Merge

genomic-medicine-sweden · Jan 16, 2025 · 203c5ea · 203c5ea
2 parents 0b31571 + 2e88459
commit 203c5ea
Show file tree

Hide file tree

Showing 6 changed files with 25 additions and 19 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,6 +9,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Light installation doc updates
+- Updated NGP config file
 - Added ska2 module process (`ska_build`)
 - Added ska2 to `bacterial_base.nf`
 - Added emmtyper module process (`emmtyper`)
@@ -22,6 +24,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+- Interrupted installation now hard resets E.Coli. to avoid fragmented installation
+- Installation target file for streptococcus changed, to resolve interrupted installation
+- Included htslib image to natively support tabix and bgzip
+- Fixed a bug that prevented pipeline from correctly guessing misspelled profiles
 - Fixed tbprofiler related installation rules in `Makefile`
 - All modules can be called in one workflow -> profile determines whether they are actually executed using `when` statement
 - Empty channels fixed
@@ -34,6 +40,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 
+- Removed sudo requirement from apptainer container creation (only required for older versions of apptainer) to streamline installation
 - Updated tbdb submodule
 - Moved taxon related methods to methods directory
 - Changed spyogenes genome from GCF_900475035.1 to GCF_000006785.2

diff --git a/Makefile b/Makefile
@@ -453,7 +453,8 @@ ecoli_download_wgmlst_schema: $(ECOLI_WGMLST_DIR)/alleles/ecoli_INNUENDO_wgMLST/
 
 $(ECOLI_WGMLST_DIR)/alleles/ecoli_INNUENDO_wgMLST/Escherichia_coli.trn:
 	$(call log_message,"Downloading E. coli wgMLST schema ...")
-	mkdir -p $(ECOLI_WGMLST_DIR)/alleles &> /dev/null \
+	rm -rf $(ECOLI_WGMLST_DIR)/alleles &> /dev/null \
+	&& mkdir -p $(ECOLI_WGMLST_DIR)/alleles &> /dev/null \
 	&& cd $(ECOLI_WGMLST_DIR)/alleles \
 	&& apptainer exec --bind $(MNT_ROOT) $(CONTAINER_DIR)/chewbbaca.sif \
 		chewie DownloadSchema \
@@ -725,7 +726,7 @@ $(STREP_CGMLST_DIR)/alleles/index.html:
 
 streptococcus_unpack_cgmlst_schema: $(STREP_CGMLST_DIR)/alleles/unpacking.done
 
-$(STREP_CGMLST_DIR)/alleles/unpacking.done: $(STREP_CGMLST_DIR)/alleles/profiles.list
+$(STREP_CGMLST_DIR)/alleles/unpacking.done: $(STREP_CGMLST_DIR)/alleles/index.html
 	$(call log_message,"Unpacking S. pyogenes cgMLST schema ...")
 	cd $(STREP_CGMLST_DIR)/alleles \
 	&& gunzip *.gz |& tee -a $(INSTALL_LOG) \
@@ -802,14 +803,14 @@ mtuberculosis_bgzip_bed: $(MTUBE_TBDB_DIR)/converged_who_fohm_tbdb.bed.gz
 $(MTUBE_TBDB_DIR)/converged_who_fohm_tbdb.bed.gz: $(MTUBE_TBDB_DIR)/converged_who_fohm_tbdb.bed
 	$(call log_message,"Bgzipping converged WHO + FoHM + TBDB bed file ...")
 	cd $(MTUBE_TBDB_DIR) \
-	&& bgzip $$(basename $<) -o converged_who_fohm_tbdb.bed.gz |& tee -a $(INSTALL_LOG)
+	&& apptainer exec --bind $(MNT_ROOT) $(CONTAINER_DIR)/htslib.sif bgzip $$(basename $<) -o converged_who_fohm_tbdb.bed.gz |& tee -a $(INSTALL_LOG)
 
 mtuberculosis_index_bed: $(MTUBE_TBDB_DIR)/converged_who_fohm_tbdb.bed.gz.tbi
 
 $(MTUBE_TBDB_DIR)/converged_who_fohm_tbdb.bed.gz.tbi: $(MTUBE_TBDB_DIR)/converged_who_fohm_tbdb.bed.gz
 	$(call log_message,"Indexing converged WHO + FoHM + TBDB bgzipped bed file ...")
 	cd $(MTUBE_TBDB_DIR) \
-	&& tabix -p bed $$(basename $<) |& tee -a $(INSTALL_LOG)
+	&& apptainer exec --bind $(MNT_ROOT) $(CONTAINER_DIR)/htslib.sif tabix -p bed $$(basename $<) |& tee -a $(INSTALL_LOG)
 
