known methods (or see documentation to add a new one):")
                 for m in all_methods:
-                    print "\t - %s" % m
-                print "Usage: python %s <method>" % sys.argv[0]
+                    print("\t - %s" % m)
+                print("Usage: python %s <method>" % sys.argv[0])
         else:
 
             methodobj = all_methods[method_name].method.fromconsole()

src/pytransit/analysis/__init__.py

@@ -5,24 +5,23 @@ import glob
 modules = glob.glob(dirname(__file__)+"/*.py")
 __all__ = [ basename(f)[:-3] for f in modules if isfile(f)]
 
-import base
+from pytransit.analysis import base
 
-import gumbel
-import example
-import tn5gaps
-import binomial
-import griffin
-import resampling
-import hmm
-import rankproduct
-import gi
-import utest
-import normalize
-import pathway_enrichment #08/22/2018 by Ivan
-import anova
-import zinb
-import tnseq_stats
-import winsorize
+from pytransit.analysis import gumbel
+from pytransit.analysis import example
+from pytransit.analysis import tn5gaps
+from pytransit.analysis import binomial
+from pytransit.analysis import griffin
+from pytransit.analysis import resampling
+from pytransit.analysis import hmm
+from pytransit.analysis import rankproduct
+from pytransit.analysis import gi
+from pytransit.analysis import utest
+from pytransit.analysis import normalize
+from pytransit.analysis import pathway_enrichment
+from pytransit.analysis import anova
+from pytransit.analysis import zinb
+from pytransit.analysis import tnseq_stats
 
 methods = {}
 methods["example"] = example.ExampleAnalysis()
@@ -43,10 +42,10 @@ methods["zinb"] = zinb.ZinbAnalysis()
 methods["normalize"] = normalize.Normalize()
 methods["pathway_enrichment"]=pathway_enrichment.GSEAAnalysis()
 methods["tnseq_stats"]=tnseq_stats.TnseqStats()
-methods["winsorize"] = winsorize.Winsorize()
 
 # EXPORT METHODS
-import norm
+from pytransit.analysis import norm
+
 export_methods = {}
 export_methods["norm"] = norm.NormAnalysis()
 

src/pytransit/analysis/anova.py

@@ -6,7 +6,7 @@ import time
 import sys
 import collections
 
-import base
+from pytransit.analysis import base
 import pytransit
 import pytransit.transit_tools as transit_tools
 import pytransit.tnseq_tools as tnseq_tools
@@ -52,8 +52,8 @@ class AnovaMethod(base.MultiConditionMethod):
         normalization = kwargs.get("n", "TTR")
         NTerminus = float(kwargs.get("iN", 0.0))
         CTerminus = float(kwargs.get("iC", 0.0))
-        ignored_conditions = filter(None, kwargs.get("-ignore-conditions", "").split(","))
-        included_conditions = filter(None, kwargs.get("-include-conditions", "").split(","))
+        ignored_conditions = list(filter(None, kwargs.get("-ignore-conditions", "").split(",")))
+        included_conditions = list(filter(None, kwargs.get("-include-conditions", "").split(",")))
 
         if len(included_conditions) > 0 and len(ignored_conditions) > 0:
             print(self.transit_error("Cannot use both include-conditions and ignore-conditions flags"))
@@ -136,7 +136,7 @@ class AnovaMethod(base.MultiConditionMethod):
                 status.append("TA sites <= 1")
                 pvals.append(1)
             else:
-                countSum, countsVec = self.group_by_condition(map(lambda wigData: wigData[RvSiteindexesMap[Rv]], data), conditions)
+                countSum, countsVec = self.group_by_condition(list(map(lambda wigData: wigData[RvSiteindexesMap[Rv]], data)), conditions)
 
                 if (countSum == 0):
                     pval = 1

src/pytransit/analysis/base.py

@@ -124,8 +124,8 @@ class TransitFile (TransitGUIBase):
             if line.startswith("#"): continue
             tmp = line.split("\t")
             tmp[-1] = tmp[-1].strip()
-            #print colnames
-            #print  len(colnames), len(tmp)
+            #print(colnames)
+            #print( len(colnames), len(tmp))
             try:
                 rowdict = dict([(colnames[i], tmp[i]) for i in range(len(colnames))])
             except Exception as e:
@@ -153,15 +153,15 @@ class TransitFile (TransitGUIBase):
 
     def displayInTrackView(self, displayFrame, event):
 
