.coveragerc

+[run]
+source = kleborate

Kleborate_results.txt

-strain	species	species_match	contig_count	N50	largest_contig	ST	virulence_score	resistance_score	num_resistance_classes	num_resistance_genes	Yersiniabactin	YbST	Colibactin	CbST	Aerobactin	AbST	Salmochelin	SmST	rmpA	rmpA2	wzi	K_locus	K_locus_problems	K_locus_confidence	K_locus_identity	K_locus_missing_genes	O_locus	O_locus_problems	O_locus_confidence	O_locus_identity	O_locus_missing_genes	Chr_ST	gapA	infB	mdh	pgi	phoE	rpoB	tonB	ybtS	ybtX	ybtQ	ybtP	ybtA	irp2	irp1	ybtU	ybtT	ybtE	fyuA	clbA	clbB	clbC	clbD	clbE	clbF	clbG	clbH	clbI	clbL	clbM	clbN	clbO	clbP	clbQ	AGly	Col	Fcyn	Flq	Gly	MLS	Ntmdz	Phe	Rif	Sul	Tet	Tmt	Bla	Bla_Carb	Bla_ESBL	Bla_ESBL_inhR	Bla_broad	Bla_broad_inhR
-Klebs_HS11286	Klebsiella pneumoniae	strong	7	5333942	5333942	ST11	1	2	9	17	ybt 9; ICEKp3	15	-	0	-	0	-	0	-	-	wzi74	KL103	*	Very high	96.69%		O2v1	none	Very high	97.72%		ST11	3	3	1	1	1	1	4	14	11	14	5	9	22	19	10	5	11	11	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	StrB;StrA*;AadA2*;RmtB;Aac3-IId*?	-	-	GyrA-83I;ParC-80I	-	-	-	-	-	SulII	TetG	DfrA12?	AmpH*	KPC-2	CTX-M-14;CTX-M-14	-	SHV-11	TEM-30*;TEM-30*;TEM-30*
-MGH78578	Klebsiella pneumoniae	strong	6	5315120	5315120	ST38	0	1	7	15	-	0	-	0	-	0	-	0	-	-	wzi50	KL52	none	Perfect	100.00%		OL101	*	High	94.91%		ST38	2	1	2	1	2	2	2	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	AadA1-pm*?;Aac6-Ib;StrB;Aph3''Ia;StrA;AadB	-	-	GyrA-83Y	-	-	-	CmlA5;CatA1*	-	SulI;SulII	TetD	-	AmpH*;SHV-187*;OXA-9*	-	SHV-12	-	-	TEM-54*;TEM-30*
-NTUH-K2044	Klebsiella pneumoniae	strong	2	5248520	5248520	ST23	4	0	0	0	ybt 2; ICEKp1	326	-	0	iuc 1	1	iro 3	18-1LV	rmpA_11 (ICEKp1),rmpA_2 (KpVP-1)	rmpA2_3	wzi1	KL1	none	Perfect	100.00%		O1v2	none	Very high	99.13%		ST23	2	1	1	1	9	4	12	9	7	9	6	5	1	1	6	7	7	6	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	AmpH;SHV-190*	-	-	-	-	-
-SGH10	Klebsiella pneumoniae	strong	2	5485114	5485114	ST23	5	0	0	0	ybt 1; ICEKp10	53	clb 2	29	iuc 1	1	iro 1	2	rmpA_2 (KpVP-1)	rmpA2_6*	wzi1	KL1	none	Very high	100.00%		O1v2	none	Very high	99.11%		ST23	2	1	1	1	9	4	12	2	2	2	2	2	6	124	2	2	2	2	2	2	2	2	2	2	2	3	2	2	2	2	2	2	2	-	-	-	-	-	-	-	-	-	-	-	-	AmpH;SHV-190*	-	-	-	-	-

data/README.md

-# Kleborate data
-
-* [ncbi_genome_kleborate_results.txt](ncbi_genome_kleborate_results.txt) 
-Kleborate output for all _Klebsiella_ genomes in NCBI (genomes downloaded using [this tool](https://github.com/kblin/ncbi-genome-download)). The first 21 columns in the file are NCBI's metadata for the genome. The remaining columns are Kleborate's output.
-
-* [Genotyped_Isolates_Lam2017.txt](Genotyped_Isolates_Lam2017.txt)
-Manually curated genotype information used in the Lam et al 2017 preprint
-
-* [UK-IRE-MDR_Lam2017.txt](UK-IRE-MDR_Lam2017.txt)
-Kleborate results for 200 MDR isolates from UK & Ireland [Moradigaravand et al, MBio 2017](http://mbio.asm.org/content/8/1/e01976-16.long) as reported in the Lam et al 2017 preprint

debian/changelog

-kleborate (0.3.0-1) UNRELEASED; urgency=medium
+kleborate (1.0.0-1) UNRELEASED; urgency=medium
 