 # ==============================================================================
 # Perform checks

diff --git a/configs/nextflow.base.config b/configs/nextflow.base.config
@@ -10,6 +10,7 @@ params {
 	krakenDb = "/filepath/to/kraken_db" //edit if useKraken = true
 	workDir = "/filepath/to/workdir" //edit
 	publishDir = ""
+        speciesDir = "" //stable default
 	publishDirMode = 'copy'
 	publishDirOverwrite = true
 	outdir = "/filepath/to/outdir" //edit

diff --git a/configs/nextflow.ngp.config b/configs/nextflow.ngp.config
@@ -1,6 +1,6 @@
 params {
 	penv = "OpenMP"
-	root = "/gms-apps/pipelines/jasen" //edit
+	root = "/mnt/ngpbenchmark2/gms-apps/pipelines/jasen/v0.9" //edit
 	amrfinderDb = "${root}/assets/amrfinder_db/latest"
 	resfinderDb = "${root}/assets/resfinder_db"
 	pointfinderDb = "${root}/assets/pointfinder_db"
@@ -9,11 +9,12 @@ params {
 	mlstBlastDb = "${root}/assets/mlst_db/blast"
 	pubMlstDb = "${root}/assets/mlst_db/pubmlst"
 	krakenDb = "/gms-home/isasyl/code/JASEN" //edit if useKraken = true
-	workDir = "/gms-apps/pipelines/jasen/trash" //edit
+	workDir = "/mnt/ngpbenchmark2/gms-data/gmc-west/pipeline_output/jasen_workdir" //edit
 	publishDir = ""
+        speciesDir = "" //stable default
 	publishDirMode = 'copy'
 	publishDirOverwrite = true
-	outdir = "/gms-apps/pipelines/jasen/trash" //edit
+	outdir = "/mnt/ngpbenchmark2/gms-data/gmc-west/pipeline_output/jasen_output" //edit
 	scratch = true
 	containerDir = "${root}/container"
 	args = ""
@@ -26,19 +27,19 @@ params {
 	useSkesa = false // To use spades set useSkesa = false
   devMode = false
 
-  cpus_small=2
+  cpus_small=2 // Originally 2
   cpus_medium=8
   cpus_large=16
   cpus_huge=32
-  mem_small='6 GB'
+  mem_small='6 GB' // Originally 6gb
   mem_medium='14 GB'
   mem_large='30 GB'
   mem_huge='120 GB'
 }
 
 apptainer {
 	enabled = true
-	runOptions = '--bind /gms-apps/pipelines/jasen/:/gms-apps/pipelines/jasen/,/gms-scratch/:/gms-scratch/'
+	runOptions = '--bind /mnt/ngpbenchmark2/gms-apps/pipelines/jasen/v0.9/:/mnt/ngpbenchmark2/gms-apps/pipelines/jasen/v0.9/'
 	cacheDir = "${params.containerDir}/"
 
 	env.NXF_APPTAINER_LOCALCACHEDIR="${params.workDir}"
@@ -284,12 +285,6 @@ process {
 		container = "${params.containerDir}/samtools.sif"
 		publishDir = [ path: "${params.outdir}/${params.speciesDir}/${params.bamDir}", mode: 'copy', overwrite: true ]
 	}
-	withName: samtools_sort_ref {
-		cpus = params.cpus_large
-		memory = params.mem_small
-		container = "${params.containerDir}/samtools.sif"
-		publishDir = [ path: "${params.outdir}/${params.speciesDir}/${params.bamDir}", mode: 'copy', overwrite: true ]
-	}
 	withName: save_analysis_metadata {
 		container = "${params.containerDir}/bonsai-prp.sif"
 		publishDir = [ path: "${params.outdir}/${params.speciesDir}/analysis_metadata", mode: 'copy', overwrite: true ]

diff --git a/container/Makefile b/container/Makefile
@@ -56,6 +56,7 @@ URL_chewbbaca := https://depot.galaxyproject.org/singularity/chewbbaca:3.3.2--py
 URL_emmtyper := https://depot.galaxyproject.org/singularity/emmtyper:0.2.0--py_0
 URL_flye := https://depot.galaxyproject.org/singularity/flye:2.9.3--py39hd65a603_0
 URL_freebayes := https://depot.galaxyproject.org/singularity/freebayes:1.3.6--hbfe0e7f_2
+URL_htslib := https://depot.galaxyproject.org/singularity/htslib:1.21--h566b1c6_1
 URL_kraken2 := https://depot.galaxyproject.org/singularity/kraken2:2.1.2--pl5321h9f5acd7_3
 URL_medaka := https://depot.galaxyproject.org/singularity/medaka:1.11.3--py39h05d5c5e_0
 URL_mlst := https://depot.galaxyproject.org/singularity/mlst:2.23.0--hdfd78af_1
@@ -101,8 +102,9 @@ $(remote_containers):
 	$(call log_message,"Downloading remote container $@ ...")
 	$(eval tool := $(basename $@))
 	$(eval container_url := ${URL_${tool}})
-	output_file=$$(echo ${container_url} | sed -e 's#https://##' -e 's#/#-#g' -e 's#:#-#g').img \
-	&& wget -O $${output_file} ${container_url} --no-check-certificate \
+	$(eval sanitized_url := $(shell echo ${container_url} | sed -e 's/%3A/:/g'))
+	output_file=$$(echo ${sanitized_url} | sed -e 's#https://##' -e 's#/#-#g' -e 's#:#-#g').img \
+	&& wget -O $${output_file} ${sanitized_url} --no-check-certificate \
 	&& ln -sf $${output_file} $@ 
 
 

diff --git a/docs/source/install.md b/docs/source/install.md
@@ -14,7 +14,7 @@
 ### Copy code locally
 
 ```bash
-git clone --recurse-submodules --single-branch --branch master \\ 
+git clone --recurse-submodules --branch master \\ 
     https://github.com/genomic-medicine-sweden/jasen.git &&        \\
 cd jasen
 ```