Merge pull request #1 from grp-bork/update/nevermore_0.13.0_20240620

updated nevermore -> 0.13.0

nevermore/modules/align/bowtie2.nf

@@ -0,0 +1,76 @@
+process bowtie2_build {
+	container "quay.io/biocontainers/bowtie2:2.5.3--py39h6fed5c7_1"
+	tag "${sample.id}"
+
+	input:
+    tuple val(sample), path(genomeseq)
+
+    output:
+    tuple val(sample), path("${sample.id}/bowtie2/${sample.id}*"), emit: index
+
+    script:
+    """
+    mkdir -p ${sample.id}/bowtie2/
+
+    gzip -dc ${genomeseq} > genome.fa
+
+    bowtie2-build --threads ${task.cpus} -f genome.fa ${sample.id}/bowtie2/${sample.id}
+
+    rm -vf genome.fa
+    """
+
+}
+
+
+process bowtie2_align {
+	// container "quay.io/biocontainers/bowtie2:2.5.3--py39h6fed5c7_1"
+	container "registry.git.embl.de/schudoma/bowtie2-docker:latest"
+	tag "${sample.id}"
+
+	input:
+    tuple val(sample), path(fastqs), path(index)
+
+    output:
+    tuple val(sample), path("${sample.id}/bowtie2_align/${sample.id}.bam"), emit: bam
+    tuple val(sample), path("${sample.id}/bowtie2_align/${sample.id}.bam.bai"), emit: bai
+    tuple val(sample), path("${sample.id}.BOWTIE2.DONE"), emit: sentinel
+
+    script:
+
+    def input_files = ""
+	def r1_files = fastqs.findAll( { it.name.endsWith("_R1.fastq.gz") && !it.name.matches("(.*)(singles|orphans|chimeras)(.*)") } )
+	def r2_files = fastqs.findAll( { it.name.endsWith("_R2.fastq.gz") } )
+	def orphans = fastqs.findAll( { it.name.matches("(.*)(singles|orphans|chimeras)(.*)") } )
+
+	if (r1_files.size() != 0 && r2_files.size() != 0) {
+		input_files += "-1 ${r1_files.join(' ')} -2 ${r2_files.join(' ')}"
+		single_reads = false
+	} else if (r1_files.size() != 0) {
+		input_files += "-U ${r1_files.join(' ')}"
+	} else if (r2_files.size() != 0) {
+		input_files += "-U ${r2_files.join(' ')}"
+	} else if (orphans.size() != 0) {
+		input_files += "-U ${orphans.join(' ')}"
+	}
+
+    // --fr/--rf/--ff
+    def threads = task.cpus.intdiv(2)
+    def bowtie2_options = "-p ${threads} -q --phred33"
+
+    def index_id = index[0].name.replaceAll(/.[0-9]+.bt2[l]?$/, "")
+    // -S ${sample.id}/hisat2_align/${sample.id}.sam
+    // index_id=\$(ls ${index[0]} | sed 's/\\.[0-9]\\+\\.ht2\$//')
+    """
+    mkdir -p ${sample.id}/bowtie2_align/ tmp/
+
+    export TMPDIR=tmp/
+
+    bowtie2 -x ${index_id} ${bowtie2_options} ${input_files} > ${sample.id}.sam
+    samtools sort -@ ${threads} ${sample.id}.sam > ${sample.id}/bowtie2_align/${sample.id}.bam
+    samtools index ${sample.id}/bowtie2_align/${sample.id}.bam
+    rm -fv ${sample.id}.sam
+
+    touch ${sample.id}.BOWTIE2.DONE
+    """
+
+}

nevermore/modules/align/bwa.nf

@@ -1,5 +1,5 @@
 process bwa_mem_align {
-    container "docker://registry.git.embl.de/schudoma/align-docker:latest"
+    container "registry.git.embl.de/schudoma/align-docker:latest"
     label 'align'
 
     input:

