Merge pull request #4 from morrislab/py3

Python 3 compatible

.travis.yml

@@ -0,0 +1,9 @@
+language: python
+python:
+    - "2.7"
+    - "3.5"
+    - "3.6"
+install:
+    travis_retry python setup.py install
+script:
+    travis_retry python setup.py test

README.md

@@ -1,3 +1,7 @@
+[![Build Status](https://travis-ci.org/morrislab/rnascan.svg?branch=master)](https://travis-ci.org/morrislab/rnascan)
+![Version](https://img.shields.io/badge/version-0.10.2-brightgreen.svg)
+[![GitHub license](https://img.shields.io/github/license/morrislab/rnascan.svg)](https://github.com/morrislab/rnascan/blob/master/LICENSE)
+
 # rnascan
 
 rnascan is a (mostly) Python suite to scan RNA sequences and secondary structures with sequence and secondary structure PFMs. Secondary structure is represented as weights in different secondary structure contexts, similar to how a PFM represents weights of different nucleotides or amino acids. This allows representation and use of secondary structures in a way that is similar to how PFMs are used to scan nucleotide sequences, and also allows for some flexibility in the structure, as you might find in the boltzmann distribution of secondary structures.
@@ -44,7 +48,7 @@ g++ -o ~/bin/parse_secondary_structure scripts/parse_secondary_structure.cpp
 
 ### 4. Install `rnascan` Python components
 
-This package was written for Python 2.7.x or later (_not compatible with Python 3 yet_). To install the package, run the following:
+This package requires Python 2.7+ or Python 3.5+. To install the package, run the following:
 
 ```
 python setup.py install
@@ -80,7 +84,7 @@ Here are some example commands using minimal options:
 
 ```
 # To run a test sequence
-rnascan -p pfm_seq.txt -s AGTTCCGGTCCGGCAGAGATCGCG > hits.tab
+rnascan -p pfm_seq.txt -t AGTTCCGGTCCGGCAGAGATCGCG > hits.tab
 
 # Sequence-only (use -p)
 rnascan -p pfm_seq.txt sequences.fasta > hits.tab

rnascan/BioAddons/motifs/matrix.py

@@ -6,12 +6,13 @@
 #
 
 
-
 from Bio.motifs import matrix
 from Bio.Alphabet import NucleotideAlphabet
 import platform
 
-class ExtendedPositionSpecificScoringMatrix(matrix.PositionSpecificScoringMatrix):
+
+class ExtendedPositionSpecificScoringMatrix(
+        matrix.PositionSpecificScoringMatrix):
     """This new class inherits Bio.motifs.matrix.PositionSpecificScoringMatrix.
     It has been modified to support any kind of Alphabet. This allows us to
     perform motif scans on RNA sequence as well as RNA secondary structure.
@@ -45,6 +46,7 @@ def _py_calculate(self, sequence, m, n):
     # Fall back to the slower Python implementation if Jython or IronPython.
     try:
         from . import _pwm
+
         def _calculate(self, sequence, m, n):
 
             # Only RNA and DNA is supported right now. If sequence is
@@ -54,7 +56,7 @@ def _calculate(self, sequence, m, n):
 
             letters = ''.join(sorted(self.alphabet.letters))
             logodds = [[self[letter][i] for letter in letters]
-                            for i in range(m)]
+                       for i in range(m)]
             return self._pwm.calculate(sequence, logodds)
     except ImportError:
         if platform.python_implementation() == 'CPython':
@@ -63,7 +65,6 @@ def _calculate(self, sequence, m, n):
             def _calculate(self, sequence, m, n):
                 return self._py_calculate(sequence, m, n)
 
-
     def calculate(self, sequence):
 
         # TODO - Force uppercase here and optimise switch statement in C

rnascan/average_structure.py

@@ -20,7 +20,7 @@
 from Bio import SeqIO
 from Bio.SeqRecord import SeqRecord
 from Bio.Seq import Seq
-from pfmutil import norm_pfm
+from .pfmutil import norm_pfm
 import subprocess
 import numpy as np
 
@@ -44,7 +44,7 @@ def struct_pfm_from_aligned(sequences):
 def get_structure_probability_matrix_for_sequence(id,seq,frag_length,overlap):
     aligned_annotated_sequences = []
 
-    for i in xrange(-frag_length/2,len(seq)-frag_length/2,frag_length-overlap):
+    for i in range(-frag_length/2,len(seq)-frag_length/2,frag_length-overlap):
         temphandle = tempfile.NamedTemporaryFile(delete=False,mode='r+b') # for centroid structure
         temphandle2 = tempfile.NamedTemporaryFile(delete=False,mode='r+b') # for output of structure parser
 
@@ -108,7 +108,7 @@ def get_structure_probability_matrix_from_probabilities(id,seq,frag_length):
 
     probabilities = {}
 
-    for alph,p in programs.iteritems():
+    for alph,p in programs.items():
         args = [p] + plfold_args
         plfold_proc = subprocess.Popen(args, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=None)
         #plfold_output = plfold_proc.communicate(input_record.format("fasta"))[0]

rnascan/pfmutil.py

@@ -45,7 +45,7 @@ def read_pfm(pfmfile):
     pfm = {}
     with open(pfmfile) as f:
         reader = csv.reader(f, delimiter='\t')
-        headerline = reader.next()
+        headerline = next(reader)
         alphabet = headerline[1:]
         for base in alphabet:
             pfm[base] = []
@@ -244,9 +244,9 @@ def reduce_pfm_alphabet(pfm):
 
     pfm = read_pfm(file)
 
-    print(format_pfm(pfm))
+    print((format_pfm(pfm)))
 
     reduced_pfm = reduce_pfm_alphabet(pfm)    
 
-    print(format_pfm(reduced_pfm))
+    print((format_pfm(reduced_pfm)))