   * Initial release (Closes: #<bug>)
 
- -- Andreas Tille <tille@debian.org>  Tue, 24 Sep 2019 12:36:03 +0200
+ -- Andreas Tille <tille@debian.org>  Wed, 15 Jan 2020 21:44:54 +0100

debian/control

@@ -5,12 +5,12 @@ Section: science
 Priority: optional
 Build-Depends: debhelper-compat (= 12),
                dh-python,
-               python3-all,
+               python3,
                python3-setuptools,
                ncbi-blast+ <!nocheck>,
                mash <!nocheck>,
                kaptive <!nocheck>
-Standards-Version: 4.4.0
+Standards-Version: 4.4.1
 Vcs-Browser: https://salsa.debian.org/med-team/kleborate
 Vcs-Git: https://salsa.debian.org/med-team/kleborate.git
 Homepage: https://github.com/katholt/Kleborate

debian/patches/fix_get_resource_paths.patch

-Author: Andreas Tille <tille@debian.org>
-Last-Update: Tue, 24 Sep 2019 12:36:03 +0200
-Description: Fix tests: get_resource_paths() returns 5 values
-
---- a/test/test_iro.py
-+++ b/test/test_iro.py
-@@ -22,7 +22,7 @@ class TestIro(unittest.TestCase):
-     """
- 
-     def setUp(self):
--        self.data_folder, self.mlstblast, self.resblast, self.clusterblast = get_resource_paths()
-+        self.data_folder, self.mlstblast, self.resblast, self.clusterblast, self.rmpablast = get_resource_paths()
- 
-     def test_iro_random(self):
-         """
---- a/test/test_mlst.py
-+++ b/test/test_mlst.py
-@@ -22,7 +22,7 @@ class TestMlst(unittest.TestCase):
-     """
- 
-     def setUp(self):
--        self.data_folder, self.mlstblast, self.resblast, self.clusterblast = get_resource_paths()
-+        self.data_folder, self.mlstblast, self.resblast, self.clusterblast, self.rmpablast = get_resource_paths()
- 
-     def test_chromosome_random(self):
-         """
---- a/test/test_res_mgrb_pmrb.py
-+++ b/test/test_res_mgrb_pmrb.py
-@@ -31,7 +31,7 @@ class TestResAlleles(unittest.TestCase):
- 
-     def setUp(self):
-         self.args = Args()
--        self.data_folder, self.mlstblast, self.resblast, self.clusterblast = get_resource_paths()
-+        self.data_folder, self.mlstblast, self.resblast, self.clusterblast, self.rmpablast = get_resource_paths()
-         _, _, self.res_headers = get_output_headers(self.args, self.resblast, self.data_folder)
- 
-     def test_both_genes_intact(self):

debian/patches/python3.patch

@@ -3,76 +3,31 @@ Last-Update: Tue, 24 Sep 2019 12:36:03 +0200
 Origin: https://github.com/katholt/Kleborate/issues/17
 Description: When using Python3 the executable is named python3
 
---- a/kleborate-runner.py
-+++ b/kleborate-runner.py
+--- a/README.md
++++ b/README.md
+@@ -86,7 +86,7 @@ Kleborate can be installed to your syste
+ ```bash
+ git clone --recursive https://github.com/katholt/Kleborate.git
+ cd Kleborate
+-python setup.py install
++python3 setup.py install
+ kleborate -h
+ ```
+ 
+@@ -115,7 +115,7 @@ A python3 script to download the latest
+ 
+ ```
+ cd Kleborate/scripts
+-python getmlst.py --species "Klebsiella pneumoniae"
++python3 getmlst.py --species "Klebsiella pneumoniae"
+ mv Klebsiella_pneumoniae.fasta ../kleborate/data
+ mv kpneumoniae.txt ../kleborate/data
+ ```
+--- a/scripts/getmlst.py
++++ b/scripts/getmlst.py
 @@ -1,4 +1,4 @@
 -#!/usr/bin/env python
-+#!/usr/bin/python3
- """
- Convenience wrapper for running Kleborate directly from source tree.
++#!/usr/bin/env python3
  
