drep 4.0.2__py3-none-any.whl

drep-4.0.2.data/scripts/dRep

@@ -0,0 +1,32 @@
+#!python
+
+
+###############################################################################
+#
+# dRep - main program entry point
+#
+###############################################################################
+
+__author__ = "Matt Olm"
+__license__ = "MIT"
+__email__ = "mattolm@gmail.com"
+__status__ = "Development"
+
+import argparse
+import os
+import sys
+
+if sys.version_info[0] < 3:
+    print('''
+    !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
+    !!! you're running dRep with python2 - you need python 3 !!!
+    !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!''')
+    sys.exit(1)
+
+import drep.argumentParser
+from drep.controller import Controller
+
+if __name__ == '__main__':
+    args = drep.argumentParser.parse_args(sys.argv[1:])
+    # do what you came here to do :)
+    Controller().parseArguments(args)

drep-4.0.2.data/scripts/parse_stb.py

@@ -0,0 +1,140 @@
+#!python
+
+import os
+import sys
+import gzip
+import textwrap
+import argparse
+
+def extract_bins(fasta, stb_file, out_base):
+    if (out_base != '') & (out_base[-1] != '/'):
+        out_base += '_'
+
+    # Make scaffold to bin dictionary
+    stb = {}
+    with open(stb_file) as stb_reader:
+        for line in stb_reader:
+            line = line.strip()
+
+            if line.startswith('#') or line.startswith('scaffold_name'):
+                continue
+
+            scaffold, bin = line.split('\t')[:2]
+            stb[scaffold.strip()] = bin.strip()
+
+    # Parse the FASTA file and write to bins
+    if fasta.endswith('.gz'):
+        open_func = gzip.open
+        mode = 'rt'
+    else:
+        open_func = open
+        mode = 'r'
+
+    with open_func(fasta, mode) as handle:
+        record_id = ''
+        record_seq = ''
+        for line in handle:
+            if line.startswith('>'):
+                if record_id and record_id in stb:
+                    bin = stb[record_id]
+                    with open(f"{out_base}{bin}.fa", 'a') as nw:
+                        nw.write(f">{record_id}\n{record_seq}\n")
+                record_id = line[1:].strip().split(' ')[0]
+                record_seq = ''
+            else:
+                record_seq += line.strip()
+
+        # Write the last record
+        if record_id and record_id in stb:
+            bin = stb[record_id]
+            with open(f"{out_base}{bin}.fa", 'a') as nw:
+                nw.write(f">{record_id}\n{record_seq}\n")
+
+import os
+import gzip
+
+def gen_stb(fastas):
+    if ((len(fastas) == 1) & (not fastas[0].endswith('.gz'))):
+        # See if this is a text file, not a fasta file
+        text_list = True
+        genomes = []
+        with open(fastas[0], 'r') as o:
+            for line in o.readlines():
+                if line.startswith('>'):
+                    text_list = False
+                    break
+                else:
+                    genomes.append(line.strip())
+        if text_list:
+            print("Treating .fasta input as list")
+            fastas = genomes
+
+    stb = {}
+    for fasta in fastas:
+        bin = os.path.basename(fasta)
+        if fasta.endswith('.gz'):
+            open_func = gzip.open
+            mode = 'rt'
+        else:
+            open_func = open
+            mode = 'r'
+
+        with open_func(fasta, mode) as handle:
+            for line in handle:
+                if line.startswith('>'):
+                    id = line[1:].strip().split(' ')[0]
+                    stb[id] = bin
+
+    return stb
+
+
+def print_stb(stb, output):
+    file = open(output,'w')
+    for key in sorted(stb, key=stb.get):
+        file.write("{0}\t{1}\n".format(key,stb[key]))
+    file.close()
+
+
+class SmartFormatter(argparse.HelpFormatter):
+    def _split_lines(self, text, width):
+        if text.startswith('R|'):
+            return text[2:].splitlines()
+        # this is the RawTextHelpFormatter._split_lines
+        return argparse.HelpFormatter._split_lines(self, text, width)
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+        usage=textwrap.dedent('''\
+         \n
+         The program has two uses related to scaffold to bin (.stb) files.
+         .stb files should be tab-separated, with no header, and two columns: scaffold and bin
+
+         Use 1) Pass a list of genomes to generate a .stb file.
+
+         Example:
+         parse_stb.py --reverse -f dereplicate_genomes/* -o representitve_genomes.stb
+
+         Use 2) Pass a single .fasta file and a scaffold to bin file (.stb) to generate a number of
+         fasta files based on the .stb file.
+
+         Example:
+         parse_stb.py -f concat_genomes.fasta -s scaffold_to_bin.tsv -o genomeList_1
+         '''))
+
+    parser.add_argument('-s','--stb',help='scaffold to bin file')
+    parser.add_argument('-f','--fasta',help='fasta file to extract scaffolds from. Will treat as compressed if ends in .gz. This can also be a single text file with a genome on each line',nargs='*')
+    parser.add_argument('-o','--output',help='output base name', default = '')
+
+    parser.add_argument('--reverse',help='generate a stb from a list of genomes',\
+                        action = "store_true")
+    args = parser.parse_args()
+
+    if args.reverse == False:
+        if len(args.fasta) != 1:
+            print("must give one and only one fasta file")
+            sys.exit()
+        extract_bins(args.fasta[0], args.stb, args.output)
+
+    if args.reverse == True:
+        stb = gen_stb(args.fasta)
+        print_stb(stb, args.output)