-        #print "Self:", self
-        #print "Frame:", displayFrame
-        #print "Event:", event
-        #print "Frame parent:", displayFrame.parent
+        #print("Self:", self)
+        #print("Frame:", displayFrame)
+        #print("Event:", event)
+        #print("Frame parent:", displayFrame.parent)
         try:
             gene = displayFrame.grid.GetCellValue(displayFrame.row, 0)
             displayFrame.parent.allViewFunc(displayFrame, gene)
         except Exception as e:
-            print file_prefix, "Error occurred: %s" % e
+            print(file_prefix, "Error occurred: %s" % e)
 
 #
 
@@ -318,23 +318,23 @@ class AnalysisMethod:
         try:
             return self.fromargs(sys.argv[2:])
         except InvalidArgumentException as e:
-            print "Error: %s" % str(e)
-            print self.usage_string()
+            print("Error: %s" % str(e))
+            print(self.usage_string())
         except IndexError as e:
-            print "Error: %s" % str(e)
-            print self.usage_string()
+            print("Error: %s" % str(e))
+            print(self.usage_string())
         except TypeError as e:
-            print "Error: %s" % str(e)
+            print("Error: %s" % str(e))
             traceback.print_exc()
-            print self.usage_string()
+            print(self.usage_string())
         except ValueError as e:
-            print "Error: %s" % str(e)
+            print("Error: %s" % str(e))
             traceback.print_exc()
-            print self.usage_string()
+            print(self.usage_string())
         except Exception as e:
-            print "Error: %s" % str(e)
+            print("Error: %s" % str(e))
             traceback.print_exc()
-            print self.usage_string()
+            print(self.usage_string())
         sys.exit()
 
 #
@@ -356,7 +356,7 @@ class AnalysisMethod:
         #TODO: write docstring
         members = sorted([attr for attr in dir(self) if not callable(getattr(self,attr)) and not attr.startswith("__")])
         for m in members:
-            print "%s = %s" % (m, getattr(self, m))
+            print("%s = %s" % (m, getattr(self, m)))
 
 #
 

src/pytransit/analysis/binomial.py

@@ -22,7 +22,7 @@ import numpy
 import scipy.stats
 import datetime
 
-import base
+from pytransit.analysis import base
 import pytransit.transit_tools as transit_tools
 import pytransit.tnseq_tools as tnseq_tools
 import pytransit.norm_tools as norm_tools
@@ -346,7 +346,7 @@ class BinomialMethod(base.SingleConditionMethod):
             elif K[g]/float(N[g]) == 1: theta[g][0] = 0.001
             else: theta[g][0] = K[g]/float(N[g])
 
-            #print g, ORF[g], K[g], N[g], theta[g][0]
+            #print(g, ORF[g], K[g], N[g], theta[g][0])
             Z[g][0] = scipy.stats.bernoulli.rvs(1-theta[g][0])
 
 
@@ -439,9 +439,9 @@ class BinomialMethod(base.SingleConditionMethod):
                 Z[:,i] = scipy.stats.bernoulli.rvs(p1)
             except:
                 inan = numpy.isnan(p1)
-                print >> sys.stderr, "K=\t", K[inan]
-                print >> sys.stderr, "N=\t", N[inan]
-                print >> sys.stderr, "theta=", theta[inan,i]
+                sys.stderr.write("K=\t", K[inan],"\n")
+                sys.stderr.write("N=\t", N[inan],"\n")
+                sys.stderr.write("theta=", theta[inan,i],'\n')
                 sys.exit()
             pz1[i] = p1[0]
 
@@ -546,8 +546,8 @@ if __name__ == "__main__":
     G.console_message("Printing the member variables:")   
     G.print_members()
 
-    print ""
-    print "Running:"
+    print("")
+    print("Running:")
 
     G.Run()
 

src/pytransit/analysis/example.py

@@ -23,7 +23,7 @@ import numpy
 import scipy.stats
 import datetime
 
-import base
+from pytransit.analysis import base
 import pytransit.transit_tools as transit_tools
 import pytransit.tnseq_tools as tnseq_tools
 import pytransit.norm_tools as norm_tools
@@ -236,17 +236,17 @@ if __name__ == "__main__":
 
     (args, kwargs) = transit_tools.cleanargs(sys.argv[1:])
 
-    print "ARGS:", args
-    print "KWARGS:", kwargs
+    print("ARGS:", args)
+    print("KWARGS:", kwargs)
 
     G = Example.fromargs(sys.argv[1:])
 
-    print G
+    print(G)
     G.console_message("Printing the member variables:")   
     G.print_members()
 
-    print ""
-    print "Running:"
+    print("")
+    print("Running:")
 
     G.Run()