Merge pull request #64 from genepi/Adapt-Dockerfile

Prepare Release 0.2.0
genepi · Mar 6, 2024 · 30f4728 · 30f4728
2 parents 23677b8 + 25a239c
commit 30f4728
Show file tree

Hide file tree

Showing 8 changed files with 103 additions and 43 deletions.
diff --git a/CITATION.cff b/CITATION.cff
@@ -1,12 +1,57 @@
-cff-version: 1.2.0
+cff-version: "1.2.0"
 message: "If you use this software, please cite it as below."
+title: "Nanopore sequencing with unique molecular identifiers enables accurate mutation analysis and haplotyping in the complex Lipoprotein(a) KIV-2 VNTR"
 authors:
-- family-names: Amstler
-  given-names: Stephan
-  orcid: https://orcid.org/0009-0007-7214-7481
-title: "Umi-pipeline-nf - A nextflow pipeline to analyse UMI-tagged amplicons from nanopore sequencing."
-version: 0.2.0
-identifiers:
-  - type: doi
-    value: 10.1101/2024.03.01.582741
-url: https://github.com/genepi/umi-pipeline-nf
+  - family-names: "Amstler"
+    given-names: "Stephan"
+  - family-names: "Streiter"
+    given-names: "Gertraud"
+  - family-names: "Pfurtscheller"
+    given-names: "Cathrin"
+  - family-names: "Forer"
+    given-names: "Lukas"
+  - family-names: "Di Maio"
+    given-names: "Silvia"
+  - family-names: "Weissensteiner"
+    given-names: "Hansi"
+  - family-names: "Paulweber"
+    given-names: "Bernhard"
+  - family-names: "Schoenherr"
+    given-names: "Sebastian"
+  - family-names: "Kronenberg"
+    given-names: "Florian"
+  - family-names: "Coassin"
+    given-names: "Stefan"
+doi: "10.1101/2024.03.01.582741"
+date-released: "2024-03-05"
+license: "Apache-2.0"
+repository-code: "https://github.com/genepi/umi-pipeline-nf"
+preferred-citation:
+  type: "article"
+  authors:
+  - family-names: "Amstler"
+    given-names: "Stephan"
+  - family-names: "Streiter"
+    given-names: "Gertraud"
+  - family-names: "Pfurtscheller"
+    given-names: "Cathrin"
+  - family-names: "Forer"
+    given-names: "Lukas"
+  - family-names: "Di Maio"
+    given-names: "Silvia"
+  - family-names: "Weissensteiner"
+    given-names: "Hansi"
+  - family-names: "Paulweber"
+    given-names: "Bernhard"
+  - family-names: "Schoenherr"
+    given-names: "Sebastian"
+  - family-names: "Kronenberg"
+    given-names: "Florian"
+  - family-names: "Coassin"
+    given-names: "Stefan"
+  doi: "10.1101/2024.03.01.582741"
+  journal: "bioRxiv"
+  day: 5
+  month: 3
+  title: "Nanopore sequencing with unique molecular identifiers enables accurate mutation analysis and haplotyping in the complex Lipoprotein(a) KIV-2 VNTR"
+  year: 2024
diff --git a/README.md b/README.md
@@ -53,6 +53,12 @@ nextflow run genepi/umi-pipeline-nf -r v0.1.0 -profile test,docker
 nextflow run genepi/umi-pipeline-nf -r v0.1.0 -c <custom.config> -profile docker 
 ```
 
+## Citation 
+
+If you use the pipeline please cite our Paper:
+
+Amstler S, Streiter G, Pfurtscheller C, Forer L, Di Maio S, Weissensteiner H, Paulweber B, Schoenherr S, Kronenberg F, Coassin S. Nanopore sequencing with unique molecular identifiers enables accurate mutation analysis and haplotyping in the complex Lipoprotein(a) KIV-2 VNTR. bioRxiv. 2024. doi: 10.1101/2024.03.01.582741.
+
 
 ### Credits
 

diff --git a/config/base.config b/config/base.config
@@ -4,10 +4,10 @@
 // PROCESS RESOURCES
 process {
 	withName: "POLISH_CLUSTER" {
-		memory = { 10.GB * task.attempt }
-		cpus = 2
+		memory = { 1.GB * task.attempt }
+		cpus = 1
 	}
 
 	errorStrategy =  'retry'
-	maxRetries = 3
+	maxRetries = 5
 }
diff --git a/config/custom.config b/config/custom.config
@@ -21,13 +21,31 @@ params {
 
 	// adaptable parameters
 
-	output_format 				= "fastq"	
-	filter_strategy_clusters 	= "quality"
+    //READ FILTERING
+    min_read_length                       = 0
+    min_qscore                            = 10
 
-	call_variants 				= true
-	variant_caller 				= "freebayes"
+    // SUBSAMPLING
+    subsampling                           = false