---- a/kleborate/kleborate.py
-+++ b/kleborate/kleborate.py
-@@ -208,7 +208,7 @@ def get_output_headers(args, resblast, d
- 
- 	# If resistance genes are on, run the resBLAST.py script to get its headers.
- 	if args.resistance:
--		res_out = subprocess.check_output('python ' + resblast +
-+		res_out = subprocess.check_output(sys.executable + ' '  + resblast +
- 										  ' -s ' + data_folder + '/ARGannot_r2.fasta' +
- 										  ' -t ' + data_folder + '/ARGannot_clustered80_r2.csv',
- 										  shell=True)
-@@ -374,7 +374,7 @@ def run_kaptive(kaptive_py, kaptive_db,
- 															random.randint(0, 999999))
- 	kaptive_table = kaptive_prefix + '_table.txt'
- 
--	p = subprocess.Popen('python ' + kaptive_py +
-+	p = subprocess.Popen(sys.executable + ' '  + kaptive_py +
- 						 ' -a ' + contigs +
- 						 ' -k ' + kaptive_db +
- 						 ' -o ' + kaptive_prefix +
-@@ -492,7 +492,7 @@ def get_species_results(contigs, data_fo
- 
- 
- def get_chromosome_mlst_results(mlstblast, data_folder, contigs):
--	f = os.popen('python ' + mlstblast +
-+	f = os.popen(sys.executable + ' '  + mlstblast +
- 				 ' -s ' + data_folder + '/Klebsiella_pneumoniae.fasta' +
- 				 ' -d ' + data_folder + '/kpneumoniae.txt' +
- 				 ' -i no' +
-@@ -521,7 +521,7 @@ def get_chromosome_mlst_results(mlstblas
- def get_virulence_cluster_results(mlstblast, data_folder, contigs, alleles_fasta, profiles_txt,
- 								  vir_name, vir_st_name, unknown_group_name, min_gene_count,
- 								  header_function):
--	f = os.popen('python ' + mlstblast +
-+	f = os.popen(sys.executable + ' '  + mlstblast +
- 				 ' -s ' + data_folder + '/' + alleles_fasta +
- 				 ' -d ' + data_folder + '/' + profiles_txt +
- 				 ' -i yes' +
-@@ -580,7 +580,7 @@ def get_iro_mlst_results(mlstblast, data
- 
- def get_hypermucoidy_results(rmpablast, data_folder, contigs):
- 	hypermucoidy = '-'
--	f = os.popen('python ' + rmpablast +
-+	f = os.popen(sys.executable + ' '  + rmpablast +
- 				 ' -s ' + data_folder + '/hypermucoidy.fasta' +
- 				 ' -d ' + data_folder + '/hypermucoidy_rmpA.txt' +
- 				 ' ' + contigs)
-@@ -596,7 +596,7 @@ def get_hypermucoidy_results(rmpablast,
- 
- def get_wzi_and_k_locus_results(mlstblast, data_folder, contigs):
- 	wzi_st, k_type = '-', '-'
--	f = os.popen('python ' + mlstblast +
-+	f = os.popen(sys.executable + ' '  + mlstblast +
- 				 ' -s ' + data_folder + '/wzi.fasta' +
- 				 ' -d ' + data_folder + '/wzi.txt' +
- 				 ' -i yes' +
-@@ -620,7 +620,7 @@ def get_wzi_and_k_locus_results(mlstblas
- def get_resistance_results(resblast, data_folder, contigs, args, res_headers):
- 	res_hits = []
- 	if args.resistance:
--		f = os.popen('python ' + resblast +
-+		f = os.popen(sys.executable + ' '  + resblast +
- 					 ' -s ' + data_folder + '/ARGannot_r2.fasta' +
- 					 ' -t ' + data_folder + '/ARGannot_clustered80_r2.csv' +
- 					 ' -q ' + data_folder + '/QRDR_120.aa' +
+ '''
+ Download MLST datasets from this site: http://pubmlst.org/data/ by

debian/patches/series

 python3.patch
-fix_get_resource_paths.patch
 use_debian_installed_kaptive.patch

debian/patches/use_debian_installed_kaptive.patch

@@ -2,9 +2,9 @@ Author: Andreas Tille <tille@debian.org>
 Last-Update: Tue, 24 Sep 2019 12:36:03 +0200
 Description: Make sure Debian packaged kaptive will be found
 
