Merge pull request #32 from PlantandFoodResearch/fix/braker/fasta

Now removing comments from FASTA file before feeding it to BRAKER
Plant-Food-Research-Open · May 13, 2024 · 87508dc · 87508dc
2 parents e49e94c + 7a39c25
commit 87508dc
Show file tree

Hide file tree

Showing 8 changed files with 51 additions and 9 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,24 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## 0.3.2 - [13-May-2024]
+
+### `Added`
+
+### `Fixed`
+
+1. Increased time limit for REPEATMODELER_REPEATMODELER to 5 days
+2. Now removing comments from fasta file before feeding it to BRAKER added tests for the perl one liner
+3. Fixed CHANGELOG version check failure in `version_check.sh`
+4. Increased the SLURM job time limit to 14 days
+
+### `Dependencies`
+
+1. NextFlow!>=23.04.4
+2. nf-validation=1.1.3
+
+### `Deprecated`
+
 ## 0.3.1 - [10-May-2024]
 
 ### `Added`

diff --git a/conf/base.config b/conf/base.config
@@ -66,21 +66,21 @@ process {
         memory              = { check_max( 200.GB * task.attempt, 'memory' ) }
     }
 
-    withName:REPEATMODELER_REPEATMODELER {
-        time                = { check_max( 3.days  * task.attempt, 'time'    ) }
+    withName:EGGNOGMAPPER {
+        time                = { check_max( 1.day  * task.attempt, 'time'    ) }
     }
     withName:REPEATMASKER {
         time                = { check_max( 2.days  * task.attempt, 'time'    ) }
     }
+    withName:REPEATMODELER_REPEATMODELER {
+        time                = { check_max( 5.days  * task.attempt, 'time'    ) }
+    }
     withName:EDTA_EDTA {
         time                = { check_max( 7.days  * task.attempt, 'time'    ) }
     }
     withName:BRAKER3 {
         time                = { check_max( 7.days  * task.attempt, 'time'    ) }
     }
-    withName:EGGNOGMAPPER {
-        time                = { check_max( 1.day  * task.attempt, 'time'    ) }
-    }
     withName:CUSTOM_DUMPSOFTWAREVERSIONS {
         cache = false
     }

diff --git a/modules/kherronism/braker3/main.nf b/modules/kherronism/braker3/main.nf
@@ -42,8 +42,12 @@ process BRAKER3 {
     """
     cp -r /usr/share/augustus/config augustus_config
 
+    perl -p -e 's/^(>\\S+).*\$/\$1/' \\
+        ${fasta} \\
+        > ${prefix}.name.only.genome.masked.fasta
+
     braker.pl \\
-        --genome ${fasta} \\
+        --genome ${prefix}.name.only.genome.masked.fasta \\
         ${new_species} \\
         --workingdir ${prefix} \\
         --AUGUSTUS_CONFIG_PATH "\$(pwd)/augustus_config" \\

diff --git a/modules/kherronism/braker3/tests/name.only.sh b/modules/kherronism/braker3/tests/name.only.sh
@@ -0,0 +1,4 @@
+#!/usr/bin/env bash
+
+perl -p -e 's/^(>\S+).*$/$1/' \
+    modules/kherronism/braker3/tests/test.fa
diff --git a/modules/kherronism/braker3/tests/test.fa b/modules/kherronism/braker3/tests/test.fa
@@ -0,0 +1,16 @@
+>chr1   This is with four spaces and 	a space and a tab
+AAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAAC
+CCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTA
+>chr2   This is with four spaces
+TAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAA
+CCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCT
+AAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAAC
+>chr3 This is with a single space
+TAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAA
+CCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCT
+>chrX
+AACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACC
+CTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAA
+>chrY	This desc is with tab   and another tab | and a vertical slash
+AACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACC
+CTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAAACCCTAA
diff --git a/nextflow.config b/nextflow.config
@@ -58,7 +58,7 @@ manifest {
     description                 = """A NextFlow pipeline for pan-genome annotation"""
     mainScript                  = 'main.nf'
     nextflowVersion             = '!>=23.04.4'
-    version                     = '0.3.1'
+    version                     = '0.3.2'
     doi                         = ''
 }
 

diff --git a/pfr_pangene b/pfr_pangene
@@ -2,7 +2,7 @@
 
 
 #SBATCH --job-name PANGENE
-#SBATCH --time=7-00:00:00
+#SBATCH --time=14-00:00:00
 #SBATCH --nodes=1
 #SBATCH --ntasks=1
 #SBATCH --cpus-per-task=1

diff --git a/version_check.sh b/version_check.sh
@@ -4,5 +4,5 @@ config_version=$(sed -n "s/.*version.*= '\(.*\)'.*/\1/p" nextflow.config)
 
 # Check CHANGELOG version
 
-grep "## $config_version - " CHANGELOG.md >/dev/null \
+head -n 10 CHANGELOG.md | grep "## $config_version - " >/dev/null \
     || (echo 'Failed to match CHANGELOG version'; exit 1)