+    subsampling_seed                      = 11
+    subsampling_readnumber                = 100000
+
+    // VARIANT_CALLING
+    call_variants                         = false    
+    variant_caller                        = "freebayes"
 
-	medaka_model 				= "r1041_e82_400bps_hac_g615"
+    // ADVANCED
+    min_reads_per_barcode                 = 1000
+    umi_errors                            = 2
+    max_dist_umi                          = 2
+    min_reads_per_cluster                 = 20
+    max_reads_per_cluster                 = 60
+	min_consensus_quality                 = 40
+	masking_strategy                      = "softmask"
+    filter_strategy_clusters              = "quality"
+    min_overlap                           = 0.95
+    balance_strands                       = true
+    medaka_model                          = "r1041_e82_400bps_hac_g615"
 }
 
 // NEXTFLOW REPORTING

diff --git a/config/test.config b/config/test.config
@@ -8,28 +8,20 @@
 
 params {
 
-	help 				= false
-	version 			= false
-	debug 				= true
+	help 						= false
+	version 					= false
+	debug 						= true
 
-	input 				= "$baseDir/data/fastq_pass/"
-	output 				= "umi-pipeline-nf_test-run"
-	reference 			= "$baseDir/data/ref/lpa-ref2645.fasta"
-	reference_fai 			= "$baseDir/data/ref/lpa-ref2645.fasta.fai"
-	bed 				= "$baseDir/data/ref/lpa-ref2645.bed"
-
-	subsampling 			= false
+	input 						= "$baseDir/data/fastq_pass/"
+	output 						= "umi-pipeline-nf_test-run"
+	reference 					= "$baseDir/data/ref/lpa-ref2645.fasta"
+	reference_fai 				= "$baseDir/data/ref/lpa-ref2645.fasta.fai"
+	bed 						= "$baseDir/data/ref/lpa-ref2645.bed"
 
 	min_reads_per_cluster 		= 10
 	max_reads_per_cluster 		= 20
-
-	write_reports 			= true
-	output_format 			= "fastq"
-	filter_strategy_clusters 	= "quality"
-	call_variants 			= true
-	variant_caller 			= "freebayes"
-
-	medaka_model 			= "r1041_e82_400bps_hac_g615"
+	call_variants 				= true
+	variant_caller 				= "mutserve"
 }
 
 // NEXTFLOW REPORTING

diff --git a/env/Dockerfile b/env/Dockerfile
@@ -18,8 +18,6 @@ RUN conda update -y conda && \
     conda clean --all
 
 WORKDIR "/opt"
-RUN wget https://github.com/seppinho/mutserve/releases/download/v2.0.0-rc15/mutserve.zip && \
-    unzip mutserve.zip
-ENV PATH="/opt/mutserve:${PATH}"
+RUN wget https://github.com/seppinho/mutserve/releases/download/v2.0.0-rc13.lpa/mutserve_LPA_adapted.jar
 
 
diff --git a/lib/processes/variant_calling/mutserve.nf b/lib/processes/variant_calling/mutserve.nf
@@ -14,7 +14,7 @@ process MUTSERVE {
 
     script:
     """
-      mutserve call  \
+      java -jar /opt/mutserve_LPA_adapted.jar call  \
       --output ${type}.vcf \
       --write-raw \
       --reference ${reference} \

diff --git a/nextflow.config b/nextflow.config
@@ -1,7 +1,7 @@
 // NEXTFLOW MANIFEST
 manifest {
     name                                  = 'umi-pipeline-nf'
-    version                               = '0.1.0'
+    version                               = '0.2.0'
     description                           = 'Nextflow pipeline to analyze umi amplicon data'
     author                                = 'Stephan Amstler'
     homePage                              = 'https://github.com/AmstlerStephan/umi-pipeline-nf.git'
@@ -39,7 +39,8 @@ params {
 
     // ADVANCED
     min_reads_per_barcode                 = 1000
-    umi_errors                            = 3
+    umi_errors                            = 2
+    max_dist_umi                          = 2
     min_reads_per_cluster                 = 20
     max_reads_per_cluster                 = 60
 	min_consensus_quality                 = 40
@@ -66,7 +67,7 @@ params {
 // Load base.config by default for all pipelines
 includeConfig "${baseDir}/config/base.config"
 
-process.container                         = 'quay.io/genepi/umi-pipeline-nf:v0.1.0'
+process.container                         = 'quay.io/genepi/umi-pipeline-nf:v0.2.0'
 
 profiles {