---- a/kleborate/kleborate.py
-+++ b/kleborate/kleborate.py
-@@ -353,13 +353,13 @@ def get_resource_paths():
+--- a/kleborate/kaptive.py
++++ b/kleborate/kaptive.py
+@@ -20,13 +20,13 @@ import tempfile
  
  def get_kaptive_paths():
      this_file = os.path.realpath(__file__)
@@ -16,7 +16,7 @@ Description: Make sure Debian packaged kaptive will be found
      if not os.path.isfile(kaptive_py):
          sys.exit('Error: could not find kaptive.py')
 -    db_dir = os.path.join(kaptive_dir, 'reference_database')
-+	db_dir = '/usr/share/kaptive/reference_database'
++    db_dir = '/usr/share/kaptive/reference_database/'
      kaptive_k_db = os.path.join(db_dir, 'Klebsiella_k_locus_primary_reference.gbk')
      if not os.path.isfile(kaptive_k_db):
          sys.exit('Error: could not find Klebsiella_k_locus_primary_reference.gbk')

debian/rules

@@ -2,9 +2,3 @@
 
 %:
 	dh $@ --with python3 --buildsystem=pybuild
-
-### When overriding auto_test make sure DEB_BUILD_OPTIONS will be respected
-override_dh_auto_test:
-ifeq (,$(filter nocheck,$(DEB_BUILD_OPTIONS)))
-	dh_auto_test || true		# FIXME: Cheating through two potentially broken tests
-endif

kleborate-runner.py

-#!/usr/bin/env python
+#!/usr/bin/env python3
 """
 Convenience wrapper for running Kleborate directly from source tree.
 

kleborate/blastn.py

+"""
+Copyright 2018 Kat Holt
+Copyright 2018 Ryan Wick (rrwick@gmail.com)
+https://github.com/katholt/Kleborate/
+
+This file is part of Kleborate. Kleborate is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by the Free Software Foundation,
+either version 3 of the License, or (at your option) any later version. Kleborate is distributed in
+the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for more
+details. You should have received a copy of the GNU General Public License along with Kleborate. If
+not, see <http://www.gnu.org/licenses/>.
+"""
+
+import os
+import subprocess
+
+
+def run_blastn(db, query, minident, culling_limit=1, ungapped=False):
+    build_blast_database_if_needed(db)
+
+    cmd = 'blastn -task blastn -db {} -query {}'.format(db, query)
+    cmd += " -outfmt '6 sacc pident slen length score qseq sstrand sstart send'"
+    cmd += ' -dust no -evalue 1E-20 -word_size 32 -max_target_seqs 10000'
+    cmd += ' -culling_limit {} -perc_identity {}'.format(culling_limit, minident)
+    if ungapped:
+        cmd += ' -ungapped'
+
+    # TODO: switch this over to subprocess
+    blast_hits = []
+    f = os.popen(cmd)
+    for line in f:
+        blast_hits.append(BlastHit(line))
+    f.close()
+
+    return blast_hits
+
+
+class BlastHit(object):
+    def __init__(self, line):
+        fields = line.rstrip().split('\t')
+        self.gene_id = fields[0]                # sacc
+        self.pcid = float(fields[1])            # pident
+        self.ref_length = int(fields[2])        # slen
+        self.alignment_length = int(fields[3])  # length
+        self.score = float(fields[4])           # score
+        self.hit_seq = fields[5]                # qseq
+        self.strand = fields[6]                 # sstrand
+        self.ref_start = int(fields[7])         # sstart
+        self.ref_end = int(fields[8])           # send
+
+
+def build_blast_database_if_needed(seqs):
+    if not os.path.exists(seqs + '.nin'):
+        with open(os.devnull, 'w') as devnull:
+            subprocess.check_call('makeblastdb -dbtype nucl -in ' + seqs, stdout=devnull,
+                                  shell=True)