nevermore/modules/align/helpers.nf

@@ -1,36 +1,70 @@
 process merge_and_sort {
-    container "docker://quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
+    container "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
     label 'samtools'
 
     input:
     tuple val(sample), path(bamfiles)
     val(do_name_sort)
 
     output:
-    tuple val(sample), path("bam/${sample}.bam"), emit: bam
-    tuple val(sample), path("stats/bam/${sample}.flagstats.txt"), emit: flagstats
+    tuple val(sample), path("bam/${sample.id}.bam"), emit: bam
+    tuple val(sample), path("stats/bam/${sample.id}.flagstats.txt"), emit: flagstats
 
     script:
     def sort_order = (do_name_sort) ? "-n" : ""
     def merge_cmd = ""
 
     // need a better detection for this
     if (bamfiles instanceof Collection && bamfiles.size() >= 2) {
-        merge_cmd = "samtools merge -@ $task.cpus ${sort_order} bam/${sample}.bam ${bamfiles}"
+        merge_cmd = "samtools merge -@ $task.cpus ${sort_order} bam/${sample.id}.bam ${bamfiles}"
     } else {
-        merge_cmd = "ln -s ../${bamfiles[0]} bam/${sample}.bam"
+        merge_cmd = "ln -s ../${bamfiles[0]} bam/${sample.id}.bam"
     }
 
     """
     mkdir -p bam/ stats/bam/
     ${merge_cmd}
-    samtools flagstats bam/${sample}.bam > stats/bam/${sample}.flagstats.txt
+    samtools flagstats bam/${sample.id}.bam > stats/bam/${sample.id}.flagstats.txt
+    """
+}
+
+
+process merge_sam {
+    container "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
+    label 'samtools'
+
+    input:
+    tuple val(sample), path(samfiles)
+    // val(do_name_sort)
+
+    output:
+    tuple val(sample), path("sam/${sample.id}.sam"), emit: sam
+    tuple val(sample), path("stats/sam/${sample.id}.flagstats.txt"), emit: flagstats
+
+    script:
+    // def sort_order = (do_name_sort) ? "-n" : ""
+    def merge_cmd = ""
+
+    // need a better detection for this
+    if (samfiles instanceof Collection && samfiles.size() >= 2) {
+        // merge_cmd = "samtools merge -@ $task.cpus ${sort_order} bam/${sample.id}.bam ${bamfiles}"
+        merge_cmd += "samtools view --no-PG -Sh ${samfiles[0]} > sam/${sample.id}.sam\n"
+        merge_cmd += "samtools view -S ${samfiles[1]} >> sam/${sample.id}.sam"
+
+    } else {
+        merge_cmd = "ln -s ../${samfiles[0]} sam/${sample.id}.sam"
+    }
+
+    """
+    mkdir -p sam/ stats/sam/
+    ${merge_cmd}
+    samtools flagstats sam/${sample.id}.sam > stats/sam/${sample.id}.flagstats.txt
     """
 }
 
 
 process db_filter {
-    container "docker://quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
+    container "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
     label 'samtools'
 
     input:
@@ -51,7 +85,7 @@ process db_filter {
 
 
 process readcount {
-    container "docker://quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
+    container "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
     label 'samtools'
 
     input:

