Merge branch 'master' of https://github.com/cgat-developers/cgat-apps

cgat/SequenceProperties.py

@@ -46,8 +46,6 @@
 
 from cgat import Genomics as Genomics
 
-import Bio.Alphabet.IUPAC
-
 
 class SequenceProperties(object):
     """Base class.
@@ -223,7 +221,7 @@ def __init__(self, reference_usage=[]):
         self.mCountsOthers = 0
         # counts of nucleotides
         self.mCountsNA = {}
-        self.mAlphabet = Bio.Alphabet.IUPAC.unambiguous_dna.letters + "N"
+        self.mAlphabet = "GATCN"
         for x in self.mAlphabet:
             self.mCountsNA[x] = 0
 
@@ -313,7 +311,7 @@ def __init__(self, reference_usage=[]):
         SequenceProperties.__init__(self)
         self.mCountsDinuc = {}
         self.mCountsOthers = 0
-        self.mAlphabet = Bio.Alphabet.IUPAC.unambiguous_dna.letters
+        self.mAlphabet = "GATC"
         for dinucleotide in itertools.product(self.mAlphabet, repeat=2):
             self.mCountsDinuc["".join(dinucleotide)] = 0
 
@@ -555,7 +553,7 @@ def __init__(self):
             xx = []
             for y in range(5):
                 yy = {}
-                for z in Bio.Alphabet.IUPAC.extended_dna.letters:
+                for z in "GATCBDSW":
                     yy[z] = 0
                 xx.append(yy)
             self.mCountsDegeneracy.append(xx)
@@ -567,7 +565,7 @@ def addProperties(self, other):
 
         for x in (0, 1, 2):
             for y in range(5):
-                for z in Bio.Alphabet.IUPAC.extended_dna.letters:
+                for z in "GATCBDSW":
                     self.mCountsDegeneracy[x][y][
                         z] += other.mCountsDegeneracy[x][y][z]
 
@@ -603,7 +601,7 @@ def loadSequence(self, sequence, seqtype="na"):
             xx = []
             for y in range(5):
                 yy = {}
-                for z in Bio.Alphabet.IUPAC.extended_dna.letters:
+                for z in "GATCBDSW":
                     yy[z] = 0
                 xx.append(yy)
             self.mCountsDegeneracy.append(xx)
@@ -759,7 +757,7 @@ def __init__(self, reference_usage=[]):
 
         # counts of amino acids
         self.mCountsAA = {}
-        for x in Bio.Alphabet.IUPAC.extended_protein.letters:
+        for x in "ACDEFGHIKLMNPQRSTVWYBXZJUO":
             self.mCountsAA[x] = 0
 
     def addProperties(self, other):
@@ -781,7 +779,7 @@ def loadSequence(self, sequence, seqtype="na"):
         # counts of amino acids
         self.mCountsAA = {}
 
-        for x in Bio.Alphabet.IUPAC.extended_protein.letters:
+        for x in "ACDEFGHIKLMNPQRSTVWYBXZJUO":
             self.mCountsAA[x] = 0
 
         for codon in (sequence[x:x + 3] for x in range(0, len(sequence), 3)):
@@ -792,19 +790,19 @@ def getFields(self):
 
         fields = SequenceProperties.getFields(self)
         t = 0
-        for x in Bio.Alphabet.IUPAC.extended_protein.letters:
+        for x in "ACDEFGHIKLMNPQRSTVWYBXZJUO":
             fields.append("%i" % self.mCountsAA[x])
             t += self.mCountsAA[x]
-        for x in Bio.Alphabet.IUPAC.extended_protein.letters:
+        for x in "ACDEFGHIKLMNPQRSTVWYBXZJUO":
             fields.append("%f" % (float(self.mCountsAA[x]) / t))
         return fields
 
     def getHeaders(self):
         '''Return list of data headers'''
         headers = SequenceProperties.getHeaders(self)
-        for x in Bio.Alphabet.IUPAC.extended_protein.letters:
+        for x in "ACDEFGHIKLMNPQRSTVWYBXZJUO":
             headers.append("n%s" % x)
-        for x in Bio.Alphabet.IUPAC.extended_protein.letters:
+        for x in "ACDEFGHIKLMNPQRSTVWYBXZJUO":
             headers.append("p%s" % x)
         return headers
 