kleborate/clusterBLAST.py

-"""
-Copyright 2018 Kat Holt
-Copyright 2018 Ryan Wick (rrwick@gmail.com)
-https://github.com/katholt/Kleborate/
-
-This file is part of Kleborate. Kleborate is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by the Free Software Foundation,
-either version 3 of the License, or (at your option) any later version. Kleborate is distributed in
-the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for more
-details. You should have received a copy of the GNU General Public License along with Kleborate. If
-not, see <http://www.gnu.org/licenses/>.
-"""
-
-# blast for sets of genes that make up operons for screening
-# summarise hits for each operon
-
-import os
-import sys
-import subprocess
-from optparse import OptionParser
-
-
-def main():
-    usage = "usage: %prog [options]"
-    parser = OptionParser(usage=usage)
-
-    # options
-    parser.add_option("-s", "--seqs", action="store", dest="seqs", default="",
-                      help="operon sequences to screen for")
-    parser.add_option("-m", "--minident", action="store", dest="minident", default="90",
-                      help="Minimum percent identity (default 90)")
-    parser.add_option("-c", "--mincov", action="store", dest="mincov", default="80",
-                      help="Minimum percent coverage (default 80)")
-    return parser.parse_args()
-
-
-if __name__ == "__main__":
-
-    (options, args) = main()
-
-    def check_dup(x):
-        once = []
-        twice = []
-        for i in x:
-            if i not in once:
-                once.append(i)
-            else:
-                twice.append(i)
-        return once, twice
-
-    if options.seqs == "":
-        sys.exit("No operon sequences provided (-s)")
-    else:
-        (path, fileName) = os.path.split(options.seqs)
-        if not os.path.exists(options.seqs + ".nin"):
-            with open(os.devnull, 'w') as devnull:
-                subprocess.check_call("makeblastdb -dbtype nucl -in " + options.seqs,
-                                      stdout=devnull, shell=True)
-        (fileName, ext) = os.path.splitext(fileName)
-
-    # print header
-    print("\t".join(["strain", "hypermucoidy"]))
-
-    for contigs in args:
-        (_, fileName) = os.path.split(contigs)
-        (name, ext) = os.path.splitext(fileName)
-
-        # blast against all
-        f = os.popen("blastn -task blastn -db " + options.seqs + " -query " + contigs +
-                     " -outfmt '6 sacc pident slen length score' -ungapped -dust no -evalue 1E-20 -word_size 32"
-                     " -max_target_seqs 10000 -culling_limit 1 -perc_identity " + options.minident)
-
-        # list of genes in each locus with hits
-        iro = []
-        rmpA = []
-        iuc = []
-        for line in f:
-            fields = line.rstrip().split("\t")
-            (gene_id, pcid, length, allele_length, score) = (fields[0], float(fields[1]), float(fields[2]),
-                                                             float(fields[3]), float(fields[4]))
-            if gene_id.startswith("rmpA"):
-                if (allele_length / length * 100) > float(options.mincov):
-                    rmpA.append(gene_id)
-        f.close()
-
-        rmpA.sort()
-
-        rmpA_string = "-"
-        if len(rmpA) > 0:
-            rmpA_string = ";".join(rmpA)
-
-        print("\t".join([name, rmpA_string]))

kleborate/contig_stats.py

@@ -12,8 +12,15 @@ details. You should have received a copy of the GNU General Public License along
 not, see <http://www.gnu.org/licenses/>.
 """
 
-import sys
-import gzip
+from .misc import load_fasta
+
+
+def get_contig_stat_results(contigs):
+    contig_count, n50, longest_contig, ambiguous_bases = get_contig_stats(contigs)
+    return {'contig_count': str(contig_count),
+            'N50': str(n50),
+            'largest_contig': str(longest_contig),
+            'ambiguous_bases': ambiguous_bases}
 
 
 def get_contig_stats(assembly):
@@ -21,10 +28,21 @@ def get_contig_stats(assembly):
     Returns various contig length metrics.
     """
     fasta = load_fasta(assembly)
+
+    characters = set()
+    for _, seq in fasta:
+        characters |= set(b for b in seq)
+    characters -= {'A', 'C', 'G', 'T'}
+    if characters:
+        ambiguous_bases = 'yes'
+    else:
+        ambiguous_bases = 'no'
+
     contig_lengths = sorted([len(x[1]) for x in fasta])
     if not contig_lengths:
         return 0, 0, 0
     longest = contig_lengths[-1]
+
     half_total_length = sum(contig_lengths) / 2
     total_so_far = 0
     segment_lengths = contig_lengths[::-1]
@@ -35,54 +53,5 @@ def get_contig_stats(assembly):
             break
     else:
         n50 = 0
-    return len(contig_lengths), n50, longest
-
-
-def load_fasta(filename):
-    """Returns the names and sequences for the given fasta file."""
-    fasta_seqs = []
-    if get_compression_type(filename) == 'gz':
-        open_func = gzip.open
-    else:  # plain text
-        open_func = open
-    with open_func(filename, 'rt') as fasta_file:
-        name = ''
-        sequence = ''
-        for line in fasta_file:
-            line = line.strip()
-            if not line:
-                continue
-            if line[0] == '>':  # Header line = start of new contig
-                if name:
-                    fasta_seqs.append((name.split()[0], sequence))
-                    sequence = ''
-                name = line[1:]
-            else:
-                sequence += line
-        if name:
-            fasta_seqs.append((name.split()[0], sequence))
-    return fasta_seqs
-
-
-def get_compression_type(filename):
-    """
-    Attempts to guess the compression (if any) on a file using the first few bytes.
-    http://stackoverflow.com/questions/13044562
-    """
-    magic_dict = {'gz': (b'\x1f', b'\x8b', b'\x08'),
-                  'bz2': (b'\x42', b'\x5a', b'\x68'),
-                  'zip': (b'\x50', b'\x4b', b'\x03', b'\x04')}
-    max_len = max(len(x) for x in magic_dict)
 