nevermore/modules/align/hisat2.nf

@@ -0,0 +1,86 @@
+process hisat2_build {
+    container "quay.io/biocontainers/hisat2:2.2.1--hdbdd923_6"
+    // we need a hisat2/samtools mixed container
+    // container "registry.git.embl.de/schudoma/hisat2-docker:latest"
+
+    input:
+    tuple val(sample), path(genomeseq)
+
+    output:
+    tuple val(sample), path("${sample.id}/hisat2/${sample.id}*"), emit: index
+
+    script:
+    """
+    mkdir -p ${sample.id}/hisat2/
+
+    gzip -dc ${genomeseq} > genome.fa
+
+    hisat2-build -f genome.fa ${sample.id}/hisat2/${sample.id}
+
+    rm -vf genome.fa
+    """
+
+}
+
+process hisat2_align {
+    // container "quay.io/biocontainers/hisat2:2.2.1--hdbdd923_6"
+    // we need a hisat2/samtools mixed container
+    container "registry.git.embl.de/schudoma/hisat2-docker:latest"
+
+    input:
+    tuple val(sample), path(fastqs), path(index)
+
+    output:
+    // tuple val(sample), path("${sample.id}/hisat2_align/${sample.id}.bam"), path("${sample.id}/hisat2_align/${sample.id}.bam.bai"), emit: bam
+    tuple val(sample), path("${sample.id}/hisat2_align/${sample.id}.bam"), emit: bam
+    tuple val(sample), path("${sample.id}/hisat2_align/${sample.id}.bam.bai"), emit: bai
+    tuple val(sample), path("${sample.id}.HISAT2.DONE"), emit: sentinel
+
+    script:
+
+    def input_files = ""
+	def r1_files = fastqs.findAll( { it.name.endsWith("_R1.fastq.gz") && !it.name.matches("(.*)(singles|orphans|chimeras)(.*)") } )
+	def r2_files = fastqs.findAll( { it.name.endsWith("_R2.fastq.gz") } )
+	def orphans = fastqs.findAll( { it.name.matches("(.*)(singles|orphans|chimeras)(.*)") } )
+
+	if (r1_files.size() != 0 && r2_files.size() != 0) {
+		input_files += "-1 ${r1_files.join(' ')} -2 ${r2_files.join(' ')}"
+		single_reads = false
+	} else if (r1_files.size() != 0) {
+		input_files += "-U ${r1_files.join(' ')}"
+	} else if (r2_files.size() != 0) {
+		input_files += "-U ${r2_files.join(' ')}"
+	} else if (orphans.size() != 0) {
+		input_files += "-U ${orphans.join(' ')}"
+	}
+
+    // --fr/--rf/--ff
+    def threads = task.cpus.intdiv(2)
+    def hisat2_options = "-p ${threads} -q --phred33"
+    if (params.hisat2_no_spliced_alignment) {
+        // --no-spliced-alignment
+        hisat2_options += " --no-spliced-alignment"
+    }
+
+    def index_id = index[0].name.replaceAll(/.[0-9]+.ht2$/, "")
+    // -S ${sample.id}/hisat2_align/${sample.id}.sam
+    // index_id=\$(ls ${index[0]} | sed 's/\\.[0-9]\\+\\.ht2\$//')
+    """
+    mkdir -p ${sample.id}/hisat2_align/ tmp/
+
+    export TMPDIR=tmp/
+
+    hisat2 -x ${index_id} ${hisat2_options} ${input_files} > ${sample.id}.sam
+    samtools sort -@ ${threads} ${sample.id}.sam > ${sample.id}/hisat2_align/${sample.id}.bam
+    samtools index ${sample.id}/hisat2_align/${sample.id}.bam
+    rm -fv ${sample.id}.sam
+
+    touch ${sample.id}.HISAT2.DONE
+    """
+    // echo "tmpdir is \$TMPDIR"
+
+    // hisat2 -x ${sample.id} ${hisat2_options} ${input_files} > ${sample.id}.sam
+}
+
+
+

