Issue585 and issue 614

docs/gff3_fix.md

@@ -17,15 +17,19 @@ Python 2.7
 1. Corrected GFF3
 
 ## Quick start
-`python2.7 bin/gff3_fix.py -qc_r error.txt -g example.gff3 -og corrected.gff3`
+`python2.7 bin/gff3_fix.py -qc_r error.txt -g example_file/example.gff3 -og corrected.gff3`
 
 ## Optional arguments
 
 1.  -h, --help            
     - show this help message and exit
-2.  -og OUTPUT_GFF, --output_gff OUTPUT_GFF
-    - output gff3 file name
-3.  -v, --version         
+2.  -qc_r QC_REPORT, --qc_report QC_REPORT
+    - Error report from gff3_QC.py
+3.  -g GFF, --gff GFF
+    - Genome annotation file, gff3 format
+4.  -og OUTPUT_GFF, --output_gff OUTPUT_GFF
+    - output gff3 file name (default: corrected.gff3)
+5.  -v, --version         
     - show program's version number and exit
 
 ## More information

docs/gff3_merge.md

@@ -2,7 +2,7 @@
 
 ## Usage 
 
-gff3_merge.py [-h] [-g1 GFF_FILE1] [-g2 GFF_FILE2] [-f FASTA] [-og OUTPUT_GFF] [-r REPORT_FILE] [-noAuto] [-v]
+gff3_merge.py [-h] [-g1 GFF_FILE1] [-g2 GFF_FILE2] [-f FASTA] [-u1 USER_DEFINED_FILE1] [-u2 USER_DEFINED_FILE2] [-og OUTPUT_GFF] [-r REPORT_FILE] [-a] [-noAuto] [-v]
 
 ## Testing environment
 
@@ -20,22 +20,34 @@ gff3_merge.py [-h] [-g1 GFF_FILE1] [-g2 GFF_FILE2] [-f FASTA] [-og OUTPUT_GFF] [
 
 ## Quick start
 * Merge the two files with auto-assignment of replace tags (default)
-    `python2.7 GFF3toolkit/bin/gff3_merge.py -g1 GFF3toolkit/example_file/new_models.gff3 -g2 GFF3toolkit/example_file/reference.gff3 -f GFF3toolkit/example_file/reference.fa -og merged.gff -r merged_report.txt`
+    `python2.7 bin/gff3_merge.py -g1 example_file/new_models.gff3 -g2 example_file/reference.gff3 -f example_file/reference.fa -og merged.gff -r merged_report.txt`
 
 * If your GFF3 files have proper replace tags at column 9 (Format: replace=[Transcript ID]), you can merge the two GFF3 files without auto-assignment of replace tags.
-    `python2.7 GFF3toolkit/bin/gff3_merge.py -g1 GFF3toolkit/example_file/new_models_w_replace.gff3 -g2 GFF3toolkit/example_file/reference.gff3 -f GFF3toolkit/example_file/reference.fa -og merged.gff -r merged_report.txt -noAuto`
+    `python2.7 bin/gff3_merge.py -g1 example_file/new_models_w_replace.gff3 -g2 example_file/reference.gff3 -f example_file/reference.fa -og merged.gff -r merged_report.txt -noAuto`
 
 ## Optional arguments
 
 1.  -h, --help            
     - show this help message and exit
-2.  -og OUTPUT_GFF, --output_gff OUTPUT_GFF
+2.  -g1 GFF_FILE1, --gff_file1 GFF_FILE1
+    - Updated GFF3 file, such as Apollo gff
+3.  -g2 GFF_FILE2, --gff_file2 GFF_FILE2
+    - Reference GFF3 file, such as Maker gff or OGS gff
+4.  -f FASTA, --fasta FASTA
+    - Genomic sequences in the fasta format
+5.  -u1 USER_DEFINED_FILE1, --user_defined_file1 USER_DEFINED_FILE1
+    - File for specifing parent and child features for fasta extraction from updated GFF3 file.
+6.  -u2 USER_DEFINED_FILE2, --user_defined_file2 USER_DEFINED_FILE2
+    - File for specifing parent and child features for fasta extraction from reference GFF3 file.
+7.  -og OUTPUT_GFF, --output_gff OUTPUT_GFF
     - The merged GFF3 file (default: merged.gff)
-3.  -r REPORT_FILE, --report_file REPORT_FILE
+8.  -r REPORT_FILE, --report_file REPORT_FILE
     - Log file for the integration (default: merge_report.txt)
-4.  -noAuto, --auto_assignment
+9.  -a, --all
+    - auto-assignment replace tags for all transcript features. (default: Only automatically assign replace tags for the transcript without replace tags)
+10. -noAuto, --auto_assignment
     - Turn off the auto-assignment of replace tags, if you have had the replace tags in your update gff (default: Automatically assign replace tags and then merge the gff files)
-5.  -v, --version         
+11. -v, --version
     - show program's version number and exit
 