-    unknown_file = open(filename, 'rb')
-    file_start = unknown_file.read(max_len)
-    unknown_file.close()
-    compression_type = 'plain'
-    for file_type, magic_bytes in magic_dict.items():
-        if file_start.startswith(magic_bytes):
-            compression_type = file_type
-    if compression_type == 'bz2':
-        sys.exit('cannot use bzip2 format - use gzip instead')
-    if compression_type == 'zip':
-        sys.exit('cannot use zip format - use gzip instead')
-    return compression_type
+    return len(contig_lengths), n50, longest, ambiguous_bases

kleborate/data/ARGannot_clustered80_r2.csv → kleborate/data/ARGannot_clustered80_r3.csv

@@ -107,7 +107,6 @@ clusterid,queryID,class,gene,allele,seqID,accession,positions,size,cluster_conta
 83,OCH-8__631,Bla,OCH-2,OCH-8,631,DQ489307,1071-2243,1173,no,no,class C extended-spectrum beta-lactamase,Bla_ESBL
 84,NorA__638,Flq,NorA,NorA,638,HE579073,721034-722200,1167,no,no,NA,NA
 85,TetX__639,Tet,TetX,TetX,639,M37699,586-1752,1167,no,no,NA,NA
-86,AmpH__634,Bla,AmpH,AmpH,634,CP003785,4208384-4209544,1161,no,no,NA,NA
 87,VanS-A__635,Gly,VanS-A,VanS-A,635,M97297,4649-5803,1155,no,no,NA,NA
 87,VanS-Pt2__636,Gly,VanS-A,VanS-Pt2,636,DQ018710,3721-4881,1161,no,no,NA,NA
 87,VanS-Pt__637,Gly,VanS-A,VanS-Pt,637,AY926880,1391-2551,1161,no,no,NA,NA
@@ -777,7 +776,7 @@ clusterid,queryID,class,gene,allele,seqID,accession,positions,size,cluster_conta
 193,CTX-M-29__154,Bla,CTX-M-1,CTX-M-29,154,AY267213,1-876,876,no,no,class A extended-spectrum beta-lactamase,Bla_ESBL
 193,CTX-M-30__155,Bla,CTX-M-1,CTX-M-30,155,AY292654,1-876,876,no,no,class A extended-spectrum beta-lactamase,Bla_ESBL
 193,CTX-M-32__156,Bla,CTX-M-1,CTX-M-32,156,AJ557142,1-876,876,no,no,class A extended-spectrum beta-lactamase,Bla_ESBL
-193,CTX-M-33__157,Bla,CTX-M-1,CTX-M-33,157,AY238472,888-13,876,no,no,class A extended-spectrum beta-lactamase,Bla_ESBL
+193,CTX-M-33__157,Bla,CTX-M-1,CTX-M-33,157,AY238472,888-13,876,no,no,class A extended-spectrum beta-lactamase,Bla_Carb
 193,CTX-M-34__158,Bla,CTX-M-1,CTX-M-34,158,AY515297,1-876,876,no,no,class A extended-spectrum beta-lactamase,Bla_ESBL
 193,CTX-M-36__159,Bla,CTX-M-1,CTX-M-36,159,AB177384,1-876,876,no,no,class A extended-spectrum beta-lactamase,Bla_ESBL
 193,CTX-M-37__160,Bla,CTX-M-1,CTX-M-37,160,AY649755,1641-2516,876,no,no,class A extended-spectrum beta-lactamase,Bla_ESBL
@@ -1348,6 +1347,7 @@ clusterid,queryID,class,gene,allele,seqID,accession,positions,size,cluster_conta
 275,OXA-163__261,Bla,OXA-48,OXA-163,261,HQ700343,1-786,786,no,no,carbapenem-hydrolyzing class D beta-lactamase,Bla_Carb