nevermore/modules/align/minimap2.nf

@@ -0,0 +1,50 @@
+process minimap2_align {
+	container "registry.git.embl.de/schudoma/minimap2-docker:latest"
+	label 'align'
+
+	input:
+	tuple val(sample), path(fastqs)
+	path(reference)
+	val(do_name_sort)
+
+	output:
+	tuple val(sample), path("${sample.id}/${sample.id}.sam"), emit: sam
+
+	script:
+	// def reads = (sample.is_paired) ? "${sample.id}_R1.fastq.gz ${sample.id}_R2.fastq.gz" : "${sample.id}_R1.fastq.gz"
+
+	def input_files = ""
+	def r1_files = fastqs.findAll( { it.name.endsWith("_R1.fastq.gz") && !it.name.matches("(.*)(singles|orphans|chimeras)(.*)") } )
+	def r2_files = fastqs.findAll( { it.name.endsWith("_R2.fastq.gz") } )
+	def orphans = fastqs.findAll( { it.name.matches("(.*)(singles|orphans|chimeras)(.*)") } )
+
+	if (r1_files.size() != 0 && r2_files.size() != 0) {
+		input_files += "${r1_files.join(' ')} ${r2_files.join(' ')}"
+		single_reads = false
+	} else if (r1_files.size() != 0) {
+		input_files += "${r1_files.join(' ')}"
+	} else if (r2_files.size() != 0) {
+		input_files += "${r2_files.join(' ')}"
+	} else if (orphans.size() != 0) {
+		input_files += "${orphans.join(' ')}"
+	}
+
+
+
+
+	def threads = task.cpus.intdiv(2)
+	// def mm_options = "--sam-hit-only -t ${threads} -x sr --secondary=yes -a"
+	def mm_options = "-t ${threads} -x sr --secondary=yes -a"
+
+	// def sort_cmd = "| " + ((do_name_sort) ? "samtools collate -@ ${threads} -o ${sample.id}.bam - tmp/collated_bam" : "samtools sort -@ ${threads} -o ${sample.id}.bam -")
+	def sort_cmd = ""  // we cannot convert large catalogue alignments to bam, hence we cannot properly sort those
+
+	"""
+	set -e -o pipefail
+
+	mkdir -p ${sample.id}/ tmp/
+	minimap2 ${mm_options} --split-prefix ${sample.id}_split ${reference} ${input_files} ${sort_cmd} > ${sample.id}/${sample.id}.sam
+
+	rm -rvf tmp/
+	"""
+}

nevermore/modules/align/sam_align.nf

@@ -1,5 +1,5 @@
 process minimap2_align {
-	container "docker://quay.io/biocontainers/minimap2:2.28--he4a0461_0"
+	container "quay.io/biocontainers/minimap2:2.28--he4a0461_0"
 	label 'align'
 
 	input:
@@ -21,7 +21,7 @@ process minimap2_align {
 
 
 process bwa_mem_align {
-	container "docker://quay.io/biocontainers/bwa:0.7.3a--he4a0461_9"
+	container "quay.io/biocontainers/bwa:0.7.3a--he4a0461_9"
 	label 'align'
 
 	input:

nevermore/modules/collate.nf

@@ -1,4 +1,6 @@
 process collate_stats {
+    label "default"
+
     input:
     path(stats_files)
 

nevermore/modules/converters/bam2fq.nf

@@ -1,5 +1,5 @@
 process bam2fq {
-    container "docker://quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
+    container "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
     input:
     tuple val(sample), path(bam)
 

nevermore/modules/converters/fq2bam.nf

@@ -1,5 +1,5 @@
 process fq2bam {
-	container "docker://quay.io/biocontainers/bbmap:39.06--h92535d8_0"
+	container "quay.io/biocontainers/bbmap:39.06--h92535d8_0"
 
     input:
     tuple val(sample), path(fq)

nevermore/modules/converters/fq2fa.nf

@@ -1,5 +1,5 @@
 process fq2fa {
-	container "docker://quay.io/biocontainers/bbmap:39.06--h92535d8_0"
+	container "quay.io/biocontainers/bbmap:39.06--h92535d8_0"
 
     input:
     tuple val(sample), path(fq)

nevermore/modules/converters/merge_fastqs.nf

@@ -1,5 +1,6 @@
 process merge_single_fastqs {
-    container "docker://quay.io/biocontainers/bbmap:39.06--h92535d8_0"
+    container "quay.io/biocontainers/bbmap:39.06--h92535d8_0"
+    label "medium"
 
     input:
     tuple val(sample), path(fastqs)