Updated to be python3 compatible

Dockerfile

@@ -12,7 +12,9 @@ RUN apt-get  --allow-releaseinfo-change update -t oldoldstable && apt-get instal
     mariadb-server \
     mariadb-client \
     wget \
-    zlib1g-dev
+    zlib1g-dev \
+    procps \
+    && rm -rf /var/lib/apt/lists/*
 
 RUN conda install -c daler \
     pip \
@@ -24,14 +26,14 @@ RUN conda install -c daler \
     pandas \
     pyyaml \
     sphinx \
-    pysam
+    pysam \
+    colorama \
+    termcolor
 RUN conda install -c daler \
     tabix \
     bedtools=2.25.0
 ENV DISPLAY=:0
 ENV LANG C.UTF-8
 WORKDIR /opt/pybedtools
 
-RUN pip install https://github.com/AndersenLab/bam-toolbox/archive/0.0.3.tar.gz
-RUN apt-get install -y procps \
-    && rm -rf /var/lib/apt/lists/*
+RUN pip install https://github.com/AndersenLab/bam-toolbox/archive/1.0.0.tar.gz

README.md

@@ -3,12 +3,12 @@
 ## Installation
 
 ```
-pip install https://github.com/AndersenLab/bam-toolbox/archive/0.0.3.tar.gz
+pip install https://github.com/AndersenLab/bam-toolbox/archive/1.0.0.tar.gz
 ```
 
 ## Usage
 
-    bam-toolbox 0.1
+    bam-toolbox 1.0
 
     usage:
       bam <command> [<args>...]

bam/__init__.py

@@ -1 +1 @@
-__version__ = "0.0.3"
+__version__ = "1.0.0"

bam/cli.py

@@ -9,13 +9,19 @@
   coverage
 
 """
-from docopt import docopt
 from subprocess import call, check_output, CalledProcessError
-from clint.textui import colored, puts, indent
 import sys
-import bam
 import os
 
+from docopt import docopt
+from colorama import Fore, just_fix_windows_console, init
+from termcolor import colored
+
+import bam
+
+
+just_fix_windows_console()
+init(autoreset=True)
 
 debug = None
 if len(sys.argv) == 1:
@@ -46,7 +52,7 @@ def is_exe(fpath):
 
 def main():
     args = docopt(__doc__, 
-                  version='bam-toolbox v0.1',
+                  version='bam-toolbox v1.0',
                   argv = debug,
                   options_first=True)
     argv = [args['<command>']] + args['<args>']
@@ -59,33 +65,27 @@ def main():
         for install_name, program in program_list.items():
             check_output(["brew", "tap", "homebrew/science"])
             try:
-                with indent(4):
-                    puts(colored.blue("Installing " + install_name))
+                print(Fore.BLUE + "    Installing " + install_name)
                 check_output(["brew", "install", install_name])
                 program_installed.remove(install_name)
             except CalledProcessError:
                 try:
                     check_output(["which", program])
-                    with indent(4):
-                        puts(colored.blue(program + " previously installed"))
+                    print(Fore.BLUE + "    " + program + " previously installed")
                     program_installed.remove(install_name)
                 except CalledProcessError:
-                    with indent(4):
-                        puts(colored.red("Error installing " + install_name))
+                    print(Fore.RED + "    Error installing " + install_name)
         if len(program_installed) == 0:
-            with indent(4):
-                puts(colored.blue("Programs successfully installed!"))
+            print(Fore.BLUE + "    Programs successfully installed!")
         else:
-            with indent(4):
-                puts(colored.red("Error: Not all programs successfully installed: "  + ", ".join(program_installed)))
+            print(Fore.RED + "    Error: Not all programs successfully installed: "  + ", ".join(program_installed))
     elif args["<command>"] == "":
         print(__doc__)
         for prog in program_list.values():
             try:
                 check_output(["which", prog])
             except CalledProcessError:
-                with indent(4):
-                    puts(colored.red(prog + " not installed. Use a package manager to install or try using 'tb.py setup'\n"))
+                print(Fore.RED + "    " + prog + " not installed. Use a package manager to install or try using 'tb.py setup'\n")
     elif args['<command>'] in ['coverage', 'readgroups', 'fastq']:
         comm = ['python', getScriptPath() + '/' + args["<command>"] + ".py"] + argv
         exit(call(comm))

bam/coverage.py

@@ -12,16 +12,20 @@
   --header                    print header
 
 """
-from docopt import docopt
+import sys
 from collections import OrderedDict
-from clint.textui import colored, indent, puts_err
 import os
 import re
 from subprocess import Popen, PIPE
-
 from datetime import datetime
 from collections import OrderedDict
 
+from docopt import docopt
+from colorama import Fore, just_fix_windows_console, init
+from termcolor import colored
+
+just_fix_windows_console()
+init(autoreset=True)
 
 class output_line:
 