 275,OXA-181__262,Bla,OXA-48,OXA-181,262,HM992946,1-798,798,no,no,OXA-48 family carbapenem-hydrolyzing class D beta-lactamase,Bla_Carb
 275,OXA-204__263,Bla,OXA-48,OXA-204,263,JQ809466,5375-6172,798,no,no,OXA-48 family carbapenem-hydrolyzing class D beta-lactamase,Bla_Carb
+275,OXA-232__1837,Bla,OXA-48,OXA-232,1837,JX423831,2677-3474,798,no,no,OXA-48 family carbapenem-hydrolyzing class D beta-lactamase,Bla_Carb
 275,OXA-244__264,Bla,OXA-48,OXA-244,264,JX438000,1-798,798,no,no,OXA-48 family carbapenem-hydrolyzing class D beta-lactamase,Bla_Carb
 275,OXA-245__265,Bla,OXA-48,OXA-245,265,JX438001,1-798,798,no,no,OXA-48 family carbapenem-hydrolyzing class D beta-lactamase,Bla_Carb
 275,OXA-247__266,Bla,OXA-48,OXA-247,266,JX893517,1-786,786,no,no,OXA-48 family carbapenem-hydrolyzing class D beta-lactamase,Bla_Carb
@@ -1749,13 +1749,31 @@ clusterid,queryID,class,gene,allele,seqID,accession,positions,size,cluster_conta
 467,Mcr1-5__1753,Col,Mcr1,Mcr1-5,1753,KY283125,1-1626,1626,no,no,NA,NA
 467,Mcr1-6__1754,Col,Mcr1,Mcr1-6,1754,NG_052893,101-1726,1626,no,no,NA,NA
 467,Mcr1-7__1755,Col,Mcr1,Mcr1-7,1755,KY488488,1-1626,1626,no,no,NA,NA
-467,Mcr1__1835,Col,Mcr1,Mcr1,1835,KP347127,22413-24038,1626,no,no,NA,NA
-468,Mcr2__1836,Col,Mcr2,Mcr2,1836,LT598652,26779-28395,1617,no,no,NA,NA
+467,Mcr1-8__1781,Col,Mcr1,Mcr1-8,1781,KY683842.1,1-1626,1626,no,no,NA,NA
+467,Mcr1-9__1782,Col,Mcr1,Mcr1-9,1782,KY964067.1,27201-28809,1626,no,no,NA,NA
+467,Mcr1-10__1783,Col,Mcr1,Mcr1-10,1783,MF176238.1,1-1626,1626,no,no,NA,NA
+467,Mcr1-11__1784,Col,Mcr1,Mcr1-11,1784,KY853650.1,1-1629,1629,no,no,NA,NA
+467,Mcr1-12__1785,Col,Mcr1,Mcr1-12,1785,LC337668.1,1-1626,1626,no,no,NA,NA
+467,Mcr1-1__1835,Col,Mcr1,Mcr1-1,1835,KP347127,22413-24038,1626,no,no,NA,NA
+468,Mcr2-2__1786,Col,Mcr2,Mcr2-2,1786,MF176239.1,1-1617,1617,no,no,NA,NA
+468,Mcr2-1__1836,Col,Mcr2,Mcr2-1,1836,LT598652,26779-28395,1617,no,no,NA,NA
 469,PBP1b__1756,Bla,PBP1b,PBP1b,1756,AF101781,1-2466,2466,no,no,NA,NA
 470,PBP1a__1757,Bla,PBP1a,PBP1a,1757,JN645776,1-2160,2160,no,no,NA,NA
 471,MEC-C__1758,Bla,MEC,MEC-C,1758,HG515014,42996-44993,1998,no,no,NA,NA
-473,Mcr3__1760,Col,Mcr3,Mcr3,1760,KY924928,161134-162759,1626,no,no,NA,NA
-474,Mcr4__1761,Col,Mcr4,Mcr4,1761,MF543359,5808-7433,1626,no,no,NA,NA
+473,Mcr3-1__1760,Col,Mcr3,Mcr3-1,1760,KY924928,161134-162759,1626,no,no,NA,NA
+473,Mcr3-2__1787,Col,Mcr3,Mcr3-2,1787,NMWW01000143.1,316-1942,1626,no,no,NA,NA
+473,Mcr3-3__1788,Col,Mcr3,Mcr3-3,1788,MF495680.1,240178-241801,1623,no,no,NA,NA
+473,Mcr3-4__1789,Col,Mcr3,Mcr3-4,1789,NQCO01000074.1,2954-4580,1626,no,no,NA,NA
+473,Mcr3-5__1790,Col,Mcr3,Mcr3-5,1790,MF489760.1,49179-50805,1626,no,no,NA,NA