drep-4.0.2.dist-info/METADATA

@@ -0,0 +1,23 @@
+Metadata-Version: 2.4
+Name: drep
+Version: 4.0.2
+Summary: De-replication of microbial genomes assembled from multiple samples
+Home-page: https://github.com/MrOlm/drep
+Author: Matt Olm
+Author-email: mattolm@berkeley.edu
+License: MIT
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: seaborn
+Requires-Dist: matplotlib
+Requires-Dist: biopython
+Requires-Dist: scikit-learn
+Requires-Dist: tqdm
+Requires-Dist: setuptools
+Requires-Dist: pytest
+Dynamic: author
+Dynamic: author-email
+Dynamic: home-page
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: summary

drep-4.0.2.dist-info/RECORD

@@ -0,0 +1,28 @@
+drep/VERSION,sha256=xtP7BXsZjx0FY9QhjU42tI33UiUaq__njqYKrFpyx6I,6
+drep/WorkDirectory.py,sha256=xMd7qrNmUXsPPiJXpKBJgnFMzYHP4nAyBL9vWpxK0bo,11616
+drep/__init__.py,sha256=4579XfOUsiv6JlPzpU_fHU0iYApKaDSp17xqCmmqFKM,2846
+drep/argumentParser.py,sha256=Ca3LSN9-5-49Ml_7XQkUiEJbaYmbKOdJMWi0cxiCq6k,18336
+drep/controller.py,sha256=3yZ7MxHQoUUllZIhitRMhZXrTPftg3YEPlT60diTFmo,3334
+drep/d_adjust.py,sha256=ZekouLh3ExONxeQ4D0RfybkZhmhc6j6CiTlcv3y34V0,9455
+drep/d_analyze.py,sha256=YJ5ImCQ6NIS_WNS3Yr-1nvMniKTxfbDf52KOZGelZSs,50776
+drep/d_bonus.py,sha256=UGnOHSxecSDoeMvk64XpNKTM7S4aoWaanchx_tzCEjY,13829
+drep/d_choose.py,sha256=z-IJkpFoFISDJdtwXhvhPf01iXJu7xFinbWCHzcZH4c,11312
+drep/d_evaluate.py,sha256=RjB4SOqyahWjCESFhuumcMHPq8zeOXfJlpDVFw_6FbA,14393
+drep/d_filter.py,sha256=FfhpRGBSbltNHE7KrkzEguS27B4FW1BN0aExJnNRMJY,29271
+drep/d_workflows.py,sha256=gmpjp9c2B_BhfsOPbD2P32l6yp9L2ZI8qJ551Wkv24k,4161
+drep/d_cluster/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+drep/d_cluster/cluster_utils.py,sha256=yrQg-4V-bSltqwZhZhNdU_uBcvvol66wXGlIZXqr1bc,3977
+drep/d_cluster/compare_utils.py,sha256=KtKTqXRQLobF4CIHoSJG8wmpdfsx3MFmof6TU_k3f_c,27590
+drep/d_cluster/controller.py,sha256=gkdDwNkToc-TEbrRmPhzhCE0czssqeAKO999NYykNaw,9264
+drep/d_cluster/external.py,sha256=uHb4GYJfwsDgzyNi76JlCQ5VJfsQZmiH0Mq2Ls6_S_g,26053
+drep/d_cluster/greedy_clustering.py,sha256=61gb6dCP9FYEV6stWjSh6iFH26uSaMCwRJ9JLBQRGhg,6871
+drep/d_cluster/parsers.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+drep/d_cluster/union_find.py,sha256=rLO0BiXVY-VsrarzZ7h7GuSYdc0dvaae7Fg6ZIpx2Rw,19274
+drep/d_cluster/utils.py,sha256=HsNJJ3A8uLvKaTm8iR2OTq5Sz24ENmvRUSqYejmnn7o,22507
+drep-4.0.2.data/scripts/ScaffoldLevel_dRep.py,sha256=H3-TpjQkdgTCJmx080oGjmzpPsaLUQxPfHFuBOy-qVE,35201
+drep-4.0.2.data/scripts/dRep,sha256=PHJCJBCsO31KYPIQYgTdmZ7CpILAQ5EJxFlxz7_zW3g,835
+drep-4.0.2.data/scripts/parse_stb.py,sha256=d4eqJvx6M-skorqMypAo1jVjDomZPGNgTHZJZP8O3qo,4554
+drep-4.0.2.dist-info/METADATA,sha256=cxjovehPCsHW6s5bL1sUPXu3lBRHvmrVmtcBUvpDGLA,558
+drep-4.0.2.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+drep-4.0.2.dist-info/top_level.txt,sha256=St4866c-N05G5-o-ofs8yLmlWUBnX0lOFPZ7SB6h8Ls,5
+drep-4.0.2.dist-info/RECORD,,

drep-4.0.2.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

drep-4.0.2.dist-info/top_level.txt

@@ -0,0 +1 @@
+drep