Merge pull request #728 from Gaius-Augustus/master

Updating compleasm branch
Gaius-Augustus · Dec 22, 2023 · e8c5ba4 · e8c5ba4
2 parents 7729e4f + 72cf359
commit e8c5ba4
Show file tree

Hide file tree

Showing 7 changed files with 704 additions and 6 deletions.
diff --git a/README.md b/README.md
@@ -202,6 +202,8 @@ bash /opt/BRAKER/example/docker-tests/test3.sh # BRAKER3
 ```
 :warning: The container does not include Java/GUSHR/anything UTR related because we are currently not maintaining UTR prediction with BRAKER. It's buggy and unstable. Do not use it.
 
+:warning: Users have reported that you need to manually copy the AUGUSTUS_CONFIG_PATH contents to a writable location before running our containers from Nextflow. Afterwards, you need to specify the writable AUGUSTUS_CONFIG_PATH as command line argument to BRAKER in Nextflow.
+
 Good luck ;-)
 
 Installation

diff --git a/example/singularity-tests/test1.sh b/example/singularity-tests/test1.sh
@@ -45,7 +45,7 @@ if [ -d $wd ]; then
     rm -r $wd
 fi
 
-singularity exec -B ${PWD}:${PWD} ${BRAKER_SIF} braker.pl --genome=/opt/BRAKER/example/genome.fa --bam=/opt/BRAKER/example/RNAseq.bam --softmasking --workingdir=${wd} --GENEMARK_PATH=${ETP}/gmes --threads 8 --gm_max_intergenic 10000 --skipOptimize
+singularity exec -B ${PWD}:${PWD} ${BRAKER_SIF} braker.pl --genome=/opt/BRAKER/example/genome.fa --bam=/opt/BRAKER/example/RNAseq.bam --workingdir=${wd} --GENEMARK_PATH=${ETP}/gmes --threads 8 --gm_max_intergenic 10000 --skipOptimize
 
 	    # Important: the options --gm_max_intergenic 10000 --skipOptimize should never be applied to a real life run!!!
 	    # They were only introduced to speed up the test. Please delete them from the script if you use it for real data analysis.

diff --git a/example/singularity-tests/test2.sh b/example/singularity-tests/test2.sh
@@ -47,7 +47,7 @@ if [ -d $wd ]; then
     rm -r $wd
 fi
 
-singularity exec -B ${PWD}:${PWD} ${BRAKER_SIF} braker.pl --genome=/opt/BRAKER/example/genome.fa --prot_seq=/opt/BRAKER/example/proteins.fa --softmasking --workingdir=${wd} --threads 8 --gm_max_intergenic 10000 --skipOptimize
+singularity exec -B ${PWD}:${PWD} ${BRAKER_SIF} braker.pl --genome=/opt/BRAKER/example/genome.fa --prot_seq=/opt/BRAKER/example/proteins.fa --workingdir=${wd} --threads 8 --gm_max_intergenic 10000 --skipOptimize
             # Important: the options --gm_max_intergenic 10000 --skipOptimize should never be applied to a real life run!!!
             # They were only introduced to speed up the test. Please delete them from the script if you use it for real data analysis.
 

diff --git a/example/singularity-tests/test3.sh b/example/singularity-tests/test3.sh
@@ -45,7 +45,7 @@ if [ -d $wd ]; then
     rm -r $wd
 fi
 
-singularity exec -B ${PWD}:${PWD} ${BRAKER_SIF} braker.pl --genome=/opt/BRAKER/example/genome.fa --prot_seq=/opt/BRAKER/example/proteins.fa --bam=/opt/BRAKER/example/RNAseq.bam --softmasking --workingdir=${wd} \
+singularity exec -B ${PWD}:${PWD} ${BRAKER_SIF} braker.pl --genome=/opt/BRAKER/example/genome.fa --prot_seq=/opt/BRAKER/example/proteins.fa --bam=/opt/BRAKER/example/RNAseq.bam --workingdir=${wd} \
 	    --threads 8 --gm_max_intergenic 10000 --skipOptimize
 
 	    # Important: the options --gm_max_intergenic 10000 --skipOptimize should never be applied to a real life run!!!                                   

diff --git a/scripts/braker.pl b/scripts/braker.pl
@@ -5438,7 +5438,7 @@ sub GeneMark_ETP {
         if (!@bam) {
             clean_abort("$AUGUSTUS_CONFIG_PATH/species/$species",
                 $useexisting, "ERROR in file " . __FILE__ ." at line "
-                . __LINE__ ."\nFailed to find RNA-Seq data for GeneMark-ETP.\n");
+                . __LINE__ ."\nFailed to find RNA-Seq data for GeneMark-ETP. Note: GeneMark-ETP cannot be invoked with a hints file!\n");
         } elsif (! @prot_seq_files) {
             clean_abort("$AUGUSTUS_CONFIG_PATH/species/$species",
                 $useexisting, "ERROR in file " . __FILE__ ." at line "
@@ -6082,7 +6082,10 @@ sub training_augustus {
                 . (localtime)
                 . ": creating softlink from $gmGtf to $trainGenesGtf.\n"
                 if ($v > 3);
-            $cmdString = "ln -s $gmGtf $trainGenesGtf";
+            # shorten the $gmGtf path to avoid problems with absolute softlink
+            my @pp = split(/\//, $gmGtf);
+            my $gmGtfShort = $pp[-2]."/".$pp[-1];
+            $cmdString = "ln -s $gmGtfShort $trainGenesGtf";
             print LOG "$cmdString\n" if ($v > 3);
             system($cmdString) == 0
                 or clean_abort("$AUGUSTUS_CONFIG_PATH/species/$species",

diff --git a/scripts/braker_cleanup.pl b/scripts/braker_cleanup.pl
@@ -121,7 +121,8 @@
 	"GeneMark-ET/data", "GeneMark-ET/info", "GeneMark-ET/output", "GeneMark-ET/run",
 	"GeneMark-EP/data", "GeneMark-EP/info", "GeneMark-EP/output", "GeneMark-EP/run",
 	"GeneMark-ETP/etp_data", "GeneMark-ETP/rnaseq/gmst/", "GeneMark-ETP/rnaseq/hisat2/", 
-    "GeneMark-ETP/rnaseq/stringtie/", "GeneMark-ETP/arx", "GeneMark-ETP/proteins.fa/hc/regions/",
+ #   "GeneMark-ETP/rnaseq/stringtie/", 
+	"GeneMark-ETP/arx", "GeneMark-ETP/proteins.fa/hc/regions/",
 	"GeneMark-ETP/proteins.fa/nonhc/prothint","GeneMark-ETP/rnaseq/hints/proteins.fa/prothint/Spaln",
     "GeneMark-ETP/proteins.fa/nonhc/for_prothint", "GeneMark-ETP/proteins.fa/nonhc/pred_m",
     "GeneMark-ETP/proteins.fa/nonhc/regions", "GeneMark-ETP/proteins.fa/etr", "GeneMark-ETP/proteins.fa/nonhc/hc",