README.md

+[![DOI](https://zenodo.org/badge/97020646.svg)](https://zenodo.org/badge/latestdoi/97020646)
+
 # SalmID
 Rapid tool to check taxonomic ID of single isolate samples. Currently only IDs Salmonella species and subspecies, and some common contaminants (Listeria, Escherichia).
 
@@ -5,26 +7,34 @@ Rapid tool to check taxonomic ID of single isolate samples. Currently only IDs S
 Python 3
 
 ## Installation:
-Clone git to your machine:
+The easy way with homebrew ([Linux](http://linuxbrew.sh/) or [MacOS](https://brew.sh/)):
 ```
-git clone --recursive https://github.com/hcdenbakker/SalmID.git
+brew install brewsci/bio/salmid
 ```
+Big thanks to [Torsten Seemann](https://tseemann.github.io/) for including this in homebrew!
 
-Make SalmID executable:
-```
-cd SalmID
-```
+Alternatively download from GitHub:
 
+```bash
+git clone https://github.com/hcdenbakker/SalmID.git
 ```
-chmod +x SalmID.py
+
+build a wheel using [poetry](https://poetry.eustace.io/):
+
+```bash
+cd SalmID
+poetry build
 ```
 
+and install using `pip`
 
-Add the SalmID folder to your path
+```bash
+pip install dist/salmid*.whl
+```
 
 To execute:
 ```
-SalmID.py
+SalmID.py -e .fastq.gz
 ```
 This will perform a SalmID run on all fastq.gz files in the current directory.
 ```

pyproject.toml

+[tool.poetry]
+name = "salmid"
+version = "0.1.23"
+description = "Rapid tool to check taxonomic ID of single isolate samples. Currently only IDs Salmonella species and subspecies, and some common contaminants (Listeria, Escherichia)."
+authors = ["Henk den Bakker <hcd82599@uga.edu>"]
+license = "MIT"
+include = [ 'salmid/invA_mers_dict', 'salmid/rpoB_mers_dict' ]
+
+[tool.poetry.dependencies]
+python = "^3.5"
+
+[tool.poetry.dev-dependencies]
+
+[tool.poetry.scripts]
+'SalmID.py' = 'salmid.core:main'
+
+[build-system]
+requires = ["poetry>=0.12"]
+build-backend = "poetry.masonry.api"

SalmID.py → salmid/core.py

@@ -9,12 +9,13 @@ import sys
 
 from argparse import ArgumentParser
 try:
-	from version import SalmID_version
-except:
+    from .version import SalmID_version
+except ImportError:
     SalmID_version = "version unknown"
 
 
 def reverse_complement(sequence):
+    """return the reverse complement of a nucleotide (including IUPAC ambiguous nuceotide codes)"""
     complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A', 'N': 'N', 'M': 'K', 'R': 'Y', 'W': 'W',
                             'S': 'S', 'Y': 'R', 'K': 'M', 'V': 'B', 'H': 'D', 'D': 'H', 'B': 'V'}
     return "".join(complement[base] for base in reversed(sequence))
@@ -48,7 +49,9 @@ def parse_args():
         sys.exit(1)
     return parser.parse_args()
 
+
 def get_av_read_length(file):
+    """Samples the first 100 reads from a fastq file and return the average read length."""
     i = 1
     n_reads = 0
     total_length = 0
@@ -67,9 +70,18 @@ def get_av_read_length(file):
 
 
 def createKmerDict_reads(list_of_strings, kmer):
+    """Count occurence of K-mers in a list of strings
+
+    Args:
+        list_of_strings(list of str): nucleotide sequences as a list of strings
+        kmer(int): length of the K-mer to count
+
+    Returns:
+        dict: dictionary with kmers as keys, counts for each kmer as values"""
     kmer_table = {}
     for string in list_of_strings:
         sequence = string.strip('\n')
+        if len(sequence) >= kmer:
             for i in range(len(sequence) - kmer + 1):
                 new_mer = sequence[i:i + kmer]
                 new_mer_rc = reverse_complement(new_mer)
