pre-release 2.0.0a0

.gitignore

@@ -106,3 +106,6 @@ venv.bak/
 
 # vscode
 .vscode
+
+# test
+tests/_internal_

MANIFEST.in

@@ -0,0 +1,4 @@
+include tests/example*
+include tests/query*
+include primerserver2/data/*
+include example_cmd.sh

README.md

@@ -1,2 +1,10 @@
 # PrimerServer2
 PrimerServer2: a high-throughput primer design and specificity-checking platform
+
+## Description
+PrimerServer was proposed to design genome-wide specific PCR primers. It uses candidate primers produced by Primer3, uses BLAST and nucleotide thermodynamics to search for possible amplicons and filters out specific primers for each site. By using multiple threads, it runs very fast, ~0.4s per site in our case study for more than 10000 sites.
+
+## External Dependencies
+* [Samtools](http://www.htslib.org/) (>=1.9).
+* [NCBI BLAST+](https://blast.ncbi.nlm.nih.gov/Blast.cgi) (>=2.2.18)
+

example_cmd.sh

@@ -0,0 +1,5 @@
+# design primers and check specificity (the default mode)
+primertool tests/query_design_multiple tests/example.fa -p 2 -o example_design_check.json -t example_design_check.tsv
+
+# check specificity only
+primertool tests/query_check_multiple tests/example.fa --only-specificity -p 2 -o example_check.json -t example_check.tsv

primerserver2/__init__.py

@@ -0,0 +1,16 @@
+'''PrimerServer2: a high-throughput primer design and specificity-checking platform
+
+Github: https://github.com/billzt/PrimerServer2
+
+PrimerServer was proposed to design genome(or transcriptome)-wide specific PCR primers. It uses candidate primers 
+produced by Primer3, uses BLAST and nucleotide thermodynamics to search for possible amplicons and filters out 
+specific primers for each site. By using multiple CPUs, it runs very fast, ~0.4s per site in our case study for 
+more than 10000 sites.
+
+External Dependencies:
+
+blastn and makeblastdb (from NCBI BLAST+)
+
+samtools (>=v1.0)
+
+'''