@@ -824,7 +822,7 @@ def __init__(self, reference_usage=[]):
 
         # counts of amino acids
         self.mCountsAA = {}
-        for x in Bio.Alphabet.IUPAC.extended_protein.letters:
+        for x in "ACDEFGHIKLMNPQRSTVWYBXZJUO":
             self.mCountsAA[x] = 0
         self.mOtherCounts = 0
 
@@ -840,7 +838,7 @@ def loadSequence(self, sequence, seqtype="na"):
         SequenceProperties.loadSequence(self, sequence, seqtype)
 
         # set to zero
-        for x in Bio.Alphabet.IUPAC.extended_protein.letters:
+        for x in "ACDEFGHIKLMNPQRSTVWYBXZJUO":
             self.mCountsAA[x] = 0
         self.mOtherCounts = 0
 
@@ -858,25 +856,25 @@ def getFields(self):
 
         t = 0
 
-        for x in Bio.Alphabet.IUPAC.extended_protein.letters:
+        for x in "ACDEFGHIKLMNPQRSTVWYBXZJUO":
             fields.append("%i" % self.mCountsAA[x])
             t += self.mCountsAA[x]
 
         if t > 0:
-            for x in Bio.Alphabet.IUPAC.extended_protein.letters:
+            for x in "ACDEFGHIKLMNPQRSTVWYBXZJUO":
                 fields.append("%f" % (float(self.mCountsAA[x]) / t))
         else:
-            for x in Bio.Alphabet.IUPAC.extended_protein.letters:
+            for x in "ACDEFGHIKLMNPQRSTVWYBXZJUO":
                 fields.append("0")
 
         return fields
 
     def getHeaders(self):
 
         fields = SequenceProperties.getHeaders(self)
-        for x in Bio.Alphabet.IUPAC.extended_protein.letters:
+        for x in "ACDEFGHIKLMNPQRSTVWYBXZJUO":
             fields.append("n%s" % x)
-        for x in Bio.Alphabet.IUPAC.extended_protein.letters:
+        for x in "ACDEFGHIKLMNPQRSTVWYBXZJUO":
             fields.append("p%s" % x)
 
         return fields

cgat/tools/bed2bed.py

@@ -503,6 +503,8 @@ def main(argv=sys.argv):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     # IMS: new method: extend intervals by set amount
     parser.add_argument("-m", "--method", dest="methods", type=str,
                         action="append",

cgat/tools/bed2fasta.py

@@ -56,6 +56,8 @@ def main(argv=None):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument("-g", "--genome-file", dest="genome_file", type=str,
                         help="filename with genomic sequence to retrieve "
                         "sequences from.")

cgat/tools/bed2gff.py

@@ -69,6 +69,8 @@ def main(argv=sys.argv):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument("-a", "--as-gtf", dest="as_gtf", action="store_true",
                         help="output as gtf.")
 

cgat/tools/bed2stats.py

@@ -113,6 +113,8 @@ def main(argv=None):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument(
         "-g", "--genome-file", dest="genome_file", type=str,
         help="filename with genome.")

cgat/tools/bed2table.py

@@ -519,6 +519,8 @@ def main(argv=None):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument("-g", "--genome-file", dest="genome_file", type=str,
                         help="filename with genome.")
 

cgat/tools/csv_cut.py

@@ -69,6 +69,8 @@ def main(argv=None):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument("-r", "--remove", dest="remove", action="store_true",
                         help="remove specified columns, keep all others.")
 

cgat/tools/data2histogram.py

@@ -40,6 +40,8 @@ def main(argv=None):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument("-r", "--range", dest="range", type=str,
                         help="range to calculate histogram for.")
     parser.add_argument("-b", "--bin-size", dest="bin_size", type=str,

cgat/tools/gff2bed.py

@@ -103,6 +103,8 @@ def main(argv=sys.argv):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument("--is-gtf", dest="is_gtf", action="store_true",
                         help="input file is in gtf format")
 

cgat/tools/gff2fasta.py

@@ -139,6 +139,8 @@ def main(argv=None):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument("--is-gtf", dest="is_gtf", action="store_true",
                         help="input is gtf instead of gff.")
 