+473,Mcr3-6__1791,Col,Mcr3,Mcr3-6,1791,MF598076.1,0-1623,1623,no,no,NA,NA
+473,Mcr3-7__1792,Col,Mcr3,Mcr3-7,1792,MF598077.1,93-1719,1626,no,no,NA,NA
+473,Mcr3-8__1793,Col,Mcr3,Mcr3-8,1793,MF598078.1,0-1623,1623,no,no,NA,NA
+473,Mcr3-9__1794,Col,Mcr3,Mcr3-9,1794,MF598080.1,0-1626,1626,no,no,NA,NA
+473,Mcr3-10__1795,Col,Mcr3,Mcr3-10,1795,MG214531.1,6792-8418,1626,no,no,NA,NA
+473,Mcr3-11__1796,Col,Mcr3,Mcr3-11,1796,MG489958.1,0-1626,1626,no,no,NA,NA
+473,Mcr3-12__1797,Col,Mcr3,Mcr3-12,1797,MG564491.1,0-1626,1626,no,no,NA,NA
+474,Mcr4-1__1761,Col,Mcr4,Mcr4-1,1761,MF543359,5808-7433,1626,no,no,NA,NA
+474,Mcr4-2__1798,Col,Mcr4,Mcr4-2,1798,MG581979.1,9-1630,1621,no,no,NA,NA
 475,IRI__1762,Rif,IRI,IRI,1762,U56415,280-1719,1440,no,no,NA,NA
 476,CmlB1__1763,Phe,CmlB1,CmlB1,1763,NG_047658,101-1366,1266,no,no,NA,NA
 477,ADC-25__1764,Bla,ADC,ADC-25,1764,EF016355,1-1152,1152,no,no,class C beta-lactamase,Bla
@@ -1779,9 +1797,13 @@ clusterid,queryID,class,gene,allele,seqID,accession,positions,size,cluster_conta
 478,AQU1__1782,Bla,CEPH-AQU,AQU1,1782,AB765395,1-1143,1143,no,no,NA,NA
 478,AQU2__1783,Bla,CEPH-AQU,AQU2,1783,KF730243,1-1143,1143,no,no,NA,NA
 478,AQU3__1784,Bla,CEPH-AQU,AQU3,1784,KF730244,1-1149,1149,no,no,NA,NA
+478,Mcr5-1__1799,Col,Mcr5,Mcr5-1,1799,KY807920.1,9895-11539,1644,no,no,NA,NA
+478,Mcr5-2__1800,Col,Mcr5,Mcr5-2,1800,MG384740.1,1-1641,1641,no,no,NA,NA
 479,SRT-1__1785,Bla,SRT-SST,SRT-1,1785,AB008454,154-1290,1137,no,no,class C extended-spectrum beta-lactamase,Bla_ESBL
 479,SST-1__1786,Bla,SRT-SST,SST-1,1786,AB008455,152-1288,1137,no,no,cephalosporin-hydrolyzing class C beta-lactamase,Bla
+479,Mcr6-1__1801,Col,Mcr6,Mcr6-1,1801,MF176240.1,1-1617,1617,no,no,NA,NA
 480,DES-1__1787,Bla,DES,DES-1,1787,AF426161,119-1093,975,no,no,class A extended-spectrum beta-lactamase,Bla_ESBL
+480,Mcr7-1__1802,Col,Mcr7,Mcr7-1,1802,MG267386.1,23609-25229,1621,no,no,NA,NA
 481,THIN-B__1788,Bla,THIN,THIN-B,1788,AJ250876,37-987,951,no,no,NA,NA
 482,BRO-1__1789,Bla,BRO,BRO-1,1789,Z54180,84-1028,945,no,no,class A beta-lactamase,Bla
 482,BRO-2__1790,Bla,BRO,BRO-2,1790,Z54181,63-1007,945,no,no,class A beta-lactamase,Bla
@@ -1829,3 +1851,5 @@ clusterid,queryID,class,gene,allele,seqID,accession,positions,size,cluster_conta
 511,NimB__1833,Ntmdz,NimB,NimB,1833,X71443,794-1288,495,no,no,NA,NA
 512,FosX__1834,Fcyn,FosX,FosX,1834,AP010904,1708924-1709388,465,no,no,NA,NA
 513,FosA2__1735,Fcyn,FosA2,FosA2,1735,EU487198,217-642,426,no,no,NA,NA
+514,TetX3__1838,Tgc,TetX,TetX3,1838,MK134375.1,6174-7340,1167,no,no,NA,NA
+514,TetX4__1839,Tgc,TetX,TetX4,1839,MK134376.1,325-1482,1158,no,no,NA,NA