Merge pull request #80 from NBISweden/2.3.0

* Remove python_version>="3.8.0" from install_requires section in setup.py that was not working properly. Use instead old fashion test e.g. if sys.version_info < (3,9): sys.exit('Sorry, Python >= 3.9 is required') This change fix Installation issue EMBLmyGFF3 & python version requirements #79 , fix if I can specify certain python source during python setup.py install #77 * Update test : Remove dates for comparison between expected output and result (DT and RL lines). Change taxonomy for prokka test that has recently changed in NCBI taxonomy DB. * Move minimum python requirement from python 3.8 to python 3.9 due to solve some dependencies requirement issues * fix Not for ENA submission: Sequence too short #78 add possibility to avoid to skip short sequences (< 100 nt) * Change badge in Readme for CI
NBISweden · Sep 1, 2023 · d7a7f35 · d7a7f35
2 parents 975eb31 + d9f951f
commit d7a7f35
Show file tree

Hide file tree

Showing 20 changed files with 126 additions and 229 deletions.
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
@@ -16,7 +16,7 @@ jobs:
     strategy:
       matrix:
         # Run in all these versions of Python
-        python-version: [3.8, 3.9]
+        python-version: [3.9, '3.10', 3.11]
 
     # Steps represent a sequence of tasks that will be executed as part of the job
     steps:

diff --git a/EMBLmyGFF3/EMBLmyGFF3.py b/EMBLmyGFF3/EMBLmyGFF3.py
@@ -1299,6 +1299,7 @@ def main():
     parser.add_argument("--force_uncomplete_features", action="store_true", help="Force to keep features whithout all the mandatory qualifiers. /!\ Option not suitable for submission purpose.")
     parser.add_argument("--interleave_genes", action="store_false", help="Print gene features with interleaved mRNA and CDS features.")
     parser.add_argument("--keep_duplicates", action="store_true", help="Do not remove duplicate features during the process. /!\ Option not suitable for submission purpose.")
+    parser.add_argument("--keep_short_sequences", action="store_true", help="Do not skip short sequences (<100bp). /!\ Option not suitable for submission purpose.")
     parser.add_argument("--locus_numbering_start", default=1, type=int, help="Start locus numbering with the provided value.")
     parser.add_argument("--no_progress", action="store_false", help="Hide conversion progress counter.")
     parser.add_argument("--no_wrap_qualifier", action="store_true", help="By default there is a line wrapping at 80 characters. The cut is at the world level. Activating this option will avoid the line-wrapping for the qualifiers.")
@@ -1472,9 +1473,11 @@ def main():
                             "For you information, if you use the --translate option the tool will raise an error due to ??? codons that do not exist." % (record.id))
 
         # Check sequence size and skip if < 100 bp
-        if len(record.seq)<100:
-            logging.warning("Sequence %s too short (%s bp)! Minimum accpeted by ENA is 100, we skip it !" % (record.name, len(record.seq) ) )
-            continue
+        if not args.keep_short_sequences:
+            if len(record.seq)<100:
+                logging.warning("Sequence %s too short (%s bp)! Minimum accpeted by ENA is 100, we skip it !" % (record.name, len(record.seq) ) )
+                continue
+
         writer = EMBL( record, True )
 
         # qualifiers / features json information

diff --git a/EMBLmyGFF3/modules/help.py b/EMBLmyGFF3/modules/help.py
@@ -569,6 +569,13 @@ def Help(string):
 Bolean - Doesnt expect any value
 Do not remove duplicate features during the process. 
 /!\ Option not suitable for submission purpose. Features that have the same key (feature type) and location as another feature are considered as duplicates and aren't allowed by the EMBL database. So they are remove during the process. If you don't plan to submit the file to ENA and you wish to keep these features, use the --keep_duplicates option.
+""" 
+  if(string == "keep_short_sequences" or string == "all"):
+    output += string+""":
+EMBLmyGFF3 tool specific
+Bolean - Doesnt expect any value
+Do not remove short sequences (< 100bp) during the process. 
+/!\ Option not suitable for submission purpose.
 """ 
   if(string == "force_unknown_features" or string == "all"):
     output += string+""":

