updates to v0.2.6

Author: Jon Palmer

bin/funannotate-compare.py

@@ -404,6 +404,7 @@ def __init__(self,prog):
 ########################################################
 
 ####SignalP############################
+lib.log.info("Summarizing secreted protein results")
 #flip the dict and just count number for each
 signalpDict = lib.busco_dictFlip(signalp)
 
@@ -800,10 +801,9 @@ def addlink(x):
 
 lib.log.info("Compressing results to output file: %s.tar.gz" % args.out)
 lib.make_tarfile(args.out+'.tar.gz', args.out)
-lib.log.info("Finished!")
+lib.log.info("Funannotate compare completed successfully!")
 os._exit(1)
 
-
 ############################################
 
 

bin/funannotate-functional.py

@@ -98,6 +98,15 @@ def runIPRpython(Input):
     lib.log.info("No NCBI SBT file given, will use default, however if you plan to submit to NCBI, create one and pass it here '--sbt'")
 else:
     SBT = args.sbt
+    
+#check other input files
+if not os.path.isfile(SBT):
+    lib.log.error("SBT file not found, exiting")
+    os._exit(1)
+if args.antismash:
+    if not os.path.isfile(args.antismash):
+        lib.log.error("Antismash GBK file not found, exiting")
+        os._exit(1)
 
 if not args.skip_iprscan:
     if not args.iprscan and not args.email:
@@ -256,6 +265,7 @@ def runIPRpython(Input):
 #run signalP if installed, have to manually install, so test if exists first, then run it if it does
 signalp_out = os.path.join(outputdir, 'annotate_misc', 'annotations.signalp.txt')
 if lib.which('signalp'):
+    lib.log.info("Predicting secreted proteins with SignalP")
     if not lib.checkannotations(signalp_out):
         lib.signalP(Proteins, os.path.join(outputdir, 'annotate_misc'), signalp_out)
     num_annotations = lib.line_count(signalp_out)
@@ -601,5 +611,7 @@ def runIPRpython(Input):
         os.makedirs(os.path.join(outputdir, 'logfiles'))
     os.rename(log_name, os.path.join(outputdir, 'logfiles', log_name))
 
+#final wrap up message
+lib.log.info("Funannotate annotate has completed successfully!")
 
 

bin/funannotate-predict.py

@@ -170,7 +170,9 @@ def __init__(self,prog):
 RepeatMasker = os.path.abspath(RepeatMasker)
 MaskGenome = os.path.abspath(MaskGenome)
 
-#final output for augustus hints
+#final output for augustus hints, declare ahead of time for checking portion of script
+hintsE = os.path.join(args.out, 'predict_misc', 'hints.E.gff')
+hintsP = os.path.join(args.out, 'predict_misc', 'hints.P.gff')
 hints_all = os.path.join(args.out, 'predict_misc', 'hints.PE.gff')
 
 #check for masked genome here
@@ -235,7 +237,6 @@ def __init__(self,prog):
             blat_filt = os.path.join(args.out, 'predict_misc', 'blat.filt.psl')
             blat_sort1 = os.path.join(args.out, 'predict_misc', 'blat.sort.tmp.psl')
             blat_sort2 = os.path.join(args.out, 'predict_misc', 'blat.sort.psl')
-            hintsE = os.path.join(args.out, 'predict_misc', 'hints.E.gff')
             maxINT = '-maxIntron='+str(args.max_intronlen)
             lib.log.info("Aligning transcript evidence to genome with BLAT")
             if not os.path.isfile(hints_all):
@@ -289,7 +290,6 @@ def __init__(self,prog):
         Exonerate = os.path.abspath(Exonerate)
         #now run exonerate2 hints for Augustus
         exonerate2hints = os.path.join(AUGUSTUS_BASE, 'scripts', 'exonerate2hints.pl')
-        hintsP = os.path.join(args.out, 'predict_misc', 'hints.P.gff')
         e2h_in = '--in='+p2g_out
         e2h_out = '--out='+hintsP
         e2h_minINT = '--minintronlen='+str(args.min_intronlen)

funannotate.py

@@ -31,7 +31,7 @@ def fmtcols(mylist, cols):
              for i in range(0,num_lines))
     return "\n".join(lines)
 
-version = '0.2.5'
+version = '0.2.6'
 
 default_help = """
 Usage:       funannotate <command> <arguments>

lib/library.py

@@ -613,7 +613,6 @@ def fasta2chunks(input, chunks, tmpdir, output):
             handle.close()
 
 def signalP(input, tmpdir, output):
-    log.info("Predicting secreted proteins with SignalP")
     FNULL = open(os.devnull, 'w')
     #split input file into chunks, 20 should mean < 200 proteins per chunk
     fasta2chunks(input, 40, tmpdir, 'signalp_tmp')
@@ -1255,8 +1254,11 @@ def gb2proteinortho(input, folder, name):
                 for record in SeqRecords:
                     for f in record.features:
                         if f.type == 'CDS':
-                            protID = f.qualifiers['protein_id'][0]
                             locusID = f.qualifiers['locus_tag'][0]
+                            try:  #saw in a genome downloaded from Genbank that a few models don't have protID?  fix if missing to avoid error
+                                protID = f.qualifiers['protein_id'][0]
+                            except KeyError:
+                                protID = 'ncbi:'+locusID+'-T1'                       
                             start = f.location.nofuzzy_start
                             end = f.location.nofuzzy_end
                             strand = f.location.strand