@@ -135,6 +147,7 @@ def target_read_kmerizer_multi(file, k, kmerDict_1, kmerDict_2, mode):
         mean_2 = sum([kmer_Dict2[key] for key in kmer_Dict2]) / len(mers_2)
     return kmer_Dict1, kmer_Dict2, mean_1, mean_2, total_reads
 
+
 def mean_cov_selected_kmers(iterable, kmer_dict, clade_specific_kmers):
     '''
     Given an iterable (list, set, dictrionary) returns mean coverage for the kmers in iterable
@@ -147,6 +160,7 @@ def mean_cov_selected_kmers(iterable, kmer_dict, clade_specific_kmers):
         return 0
     return sum([kmer_dict[value] for value in iterable]) / len(clade_specific_kmers)
 
+
 def kmer_lists(query_fastq_gz, k,
                allmers, allmers_rpoB,
                uniqmers_bongori,
@@ -214,14 +228,15 @@ def kmer_lists(query_fastq_gz, k,
                         p_I, p_IIa, p_IIb, p_IIIa, p_IIIb, p_IV, p_VI, p_VII, p_VIII]
     return locus_scores, coverages, total_reads
 
+
 def report_taxon(locus_covs, average_read_length, number_of_reads):
-    list_taxa = [ 'Listeria ss', 'Listeria monocytogenes', 'Escherichia sp.',
+    list_taxa = [ 'Listeria ss', 'Listeria monocytogenes', 'Escherichia sp.',  # noqa: E201
                   'Salmonella bongori (rpoB)', 'Salmonella enterica (rpoB)',
                   'Salmonella bongori (invA)', 'S. enterica subsp. enterica (invA)',
                   'S. enterica subsp. salamae (invA: clade a)', 'S. enterica subsp. salamae (invA: clade b)',
                   'S. enterica subsp. arizonae (invA)', 'S. enterica subsp. diarizonae (invA)',
                   'S. enterica subsp. houtenae (invA)', 'S. enterica subsp. indica (invA)',
-                  'S. enterica subsp. VII (invA)', 'S. enterica subsp. salamae (invA: clade VIII)']
+                  'S. enterica subsp. VII (invA)', 'S. enterica subsp. salamae (invA: clade VIII)' ]  # noqa: E202
     if sum(locus_covs) < 1:
         rpoB = ('No rpoB matches!', 0)
         invA = ('No invA matches!', 0)
@@ -250,7 +265,6 @@ def report_taxon(locus_covs, average_read_length, number_of_reads):
             return rpoB, invA, (average_read_length * number_of_reads) / 5000000
 
 
-
 def main():
     ex_dir = os.path.dirname(os.path.realpath(__file__))
     args = parse_args()
@@ -317,9 +331,9 @@ def main():
                   '\t' + str(round(report[2], 1)))
     else:
         print(
-        'file\tListeria sensu stricto (rpoB)\tL. monocytogenes (rpoB)\tEscherichia spp. (rpoB)\tS. bongori (rpoB)\tS. enterica' +
-        '(rpoB)\tS. bongori (invA)\tsubsp. I (invA)\tsubsp. II (clade a: invA)\tsubsp. II' +
-        ' (clade b: invA)\tsubsp. IIIa (invA)\tsubsp. IIIb (invA)\tsubsp.IV (invA)\tsubsp. VI (invA)\tsubsp. VII (invA)' +
+        'file\tListeria sensu stricto (rpoB)\tL. monocytogenes (rpoB)\tEscherichia spp. (rpoB)\tS. bongori (rpoB)\tS. enterica' +  # noqa: E122
+        '(rpoB)\tS. bongori (invA)\tsubsp. I (invA)\tsubsp. II (clade a: invA)\tsubsp. II' +  # noqa: E122
+        ' (clade b: invA)\tsubsp. IIIa (invA)\tsubsp. IIIb (invA)\tsubsp.IV (invA)\tsubsp. VI (invA)\tsubsp. VII (invA)' +  # noqa: E122
         '\tsubsp. II (clade VIII : invA)')
         if report == 'percentage':
             for f in files:
@@ -366,6 +380,7 @@ def main():
                 pretty_covs = [str(round(cov, 1)) for cov in coverages]
                 print(f.split('/')[-1] + '\t' + '\t'.join(pretty_covs))
 
+
 if __name__ == '__main__':
     main()
 

salmid/version.py

+SalmID_version = '0.1.23'

version.py

-SalmID_version = '0.12'