diff --git a/EMBLmyGFF3/version.py b/EMBLmyGFF3/version.py
@@ -1 +1 @@
-__version__ = '2.2'
+__version__ = '2.3'
diff --git a/README.md b/README.md
@@ -1,6 +1,5 @@
-
-
-[![Build Status](https://travis-ci.org/NBISweden/EMBLmyGFF3.svg?branch=master)](https://travis-ci.org/NBISweden/EMBLmyGFF3) [![DOI](EMBLmyGFF3.svg)](https://doi.org/10.1186/s13104-018-3686-x) 
+![GitHub CI](https://github.com/NBISweden/EMBLmyGFF3/actions/workflows/main.yml/badge.svg)
+[![DOI](EMBLmyGFF3.svg)](https://doi.org/10.1186/s13104-018-3686-x) 
 [![install with bioconda](https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg?style=flat)](http://bioconda.github.io/recipes/emblmygff3/README.html) 
 [![Anaconda-Server Badge](https://img.shields.io/conda/dn/bioconda/emblmygff3.svg?style=flat)](https://anaconda.org/bioconda/emblmygff3) 
 [<img alt="docker_emblmygff3" src="https://img.shields.io/badge/container-Docker-blue">](https://quay.io/repository/biocontainers/emblmygff3)
@@ -62,7 +61,7 @@ __You don't know how to submit to ENA ? Please visit the [ENA: Guidelines and Ti
 
 ## Prerequisites
 
-**Python >=3.8**, **biopython >=1.78**, **numpy >=1.22** and the **bcbio-gff >=0.6.4** python packages.
+**Python >=3.9**, **biopython >=1.78**, **numpy >=1.22** and the **bcbio-gff >=0.6.4** python packages.
 
 In order to install pip please use the following steps:
 
@@ -321,6 +320,7 @@ You can also find a comprehensive help about the different parameters using the
 |  --isolate|             Individual isolate from which the sequence was obtained. May be needed when organism belongs to Bacteria.|
 |  --isolation_source|    Describes the physical, environmental and/or local geographical source of the biological sample from which the sequence was derived. Mandatory when environmental_sample option used.|
 |  --keep_duplicates|       Do not remove duplicate features during the process. /!\ Option not suitable for submission purpose.|
+|  --keep_short_sequences|       Do not remove short sequences (< 100bp) during the process. /!\ Option not suitable for submission purpose.|
 |  --locus_numbering_start| Start locus numbering with the provided value.|
 |  --no_progress|         Hide conversion progress counter.|
 |  --no_wrap_qualifier|   By default there is a line wrapping at 80 characters. The cut is at the world level. Activating this option will avoid the line-wrapping for the qualifiers.|

diff --git a/conda_environment_EMBLmyGFF3.yml b/conda_environment_EMBLmyGFF3.yml
@@ -6,7 +6,7 @@ channels:
   - defaults
 
 dependencies:
-  - python>=3.8.0
+  - python>=3.9.0
   - biopython>=1.78
   - bcbio-gff>=0.6.4
   - numpy>=1.22
diff --git a/examples/aa_example.py b/examples/aa_example.py
@@ -42,7 +42,7 @@ def main():
 	MOLECULE="genomic DNA"
 
 	#Create the command
-	command = "EMBLmyGFF3 --translate --rg REFERENCE_GROUP -i "+LOCUS_TAG+" -p "+PROJECT+" -m \""+MOLECULE+"\" -r "+TABLE+" -t linear -s \""+SPECIES+"\" -x "+TAXONOMY+" -o EMBLmyGFF3-aa-example.embl "+fill_path(ANNOTATION)+" "+fill_path(GENOME)
+	command = "EMBLmyGFF3 --no_progress --translate --rg REFERENCE_GROUP -i "+LOCUS_TAG+" -p "+PROJECT+" -m \""+MOLECULE+"\" -r "+TABLE+" -t linear -s \""+SPECIES+"\" -x "+TAXONOMY+" -o EMBLmyGFF3-aa-example.embl "+fill_path(ANNOTATION)+" "+fill_path(GENOME)
 	print("Running the following command: "+command)
 
 	#Execute the command

diff --git a/examples/augustus_example.py b/examples/augustus_example.py
@@ -42,7 +42,7 @@ def main():
 	MOLECULE="genomic DNA"
 