primerserver2/cmd/primertool.py

@@ -0,0 +1,113 @@
+#!/usr/bin/env python3
+
+'''PrimerServer2: a high-throughput primer design and specificity-checking platform
+Github: https://github.com/billzt/PrimerServer2
+'''
+
+__author__ = 'Tao Zhu'
+__copyright__ = 'Copyright 2019'
+__license__ = 'GPL'
+__version__ = '0.1'
+__email__ = '[email protected]'
+__status__ = 'Development'
+
+import argparse
+import re
+import os
+import sys
+import json
+import shutil
+
+from distutils.version import LooseVersion
+
+from primerserver2.core import make_sites, make_primers, design_primer, run_blast, sort_primers, output
+
+
+def error(msg, judge):
+    if judge is True:
+        print(json.dumps({'ERROR': msg}))
+    raise Exception(msg)
+
+def make_args():
+    parser = argparse.ArgumentParser(description='PrimerServer2: a high-throughput primer \
+        design and specificity-checking platform', formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+    parser.add_argument('query', help='query file. (STDIN is acceptable)', type=argparse.FileType('r'))
+    parser.add_argument('template', help='template file in FASTA format')
+
+    group = parser.add_mutually_exclusive_group()
+    group.add_argument('--no-specificity', help="Don't check specificity; Only design primers", action='store_true')
+    group.add_argument('--only-specificity', help="Only check specificity and skip primer designs", action='store_true')
+    parser.add_argument('--type', choices=['SEQUENCE_TARGET', 'SEQUENCE_INCLUDED_REGION', 'FORCE_END'],\
+        help='designing primer types', default='SEQUENCE_TARGET')
+    parser.add_argument('-p', '--cpu', type=int, help='Used CPU number.', default=2)
+    parser.add_argument('-l', '--checking-size-min', type=int, help='Lower limit of the checking amplicon size range (bp).', \
+        default=70)
+    parser.add_argument('-u', '--checking-size-max', type=int, help='Upper limit of the checking amplicon size range (bp).', \
+        default=1000)
+    parser.add_argument('-r', '--primer-num-retain', type=int, help='The maximum number of primers for each site to return.', \
+        default=10)
+    parser.add_argument('-a', '--report-amplicon-seqs', help="Get amplicon seqs (might be slow)", action='store_true')
+    parser.add_argument('--json-debug', help="Output debug information in JSON mode", action='store_true')
+    parser.add_argument('-o', '--out', help="Output primers in JSON format. (Default is STDIN)", type=argparse.FileType('w'))
+    parser.add_argument('-t', '--tsv', help="Output primers in TSV format", type=argparse.FileType('w'))
+    args = parser.parse_args()
+    return args
+
+def check_environments(args):
+    if shutil.which('samtools') is None:
+        error('No samtools detected in your system', args.json_debug)
+
+    samtools_version = os.popen('samtools --version').readlines()[0].strip().split(' ')[1]
+    if LooseVersion(samtools_version) < LooseVersion('1.9'):
+        error(f'Your samtools version is v{samtools_version}, but >=v1.9 is required', args.json_debug)
+
+    if shutil.which('blastn') is None:
+        error('No NCBI-BLAST+ (blastn) detected in your system', args.json_debug)
+
+    if shutil.which('makeblastdb') is None:
+        error('No NCBI-BLAST+ (makeblastdb) detected in your system', args.json_debug)
+
+def check_template(args):
+    if os.path.isfile(args.template) is False:
+        error(f'File not found: {args.template}', args.json_debug)
+    if os.path.isfile(args.template+'.fai') is False:
+        code = os.system(f'samtools faidx {args.template} 2>/dev/null')
+        if code != 0:
+            error(f'File {args.template} cannot be indexed by samtools faidx. Perhaps it is not in FASTA format', args.json_debug)
+
+def run(args):
+    ###################  Design primers ###################
+    query_string = args.query.read()
+    if args.only_specificity is True:
+        primers = make_primers.make_primers(query=query_string)
+    else:
+        sites = make_sites.build(query=query_string, template_file=args.template, primer_type=args.type)
+        primers = design_primer.multiple(sites, cpu=args.cpu)
+
+    ###################  Checking specificity  #############
+    dbs = [args.template]
+    if args.no_specificity is False:
+        primers = run_blast.run_blast_parallel(primers=primers, dbs=dbs, cpu=args.cpu,\
+            checking_size_max=args.checking_size_max, checking_size_min=args.checking_size_min, \
+                report_amplicon_seq=args.report_amplicon_seqs)
+        primers = sort_primers.sort_rank(primers=primers, dbs=dbs, max_num_return=args.primer_num_retain)
+
+    ###################  Output  ###########################
+    if args.out is not None:
+        print(json.dumps(primers, indent=4), file=args.out)
+    else:
+        print(json.dumps(primers, indent=4))
+
+    if args.tsv is not None:
+        if args.no_specificity is False:
+            output.after_check(primers, dbs, file=args.tsv)
+
+def main():
+    args = make_args()
+    check_environments(args)
+    check_template(args)
+    run(args)
+
+if __name__ == "__main__":
+    main()
+

src/analysis_blast.py → primerserver2/core/analysis_blast.py

@@ -2,9 +2,9 @@
 import json
 import sys
 
-from make_sites import faidx
-from Santalucia_NN_Tm import complement, rev_complement, NN_Tm
-from make_primers import make_primers
+from primerserver2.core.make_sites import faidx
+from primerserver2.core.Santalucia_NN_Tm import complement, rev_complement, NN_Tm
+from primerserver2.core.make_primers import make_primers
 
 def filter_len(blast_out, len_min, len_max):
     '''
@@ -154,10 +154,10 @@ def add_amplicon_seq(amplicons, template_file):
 
 
 if __name__ == "__main__":
-    blast_out = open('tests/query_blast.fa.out').read()
+    blast_out = open('tests/_internal_/query_blast.fa.out').read()
     amplicons = filter_len(blast_out=blast_out, len_min=75, len_max=1000)
     hits_seqs = faidx(template_file='tests/example.fa', region_string=amplicons['regions_primer'])
     report_amplicons = filter_Tm(amplicons['amplicons'], query_primer_seq={'LEFT':'CTTCTGCAATGCCAAGTCCAG',\
         'RIGHT': 'GTGGTGAAGGGTCGGTTGAA'}, hits_seqs=hits_seqs)
     report_amplicons = add_amplicon_seq(amplicons=report_amplicons, template_file='tests/example.fa')
-    print(json.dumps(report_amplicons))
+    print(json.dumps(report_amplicons, indent=4))