 ## More information 

gff3tool/bin/gff3_fix.py

@@ -34,15 +34,28 @@ def script_main():
 
 
     Quick start:
-    python2.7 bin/gff3_fix.py -qc_r error.txt -g example.gff3 -og corrected.gff3
+    python2.7 bin/gff3_fix.py -qc_r error.txt -g example_file/example.gff3 -og corrected.gff3
     """))
 
     parser.add_argument('-qc_r', '--qc_report', type=str, help='Error report from gff3_QC.py')
     parser.add_argument('-g', '--gff', type=str, help='Genome annotation file, gff3 format')
     #parser.add_argument('-r', '--report', type=str, help='output report file name')
-    parser.add_argument('-og', '--output_gff', type=str, help='output gff3 file name')
+    parser.add_argument('-og', '--output_gff', type=str, help='output gff3 file name', default='corrected.gff3')
     parser.add_argument('-v', '--version', action='version', version='%(prog)s ' + __version__)
+
     args = parser.parse_args()
+    if args.qc_report:
+        logger_stderr.info('Checking QC report file (%s)...', args.qc_report)
+    else: # no input
+        parser.print_help()
+        sys.exit()
+
+    if args.gff:
+        logger_stderr.info('Checking GFF3 file (%s)...', args.gff)
+    else: # no input
+        parser.print_help()
+        sys.exit()
+
     logger_stderr.info('Reading QC report file: (%s)...\n', args.qc_report)
     #error_dict example: {'Emr0001': [[15,16],[13]],'Esf0005': [[17]]}
     error_dict = {}

gff3tool/bin/gff3_merge.py

@@ -45,7 +45,7 @@ def check_replace(gff, user_defined1=None):
         return False
 
 
-def main(gff_file1, gff_file2, fasta, report, output_gff, auto=True, user_defined1=None, user_defined2=None, logger=None):
+def main(gff_file1, gff_file2, fasta, report, output_gff, all_assign=False, auto=True, user_defined1=None, user_defined2=None, logger=None):
     logger_null = logging.getLogger(__name__+'null')
     null_handler = logging.NullHandler()
     logger_null.addHandler(null_handler)
@@ -66,8 +66,8 @@ def main(gff_file1, gff_file2, fasta, report, output_gff, auto=True, user_define
         autoReviseReport = '{0:s}/replace_tag_report.txt'.format(autoDIR)
 
         logger.info('========== Auto-assignment of replace tags for each transcript model ==========')
-        gff3_merge.auto_replace_tag.main(gff1=gff_file1, gff2=gff_file2, fasta=fasta, outdir=autoDIR, scode='TEMP', user_defined1=user_defined1, user_defined2=user_defined2, logger=logger)
-        gff3_merge.revision.main(gff_file1, autoFILE, autoReviseGff, autoReviseReport, user_defined1, auto, logger)
+        gff3_merge.auto_replace_tag.main(gff1=gff_file1, gff2=gff_file2, fasta=fasta, outdir=autoDIR, scode='TEMP', all_assign=all_assign, user_defined1=user_defined1, user_defined2=user_defined2, logger=logger)
+        gff3_merge.revision.main(gff_file=gff_file1, revision_file=autoFILE, output_gff=autoReviseGff, report_file=autoReviseReport, user_defined1=user_defined1, auto=auto, logger=logger)
 
         logger.info('========== Check whether there are missing replace tags ==========')
         gff3 = Gff3(gff_file=autoReviseGff, logger=logger_null)
@@ -141,6 +141,7 @@ def script_main():
     parser.add_argument('-u2', '--user_defined_file2', type=str, help='File for specifing parent and child features for fasta extraction from reference GFF3 file.')
     parser.add_argument('-og', '--output_gff', type=str, help='The merged GFF3 file')
     parser.add_argument('-r', '--report_file', type=str, help='Log file for the integration')
+    parser.add_argument('-a', '--all', action='store_true', help='auto-assignment replace tags for all transcript features. (default: Only automatically assign replace tags for the transcript without replace tags)')
     parser.add_argument('-noAuto', '--auto_assignment', action='store_false', help='Turn off the auto-assignment of replace tags, if you already have replace tags in your updated gff (default: Automatically assign replace tags and then merge the gff files)')
     parser.add_argument('-v', '--version', action='version', version='%(prog)s ' + __version__)
 