 	#Create the command
-	command = "EMBLmyGFF3 --rg REFERENCE_GROUP -i "+LOCUS_TAG+" -p "+PROJECT+" -m \""+MOLECULE+"\" -r "+TABLE+" -t linear -s \""+SPECIES+"\" -x "+TAXONOMY+" -o EMBLmyGFF3-augustus-example.embl "+fill_path(ANNOTATION)+" "+fill_path(GENOME)
+	command = "EMBLmyGFF3 --no_progress --rg REFERENCE_GROUP -i "+LOCUS_TAG+" -p "+PROJECT+" -m \""+MOLECULE+"\" -r "+TABLE+" -t linear -s \""+SPECIES+"\" -x "+TAXONOMY+" -o EMBLmyGFF3-augustus-example.embl "+fill_path(ANNOTATION)+" "+fill_path(GENOME)
 	print("Running the following command: "+command)
 
 	#Execute the command

diff --git a/examples/dbxref_test_example.py b/examples/dbxref_test_example.py
@@ -42,7 +42,7 @@ def main():
 	MOLECULE="genomic DNA"
 
 	#Create the command
-	command = "EMBLmyGFF3 --rg REFERENCE_GROUP -i "+LOCUS_TAG+" -p "+PROJECT+" -m \""+MOLECULE+"\" -r "+TABLE+" -t linear -s \""+SPECIES+"\" -x "+TAXONOMY+" -o EMBLmyGFF3-dbxref_test-example.embl "+fill_path(ANNOTATION)+" "+fill_path(GENOME)
+	command = "EMBLmyGFF3 --no_progress --rg REFERENCE_GROUP -i "+LOCUS_TAG+" -p "+PROJECT+" -m \""+MOLECULE+"\" -r "+TABLE+" -t linear -s \""+SPECIES+"\" -x "+TAXONOMY+" -o EMBLmyGFF3-dbxref_test-example.embl "+fill_path(ANNOTATION)+" "+fill_path(GENOME)
 	print("Running the following command: "+command)
 
 	#Execute the command

diff --git a/examples/maker_example.py b/examples/maker_example.py
@@ -42,7 +42,7 @@ def main():
 	MOLECULE="genomic DNA"
 
 	#Create the command
-	command = "EMBLmyGFF3 --rg REFERENCE_GROUP -i "+LOCUS_TAG+" -p "+PROJECT+" -m \""+MOLECULE+"\" -r "+TABLE+" -t linear -s \""+SPECIES+"\" -x "+TAXONOMY+" -o EMBLmyGFF3-maker-example.embl "+fill_path(ANNOTATION)+" "+fill_path(GENOME)
+	command = "EMBLmyGFF3 --no_progress --rg REFERENCE_GROUP -i "+LOCUS_TAG+" -p "+PROJECT+" -m \""+MOLECULE+"\" -r "+TABLE+" -t linear -s \""+SPECIES+"\" -x "+TAXONOMY+" -o EMBLmyGFF3-maker-example.embl "+fill_path(ANNOTATION)+" "+fill_path(GENOME)
 	print("Running the following command: "+command)
 
 	#Execute the command

diff --git a/examples/prokka_disorder_example.py b/examples/prokka_disorder_example.py
@@ -48,7 +48,7 @@ def main():
 	STRAIN="K-12"
 
 	#Create the command
-	command = "EMBLmyGFF3 --rg REFERENCE_GROUP -i "+LOCUS_TAG+" -p "+PROJECT+" -m \""+MOLECULE+"\" -r "+TABLE+" -t "+TOPOLOGY+" --strain \""+STRAIN+"\" -s \""+SPECIES+"\" -x "+TAXONOMY+" -o EMBLmyGFF3-prokka_disorder-example.embl "+fill_path(ANNOTATION)+" "+fill_path(GENOME)
+	command = "EMBLmyGFF3 --no_progress --rg REFERENCE_GROUP -i "+LOCUS_TAG+" -p "+PROJECT+" -m \""+MOLECULE+"\" -r "+TABLE+" -t "+TOPOLOGY+" --strain \""+STRAIN+"\" -s \""+SPECIES+"\" -x "+TAXONOMY+" -o EMBLmyGFF3-prokka_disorder-example.embl "+fill_path(ANNOTATION)+" "+fill_path(GENOME)
 	print("Running the following command: "+command)
 
 	#Execute the command

diff --git a/examples/prokka_example.py b/examples/prokka_example.py
@@ -48,7 +48,7 @@ def main():
 	STRAIN="K-12"
 