@@ -72,27 +76,27 @@ def __init__(self, fname, mtchr = None):
 
     def parse_header(self):
         header, err = Popen(["samtools", "view", "-H", self.fname], stdout=PIPE, stderr=PIPE).communicate()
-        if err != "":
+        if err != b"":
             raise Exception(err)
         self.header = header
         contigs = OrderedDict()
         contig_regions = []
-        for x in re.findall("@SQ\WSN:(?P<chrom>[A-Za-z0-9_]*)\WLN:(?P<length>[0-9]+)", header):
-            contigs[x[0]] = int(x[1])
-            region = "%s:%s-%s" % (x[0], "1", x[1])
+        for x in re.findall(b"@SQ\t[A-Za-z0-9]*SN:(?P<chrom>[A-Za-z0-9_]*)[A-Za-z0-9]*\tLN:(?P<length>[0-9]+)", header):
+            contigs[x[0].decode('utf-8')] = int(x[1])
+            region = "%s:%s-%s" % (x[0].decode('utf-8'), "1", x[1].decode('utf-8'))
             contig_regions.append(region)
         self.contigs = contigs
         self.contig_regions = contig_regions
 
         mtchr = [x for x in self.contigs.keys() if x.lower().find("m") == 0]
         if len(mtchr) == 1:
             self.mtchr = mtchr[0]
-            with indent(4):
-                puts_err(colored.blue("\nGuessing Mitochondrial Chromosome: " + self.mtchr + "\n"))
+            print(Fore.BLUE + "\n    Guessing Mitochondrial Chromosome: " + self.mtchr + "\n",
+                  file=sys.stderr)
 
         self.genome_length = sum(contigs.values())
         if mtchr:
-            self.nuclear_length = sum([x for x in contigs.values() if x != contigs[self.mtchr]])
+            self.nuclear_length = sum([x for x in self.contigs.values() if x != self.contigs[self.mtchr]])
 
 
     def sum_coverage(self, region=None):
@@ -101,15 +105,15 @@ def sum_coverage(self, region=None):
             pos_covered = 0
             cum_depth = 0
             for row in comm.stdout:
-                chrom, pos, depth = row.strip().split("\t")
+                chrom, pos, depth = row.strip().split(b"\t")
                 pos_covered += 1
                 cum_depth += int(depth)
             return pos_covered, cum_depth
 
 
 def iterate_window(bamfile, size):
     for chrom, size in bamfile.contigs.items():
-        for i in xrange(1, size, window):
+        for i in range(1, size, window):
             if i + window > size:
                 end = size
             else:
@@ -137,10 +141,9 @@ def calc_coverage(bamfile, regions=None, mtchr=None):
         # If end extends to far, adjust for chrom
         chrom_len = bamfile.contigs[chrom]
         if end > chrom_len:
-            m = "\nSpecified chromosome end extends beyond chromosome length. Set to max of: "
-            with indent(4):
-                puts_err(colored.yellow(m + str(chrom_len) + "\n"))
-                end = chrom_len
+            m = "\n    Specified chromosome end extends beyond chromosome length. Set to max of: "
+            print(Fore.YELLOW + m + str(chrom_len) + "\n", file=sys.stderr)
+            end = chrom_len
 
         region = "{c}:{s}-{e}".format(c=chrom, s=start, e=end + 1)
         pos_covered, cum_depth = bamfile.sum_coverage(region)
@@ -199,13 +202,14 @@ def calc_coverage(bamfile, regions=None, mtchr=None):
             Calculate coverage genome wide
         """
         bam = args["<bam>"]
+        print(b.contig_regions, file=sys.stderr)
         cov = calc_coverage(b, b.contig_regions)
 
         # Genomewide depth
         output_dir = {}
+        output_dir["chrom"] = "genome"
         output_dir["start"] = 1
         output_dir["end"] = b.genome_length
-        output_dir["chrom"] = "genome"
 
         bases_mapped = sum([x["bases_mapped"] for x in cov])
         output_dir["ATTR"] = "bases_mapped"
@@ -224,8 +228,8 @@ def calc_coverage(bamfile, regions=None, mtchr=None):
 
         if b.mtchr:
             # Nuclear
-            output_dir["end"] = b.nuclear_length
             output_dir["chrom"] = "nuclear"
+            output_dir["end"] = b.nuclear_length
             bases_mapped = sum([x["bases_mapped"] for x in cov if x["chrom"] != b.mtchr])
             output_dir["ATTR"] = "bases_mapped"
             print(output_line(bam_name, output_dir, bases_mapped))
@@ -243,6 +247,6 @@ def calc_coverage(bamfile, regions=None, mtchr=None):
             print(output_line(bam_name, output_dir, pos_mapped))
 
             # mt:nuclear ratio
-            output_dir = {"start": 1, "end": b.nuclear_length, "chrom": "genome", "ATTR": "mt_nuclear_ratio"}
+            output_dir = {"chrom": "genome", "start": 1, "end": b.nuclear_length, "ATTR": "mt_nuclear_ratio"}
             mt_nuc = [x for x in cov if x["chrom"] == b.mtchr][0]["depth_of_coverage"] / coverage
             print(output_line(bam_name, output_dir, mt_nuc))

requirements.txt

@@ -1,4 +1,5 @@
-clint
+colorama
+termcolor
 docopt
 pandas
 pybedtools