@@ -214,7 +215,9 @@ def script_main():
             parser.print_help()
             sys.exit(1)
 
-
+    if args.all and not args.auto_assignment:
+        logger_stderr.error('-a and -noAuto specify opposite behaviors, only one of the two arguments can be accepted.')
+        sys.exit(0)
     if args.report_file:
         logger_stderr.info('Writing validation report (%s)...\n', args.report_file)
         report_fh = open(args.report_file, 'wb')
@@ -224,4 +227,4 @@ def script_main():
     if not args.output_gff:
         args.output_gff='merged.gff'
 
-    main(args.gff_file1, args.gff_file2, args.fasta, report_fh, args.output_gff, args.auto_assignment, args.user_defined_file1, args.user_defined_file2, logger=logger_stderr)
+    main(args.gff_file1, args.gff_file2, args.fasta, report_fh, args.output_gff, args.all, args.auto_assignment, args.user_defined_file1, args.user_defined_file2, logger=logger_stderr)

gff3tool/lib/gff3_merge/auto_replace_tag.py

@@ -29,7 +29,7 @@
 __version__ = '0.0.3'
 
 
-def main(gff1, gff2, fasta, outdir, scode, logger, user_defined1=None, user_defined2=None):
+def main(gff1, gff2, fasta, outdir, scode, logger, all_assign=False, user_defined1=None, user_defined2=None):
     logger_null = logging.getLogger(__name__+'null')
     null_handler = logging.NullHandler()
     logger_null.addHandler(null_handler)
@@ -51,8 +51,12 @@ def main(gff1, gff2, fasta, outdir, scode, logger, user_defined1=None, user_defi
         roots =[]
         for line in gff3_1.lines:
             try:
-                if line['line_type'] == 'feature' and not line['attributes'].has_key('Parent') and len(line['attributes']) != 0:
-                    roots.append(line)
+                if line['line_type'] == 'feature':
+                    # remove all the replace attributes
+                    if all_assign and 'replace' in line['attributes']:
+                        del line['attributes']['replace']
+                    if 'Parent' not in line['attributes'] and len(line['attributes']) != 0:
+                        roots.append(line)
             except:
                 pass
         for root in roots:
@@ -75,11 +79,19 @@ def main(gff1, gff2, fasta, outdir, scode, logger, user_defined1=None, user_defi
         for lines in user_defined1:
             transcripts_type.add(lines[0])
         for line in gff3_1.lines:
+            if line['line_type'] == 'feature':
+                if all_assign and 'replace' in line['attributes']:
+                    del line['attributes']['replace']
             if line['type'] in transcripts_type:
                 id = str()
                 if line['attributes'].has_key('ID'):
                     id = line['attributes']['ID']
                     transcripts.add(id)
+    if all_assign:
+        # modified gff1 without any relace attributes
+        gff3_1_mod = '{0:s}/{1:s}'.format(tmpdir, 'gff1_mod.gff3')
+        gff3_1.write(gff3_1_mod)
+        gff1 = gff3_1_mod
 
     out1_type = '{0:s}/{1:s}'.format(tmpdir, 'gff1_transcript_type.txt')
     with open(out1_type, "w") as trans_type:

gff3tool/lib/gff3_merge/revision.py

@@ -33,7 +33,7 @@
 
 __version__ = '1.0.3'
 
-def main(gff_file, revision_file, output_gff, report_file=None,user_defined1=None, auto=True,logger=None):
+def main(gff_file, revision_file, output_gff, report_file=None, user_defined1=None, auto=True, logger=None):
     logger_null = logging.getLogger(__name__+'null')
     null_handler = logging.NullHandler()
     logger_null.addHandler(null_handler)
@@ -331,4 +331,4 @@ def main(gff_file, revision_file, output_gff, report_file=None,user_defined1=Non
     if not args.output_gff:
         args.output_gff = 'Revised_{0:s}'.format(args.gff_file)
 
-    main(args.gff_file, args.revision_file, args.output_gff, args.report_file, logger=logger_stderr)
+    main(gff_file=args.gff_file, revision_file=args.revision_file, output_gff=args.output_gff, report_file=args.report_file, logger=logger_stderr)