MANIFEST.in

+include LICENSE
+include README.md
+include MANIFEST.in
+include version.py
+include setup.py
+include seqsero2_db/antigens.pickle
+include seqsero2_db/H_and_O_and_specific_genes.fasta
+include seqsero2_db/invA_mers_dict
+include seqsero2_db/special.pickle
+include bin/deinterleave_fastq.sh

README.md

-# SeqSero2 alpha-test version
-Salmonella serotyping from genome sequencing data
+# SeqSero2 v1.0.1
+Salmonella serotype prediction from genome sequencing data.
 
+Online version: http://www.denglab.info/SeqSero2
 
 # Introduction 
-SeqSero2 is a pipeline for Salmonella serotype determination from raw sequencing reads or genome assemblies. This is a alpha test version. A web app will be available soon.
-
+SeqSero2 is a pipeline for Salmonella serotype prediction from raw sequencing reads or genome assemblies
 
 # Dependencies 
-SeqSero has two modes:
-
+SeqSero has three workflows:
 
-(A) k-mer based mode (default), which applies unique k-mers of serotype determinant alleles to determine Salmonella serotypes in a fast speed. Special thanks to Dr. Hendrik Den Bakker for his significant contribution to this mode, details can be found in [SeqSeroK](https://github.com/hcdenbakker/SeqSeroK) and [SalmID](https://github.com/hcdenbakker/SalmID).
+(A) Allele micro-assembly (default). This workflow takes raw reads as input and performs targeted assembly of serotype determinant alleles. Assembled alleles are used to predict serotype and flag potential inter-serotype contamination in sequencing data (i.e., presence of reads from multiple serotypes due to, for example, cross or carryover contamination during sequencing). 
 
-K-mer mode is a independant pipeline, it only requires:
+Allele micro-assembly workflow depends on:
 
 1. Python 3;
-2. [SRA Toolkit](http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?cmd=show&f=software&m=software&s=software) (optional, just used to fastq-dump sra files);
 
+2. [Burrows-Wheeler Aligner v0.7.12](http://sourceforge.net/projects/bio-bwa/files/);
 
-(B) allele based mode (if users want to extract serotype determinant alleles), which applies a hybrid approach of reads-mapping and micro-assembly.
+3. [Samtools v1.8](http://sourceforge.net/projects/samtools/files/samtools/);
 
-Allele mode depends on:
+4. [NCBI BLAST v2.2.28+](https://blast.ncbi.nlm.nih.gov/Blast.cgi?PAGE_TYPE=BlastDocs&DOC_TYPE=Download);
 
-1. Python 3; 
+5. [SRA Toolkit v2.8.0](http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?cmd=show&f=software&m=software&s=software);
 
-2. [Burrows-Wheeler Aligner](http://sourceforge.net/projects/bio-bwa/files/); 
+6. [SPAdes v3.9.0](http://bioinf.spbau.ru/spades);
 
-3. [Samtools](http://sourceforge.net/projects/samtools/files/samtools/);
+7. [Bedtools v2.17.0](http://bedtools.readthedocs.io/en/latest/);
 
-4. [NCBI BLAST](https://blast.ncbi.nlm.nih.gov/Blast.cgi?PAGE_TYPE=BlastDocs&DOC_TYPE=Download);
+8. [SalmID v0.11](https://github.com/hcdenbakker/SalmID).
 
-5. [SRA Toolkit](http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?cmd=show&f=software&m=software&s=software);
 
-6. [SPAdes](http://bioinf.spbau.ru/spades);
+(B) Raw reads k-mer. This workflow takes raw reads as input and performs rapid serotype prediction based on unique k-mers of serotype determinants. 
+
+Raw reads k-mer workflow (originally SeqSeroK) depends on:
+
+1. Python 3;
+2. [SRA Toolkit](http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?cmd=show&f=software&m=software&s=software) (optional, just used to fastq-dump sra files);
 
-7. [Bedtools](http://bedtools.readthedocs.io/en/latest/);
 
-8. [SalmID](https://github.com/hcdenbakker/SalmID).
+(C) Genome assembly k-mer. This workflow takes genome assemblies as input and the rest of the workflow largely overlaps with the raw reads k-mer workflow
 
 
 # Executing the code 
@@ -44,7 +46,7 @@ Make sure all SeqSero2 and its dependency executables are added to your path (e.
 
     Usage: SeqSero2_package.py 
 
-    -m <string> (which mode to apply, 'k'(kmer mode), 'a'(allele mode), default=k)
+    -m <string> (which workflow to apply, 'a'(raw reads allele micro-assembly), 'k'(raw reads and genome assembly k-mer), default=a)
 
     -t <string> (input data type, '1' for interleaved paired-end reads, '2' for separated paired-end reads, '3' for single reads, '4' for genome assembly, '5' for nanopore fasta, '6'for nanopore fastq)
 
@@ -56,23 +58,26 @@ Make sure all SeqSero2 and its dependency executables are added to your path (e.
  