cgat/tools/gff2psl.py

@@ -58,6 +58,8 @@ def main(argv=None):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument("--is-gtf", dest="is_gtf", action="store_true",
                         help="input is gtf.")
 

cgat/tools/gff32gtf.py

@@ -263,6 +263,8 @@ def main(argv=None):
     # setup command line parser
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument("-m", "--method", dest="method", type=str, action="store",
                         choices=("hierarchy", "set-field", "set-pattern", "set-none"),
                         help="Method to use for conversion")

cgat/tools/gtf2table.py

@@ -473,6 +473,8 @@ def main(argv=None):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument("-g", "--genome-file", dest="genome_file", type=str,
                         help="filename with genome.")
 

cgat/tools/randomize_lines.py

@@ -38,6 +38,8 @@ def main(argv=None):
     # setup command line parser
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument("-k", "--keep-header", dest="keep_header", type=int,
                         help="randomize, but keep header in place ")
 

cgat/tools/split_gff.py

@@ -125,6 +125,8 @@ def main(argv=None):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument(
         "-i", "--min-chunk-size", dest="min_chunk_size", type=int,
         help="minimum chunk size.")

cgat/tools/table2stats.py

@@ -50,6 +50,8 @@ def main(argv=None):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument(
         "-d", "--delimiter", dest="delimiter", type=str,
         help="delimiter to separate columns ")

cgat/tools/tables2table.py

@@ -108,6 +108,8 @@ def main(argv=sys.argv):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument("-t", "--no-titles",
                         dest="input_has_titles",
                         action="store_false",

cgat/tools/transfac2transfac.py

@@ -45,6 +45,8 @@ def main(argv=None):
     # setup command line parser
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument(
         "-f", "--filter-prefix", dest="filter_prefix", default=None,
         help="ID prefix to filter on, eg. V for vertebrates")

cgat/tools/vcf2tsv.py

@@ -264,6 +264,8 @@ def main(argv=None):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument(
         "-s", "--sample-size", dest="sample_size", type=float,
         help="sample size. If less than 0, take a proportion of the chromosome size. "

cgat/tools/vcf_compare_phase.py

@@ -14,6 +14,8 @@ def main(argv=sys.argv):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument(
         "-i", "--input-vcf", dest="input_vcf_file", type=str,
         help="input vcf file")

cgat/tools/vcf_stats.py

@@ -99,6 +99,8 @@ def main(argv=sys.argv):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument(
         "-i", "--input-vcf", dest="input_vcf_file", type=str,
         help="input vcf file")

cgat/tools/vcf_vs_vcf.py

@@ -64,6 +64,8 @@ def main(argv=None):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument(
         "--regex-filename", dest="regex_filename", type=str,
         help="extract column name from filename via regular expression "

cgat/tools/wig2bed.py

@@ -112,6 +112,8 @@ def main(argv=sys.argv):
 
     parser = E.ArgumentParser(description=__doc__)
 
+    parser.add_argument("--version", action='version', version="1.0")
+
     parser.add_argument("-m", "--method", dest="methods", type=str,
                         action="append",
                         choices=("threshold", "stddev-above-mean",

conda/environments/cgat-apps.yml

@@ -13,44 +13,34 @@ dependencies:
 # python dependencies
 - python
 - alignlib-lite
-- biopython<=1.77
+- biopython
 - cython
-- cgatcore
 - jinja2
+- cgatcore
 - matplotlib
 - nose
 - numpy
 - pandas
 - pep8
 - pybedtools
 - pybigwig
-- pysam=0.15.2
-- python-lzo
+- pysam
 - pyyaml
 - pytest<=5.4.3
 - quicksect
 - rdflib
 - scikit-learn
 - scipy==1.5.3
-- seaborn
 - setuptools
 - six
 - sortedcontainers
-# R dependencies
-# Misc dependencies
-# WARNING: gdc-client is Py2 only. Please install it on a separate conda env
 - bedtools
-- coreutils
 - grep
 - htslib
-- libpng
 - samtools
-- sra-tools
 - tar
 - ucsc-bedgraphtobigwig
 - ucsc-wigtobigwig
 # does not exist on OSX
-# - util-linux
 - wget
 - zlib
-- nomkl