src/design_primer.py → primerserver2/core/design_primer.py

@@ -1,10 +1,11 @@
 
 import json
+import os
 import multiprocessing as mp
 
 import primer3
 
-p3_settings = dict(json.load(open('src/p3_settings.json')))
+p3_settings = dict(json.load(open('primerserver2/data/p3_settings.json')))
 
 def single(site):
     '''
@@ -108,4 +109,4 @@ def multiple(sites, cpu=2):
                 'size_min':75,
                 'size_max':1000
             }
-            ])))
+            ]), indent=4))

src/make_primers.py → primerserver2/core/make_primers.py

@@ -1,4 +1,5 @@
 import re
+import json
 
 import primer3
 
@@ -40,6 +41,6 @@ def make_primers(query):
     return primers
 
 if __name__ == "__main__":
-    with open('tests/query_check') as f:
+    with open('tests/_internal_/query_check') as f:
         primers = make_primers(f.read())
-        print(primers)
+        print(json.dumps(primers, indent=4))

src/make_sites.py → primerserver2/core/make_sites.py

@@ -77,6 +77,6 @@ def build(query, template_file, primer_type):
     return primer_sites
 
 if __name__ == "__main__":
-    with open('tests/query_design') as f:
+    with open('tests/query_design_multiple') as f:
         primer_sites = build(query=f.read(), template_file='tests/example.fa', primer_type='SEQUENCE_TARGET')
         print(json.dumps(primer_sites, indent=4))

src/output.py → primerserver2/core/output.py

@@ -39,6 +39,6 @@ def after_check(primers, dbs, file):
 
 
 if __name__ == "__main__":
-    primers = json.load(open('tests/sort_primers.json'))
+    primers = json.load(open('tests/_internal_/sort_primers.json'))
     dbs = ['example.fa']
     after_check(primers, dbs, file=sys.stdout)

src/run_blast.py → primerserver2/core/run_blast.py

@@ -6,9 +6,9 @@
 
 import primer3
 
-from analysis_blast import filter_len, filter_Tm, add_amplicon_seq
-from make_sites import faidx
-from make_primers import make_primers
+from primerserver2.core.analysis_blast import filter_len, filter_Tm, add_amplicon_seq
+from primerserver2.core.make_sites import faidx
+from primerserver2.core.make_primers import make_primers
 
 def run_blast(p3_input):
     '''

src/sort_primers.py → primerserver2/core/sort_primers.py

@@ -33,7 +33,7 @@ def sort_rank(primers, dbs, max_num_return=10):
     return primers
 
 if __name__ == "__main__":
-    primers = json.load(open('tests/run_blast.json'))
+    primers = json.load(open('tests/_internal_/run_blast.json'))
     dbs = ['example.fa']
-    print(json.dumps(sort_rank(primers, dbs)))
+    print(json.dumps(sort_rank(primers, dbs), indent=4))
 

setup.cfg

@@ -0,0 +1,2 @@
+[metadata]
+description-file = README.md

setup.py

@@ -1,3 +1,36 @@
 
-# primer3-py
-# flask
+from setuptools import setup, find_packages
+
+VERSION = '2.0.0a0'
+
+setup(name='primerserver2',
+      version=VERSION,
+      description="a high-throughput primer design and specificity-checking platform",
+      long_description=__doc__,
+      classifiers=[
+          'Development Status :: 2 - Pre-Alpha',
+          'Environment :: Console',
+          'Intended Audience :: Science/Research',
+          'License :: OSI Approved :: MIT License',
+          'Operating System :: Unix',
+          'Programming Language :: Python :: 3.6',
+          'Topic :: Scientific/Engineering :: Bio-Informatics'
+      ],
+      keywords='primer bioinformatics PCR',
+      author='Tao Zhu',
+      author_email='[email protected]',
+      url='https://github.com/billzt/PrimerServer2',
+      license='MIT',
+      packages=find_packages(),
+      include_package_data=True,
+      zip_safe=True,
+      python_requires='>=3.6',
+      install_requires=[
+          'primer3-py'
+      ],
+      entry_points={
+          'console_scripts': [
+              'primertool = primerserver2.cmd.primertool:main'
+          ]
+      },
+)