     -d <string> (output directory name, if not set, the output directory would be 'SeqSero_result_'+time stamp+one random number)
 	
-	-c <flag> (if '-c' was flagged, SeqSero2 will use clean mode and only output serotyping prediction without the directory containing log files)
+    -c <flag> (if '-c' was flagged, SeqSero2 will only output serotype prediction without the directory containing log files)
     
+    --check <flag> (use '--check' flag to check the required dependencies)
     
-# Examples
-K-mer mode:
+    -v, --version (show program's version number and exit)
 	
-    # K-mer (default), for separated paired-end raw reads ("-t 2")
-	SeqSero2_package.py -t 2 -i R1.fastq.gz R2.fastq.gz
-	
-	# K-mer (default), for assemblies ("-t 4", assembly only predcited by K-mer mode)
-	SeqSero2_package.py -t 4 -i assembly.fasta
 
+# Examples
 Allele mode:
 
-    # Allele mode ("-m a"), for separated paired-end raw reads ("-t 2"), use 10 threads in mapping and assembly ("-p 10")
-	SeqSero2_package.py -m a -p 10 -t 2 -i R1.fastq.gz R2.fastq.gz
+    # Allele workflow ("-m a", default), for separated paired-end raw reads ("-t 2"), use 10 threads in mapping and assembly ("-p 10")
+    SeqSero2_package.py -p 10 -t 2 -i R1.fastq.gz R2.fastq.gz
+	
+K-mer mode:
+
+    # Raw reads k-mer ("-m k"), for separated paired-end raw reads ("-t 2")
+    SeqSero2_package.py -m k -t 2 -i R1.fastq.gz R2.fastq.gz
 
+    # Genome assembly k-mer ("-t 4", genome assemblies only predicted by the k-mer workflow, "-m k")
+    SeqSero2_package.py -m k -t 4 -i assembly.fasta
 	
 # Output 
 Upon executing the command, a directory named 'SeqSero_result_Time_your_run' will be created. Your result will be stored in 'Seqsero_result.txt' in that directory. And the assembled alleles can also be found in the directory if using "-m a" (allele mode).

debian/changelog

-seqsero2 (0.1-1) UNRELEASED; urgency=medium
+seqsero2 (1.0.2-1) UNRELEASED; urgency=medium
 
   * Initial release (Closes: #??)
 
- -- Andreas Tille <tille@debian.org>  Thu, 31 Jan 2019 08:16:55 +0100
+ -- Andreas Tille <tille@debian.org>  Wed, 11 Dec 2019 16:19:03 +0100

debian/compat

-11

debian/control

@@ -3,24 +3,28 @@ Maintainer: Debian Med Packaging Team <debian-med-packaging@lists.alioth.debian.
 Uploaders: Andreas Tille <tille@debian.org>
 Section: science
 Priority: optional
-Build-Depends: debhelper (>= 11~),
+Build-Depends: debhelper-compat (= 12),
                dh-python,
-               python,
+               python3,
                bwa,
                sra-toolkit
-Standards-Version: 4.2.1
+Standards-Version: 4.4.1
 Vcs-Browser: https://salsa.debian.org/med-team/seqsero2
 Vcs-Git: https://salsa.debian.org/med-team/seqsero2.git
 Homepage: https://github.com/denglab/SeqSero2
 
 Package: seqsero2
 Architecture: all
-Depends: ${python:Depends},
+Depends: ${python3:Depends},
          ${misc:Depends},
          python-biopython,
          bwa,
          samtools,
-         sra-toolkit
+         ncbi-blast+,
+         sra-toolkit,
+         spades,
+         bedtools,
+         salmid
 Description: Salmonella serotyping from genome sequencing data
  SeqSero2 is a pipeline for Salmonella serotype determination from raw
  sequencing reads or genome assemblies.

debian/rules

@@ -3,7 +3,7 @@
 # DH_VERBOSE := 1
 
 %:
-	dh $@ --with python2
+	dh $@ --with python3 --buildsystem=pybuild
 
 override_dh_fixperms:
 	dh_fixperms

debian/upstream/metadata

@@ -25,3 +25,6 @@ Registry:
   Entry: seqsero2
 - Name: SciCrunch
   Entry: NA
+Bug-Database: https://github.com/denglab/SeqSero2/issues
+Repository: https://github.com/denglab/SeqSero2.git
+Repository-Browse: https://github.com/denglab/SeqSero2

setup.py

+import os, sys
+from distutils.core import setup
+from setuptools import find_packages
+
+def readme():
+    with open('README.md') as f:
+        return f.read()
+
+setup(name='SeqSero2',
+    version=open("version.py").readlines()[-1].split()[-1].strip("\"'"),
+    description='Salmonella serotyping',
+    long_description=readme(),
+    classifiers=[
+        'Development Status :: 3 - Alpha',
+        'License :: OSI Approved :: GNU General Public License v2 (GPLv2)',
+        'Programming Language :: Python :: 3',
+        'Topic :: Text Processing :: Linguistic',
+        ],
+    keywords='Salmonella serotyping bioinformatics WGS',
+    url='https://github.com/denglab/SeqSero2/',
+    author='Shaokang Zhang, Hendrik C Den-Bakker and Xiangyu Deng',
+    author_email='zskzsk@uga.edu, Hendrik.DenBakker@uga.edu, xdeng@uga.edu',
+    license='GPLv2',
+    scripts=["bin/deinterleave_fastq.sh","bin/Initial_Conditions.py","bin/SeqSero2_package.py","bin/SeqSero2_update_kmer_database.py"],
+    packages=[""],
+    include_package_data = True,
+    install_requires=['biopython==1.73'],
+    data_files=[("seqsero2_db",["seqsero2_db/antigens.pickle","seqsero2_db/H_and_O_and_specific_genes.fasta","seqsero2_db/invA_mers_dict","seqsero2_db/special.pickle"])],
+    zip_safe=False,
+)

version.py

+SeqSero2_version = '1.0.2'