 	#Create the command
-	command = "EMBLmyGFF3 --rg REFERENCE_GROUP -i "+LOCUS_TAG+" -p "+PROJECT+" -m \""+MOLECULE+"\" -r "+TABLE+" -t "+TOPOLOGY+" --strain \""+STRAIN+"\" -s \""+SPECIES+"\" -x "+TAXONOMY+" -o EMBLmyGFF3-prokka-example.embl "+fill_path(ANNOTATION)+" "+fill_path(GENOME)
+	command = "EMBLmyGFF3 --no_progress --rg REFERENCE_GROUP -i "+LOCUS_TAG+" -p "+PROJECT+" -m \""+MOLECULE+"\" -r "+TABLE+" -t "+TOPOLOGY+" --strain \""+STRAIN+"\" -s \""+SPECIES+"\" -x "+TAXONOMY+" -o EMBLmyGFF3-prokka-example.embl "+fill_path(ANNOTATION)+" "+fill_path(GENOME)
 	print("Running the following command: "+command)
 
 	#Execute the command

diff --git a/setup.py b/setup.py
@@ -1,6 +1,11 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 
+# Check python version - it is not possible to specify which Python version to use in the setup.py file
+import sys
+if sys.version_info < (3,9):
+    sys.exit('Sorry, Python >= 3.9 is required')
+
 from setuptools import setup, find_packages
 
 # access the version wihtout importing the EMBLmyGFF3 package
@@ -19,7 +24,7 @@
     license='GPL-3.0',
     packages=find_packages(),
 
-    install_requires=['biopython>=1.78', 'bcbio-gff>=0.6.4','numpy>=1.22', 'python_version>="3.8.0"' ],
+    install_requires=['biopython>=1.78', 'bcbio-gff>=0.6.4','numpy>=1.22'],
     include_package_data=True,
 
     entry_points={

diff --git a/t/EMBLmyGFF3-aa-test.embl b/t/EMBLmyGFF3-aa-test.embl
@@ -6,7 +6,6 @@ AC * _4
 XX
 PR   Project:17285;
 XX
-DT   02-SEP-2022 (Rel. 133, Created)
 XX
 DE   XXX
 XX
@@ -26,7 +25,6 @@ RN   [1]
 RP   1-1351857
 RG   REFERENCE_GROUP
 RT   ;
-RL   Submitted (02-SEP-2022) to the INSDC.
 XX
 FH   Key             Location/Qualifiers
 FH

diff --git a/t/EMBLmyGFF3-augustus-test.embl b/t/EMBLmyGFF3-augustus-test.embl
@@ -6,7 +6,6 @@ AC * _4
 XX
 PR   Project:17285;
 XX
-DT   04-MAR-2021 (Rel. 133, Created)
 XX
 DE   XXX
 XX
@@ -26,7 +25,6 @@ RN   [1]
 RP   1-1351857
 RG   REFERENCE_GROUP
 RT   ;
-RL   Submitted (04-MAR-2021) to the INSDC.
 XX
 FH   Key             Location/Qualifiers
 FH

diff --git a/t/EMBLmyGFF3-dbxref_test-test.embl b/t/EMBLmyGFF3-dbxref_test-test.embl
@@ -6,7 +6,6 @@ AC * _4
 XX
 PR   Project:17285;
 XX
-DT   02-SEP-2022 (Rel. 133, Created)
 XX
 DE   XXX
 XX
@@ -26,7 +25,6 @@ RN   [1]
 RP   1-1351857
 RG   REFERENCE_GROUP
 RT   ;
-RL   Submitted (02-SEP-2022) to the INSDC.
 XX
 FH   Key             Location/Qualifiers
 FH

diff --git a/t/EMBLmyGFF3-maker-test.embl b/t/EMBLmyGFF3-maker-test.embl
@@ -6,7 +6,6 @@ AC * _4
 XX
 PR   Project:17285;
 XX
-DT   04-MAR-2021 (Rel. 133, Created)
 XX
 DE   XXX
 XX
@@ -26,7 +25,6 @@ RN   [1]
 RP   1-1351857
 RG   REFERENCE_GROUP
 RT   ;
-RL   Submitted (04-MAR-2021) to the INSDC.
 XX
 FH   Key             Location/Qualifiers
 FH