Merge pull request #844 from maxplanck-ie/bwa_mem2_and_misc

Bwa mem2 and misc

.ci_stuff/organism.yaml

@@ -5,7 +5,9 @@ genome_2bit: ".ci_stuff/genome_fasta/genome.2bit"
 bowtie2_index: ".ci_stuff/BowtieIndex/genome"
 hisat2_index: ".ci_stuff/HISAT2Index/genome"
 bwa_index: ".ci_stuff/BWAindex/genome.fa"
+bwa_mem2_index: ".ci_stuff/BWA-MEM2Index/genome.fa"
 bwameth_index: "/tmp/genome.fa"
+bwameth2_index: "/tmp/genome.fa"
 known_splicesites: ".ci_stuff/gencode/m9/HISAT2/splice_sites.txt"
 star_index: ".ci_stuff/STARIndex/"
 genes_bed: "/tmp/genes.bed"

.ci_stuff/test_dag.sh

@@ -117,14 +117,14 @@ snakePipes config
 
 # createIndices
 WC=`createIndices -o output --snakemakeOptions " --dryrun --conda-prefix /tmp" --genome ftp://ftp.ensembl.org/pub/release-93/fasta/mus_musculus/dna/Mus_musculus.GRCm38.dna_sm.primary_assembly.fa.gz --gtf ftp://ftp.ensembl.org/pub/release-93/gtf/mus_musculus/Mus_musculus.GRCm38.93.gtf.gz blah | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
-if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 126 ]; then exit 1 ; fi
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 142 ]; then exit 1 ; fi
 WC=`createIndices -o output --snakemakeOptions " --dryrun --conda-prefix /tmp" --genome ftp://ftp.ensembl.org/pub/release-93/fasta/mus_musculus/dna/Mus_musculus.GRCm38.dna_sm.primary_assembly.fa.gz --gtf ftp://ftp.ensembl.org/pub/release-93/gtf/mus_musculus/Mus_musculus.GRCm38.93.gtf.gz --rmskURL http://hgdownload.soe.ucsc.edu/goldenPath/dm6/database/rmsk.txt.gz blah | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
-if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 132 ]; then exit 1 ; fi
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 148 ]; then exit 1 ; fi
 WC=`createIndices -o output --snakemakeOptions " --dryrun --conda-prefix /tmp" --DAG --genome ftp://ftp.ensembl.org/pub/release-93/fasta/mus_musculus/dna/Mus_musculus.GRCm38.dna_sm.primary_assembly.fa.gz --gtf ftp://ftp.ensembl.org/pub/release-93/gtf/mus_musculus/Mus_musculus.GRCm38.93.gtf.gz --rmskURL http://hgdownload.soe.ucsc.edu/goldenPath/dm6/database/rmsk.txt.gz blah | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
-if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 132 ]; then exit 1 ; fi
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 148 ]; then exit 1 ; fi
 # spikein
 WC=`createIndices -o output --snakemakeOptions " --dryrun --conda-prefix /tmp" --DAG --genomeURL ftp://ftp.ensembl.org/pub/release-93/fasta/mus_musculus/dna/Mus_musculus.GRCm38.dna_sm.primary_assembly.fa.gz --gtfURL ftp://ftp.ensembl.org/pub/release-93/gtf/mus_musculus/Mus_musculus.GRCm38.93.gtf.gz --spikeinGenomeURL ftp://ftp.ensembl.org/pub/release-79/fasta/drosophila_melanogaster/dna/Drosophila_melanogaster.BDGP6.dna_sm.toplevel.fa.gz --spikeinGtfURL  ftp://ftp.ensembl.org/pub/release-96/gtf/drosophila_melanogaster/Drosophila_melanogaster.BDGP6.22.96.gtf.gz --rmskURL http://hgdownload.soe.ucsc.edu/goldenPath/dm6/database/rmsk.txt.gz blah | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
-if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 165 ]; then exit 1 ; fi
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 181 ]; then exit 1 ; fi
 
 
 # DNA mapping
@@ -146,6 +146,8 @@ WC=`DNA-mapping -i SE_input -o output .ci_stuff/organism.yaml --snakemakeOptions
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 705 ]; then exit 1 ; fi
 WC=`DNA-mapping -i PE_input -o output .ci_stuff/organism.yaml --snakemakeOptions " --dryrun --conda-prefix /tmp" --DAG --trim --aligner bwa | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 719 ]; then exit 1 ; fi
+WC=`DNA-mapping -i PE_input -o output .ci_stuff/organism.yaml --snakemakeOptions " --dryrun --conda-prefix /tmp" --DAG --trim --aligner bwa-mem2 | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 719 ]; then exit 1 ; fi
 #allelic
 WC=`DNA-mapping -m allelic-mapping -i PE_input -o output --snakemakeOptions " --dryrun --conda-prefix /tmp" --VCFfile allelic_input/file.vcf.gz --strains strain1,strain2 .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 1297 ]; then exit 1 ; fi
@@ -252,6 +254,8 @@ if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 354 ]; then exit 1 ; fi
 # WGBS
 WC=`WGBS -i PE_input -o output --sampleSheet .ci_stuff/test_sampleSheet.tsv --snakemakeOptions " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 751 ]; then exit 1 ; fi
+WC=`WGBS -i PE_input -o output --sampleSheet .ci_stuff/test_sampleSheet.tsv --aligner bwameth2 --snakemakeOptions " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 751 ]; then exit 1 ; fi
 WC=`WGBS -i PE_input -o output --sampleSheet .ci_stuff/test_sampleSheet.tsv --snakemakeOptions " --dryrun --conda-prefix /tmp" --trim --GCbias .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 760 ]; then exit 1 ; fi
 WC=`WGBS -i BAM_input/filtered_bam -o output --sampleSheet .ci_stuff/test_sampleSheet.tsv --fromBAM --snakemakeOptions " --dryrun --conda-prefix /tmp" --GCbias .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
@@ -284,6 +288,8 @@ WC=`HiC -i PE_input -o output --snakemakeOptions " --dryrun --conda-prefix /tmp"
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 463 ]; then exit 1 ; fi
 WC=`HiC -i PE_input -o output --snakemakeOptions " --dryrun --conda-prefix /tmp" --noTAD .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 413 ]; then exit 1 ; fi
+WC=`HiC -i PE_input -o output --snakemakeOptions " --dryrun --conda-prefix /tmp" --aligner bwa-mem2 .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 463 ]; then exit 1 ; fi
 
 # preprocessing
 WC=`preprocessing -i PE_input -o output --snakemakeOptions " --dryrun --conda-prefix /tmp"  --fastqc --optDedupDist 2500 | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`

docs/content/News.rst

@@ -4,12 +4,15 @@ snakePipes News
 snakePipes 2.x.x
 ----------------
 
-* Bumped software versions in environment yamls.
+* Added apeglm2 logFC shrinkage to allelic DESeq2 results.
+* Added bwa-mem2 as an optional aligner to DNA-mapping and HiC, as well as as an additional tool to createIndices.
+* Added bwameth2 as an optional tool to createIndices - this will create a bwameth index with bwa-mem2.
+* Added bwameth2 as an optional aligner to WGBS - this will run bwameth with bwa-mem2 underneath.
+* Updated software versions in environment yamls.
+* Updated organism yamls.
 * Updated CSAW output.
 * Fixed a couple of issues in the ATAC-seq workflow after sofware versions update.
-* Updated organism yamls.
-* Added apeglm2 logFC shrinkage to allelic DESeq2 results.
-
+* Fixed genome size conversion to string.
 
 snakePipes 2.5.4
 ----------------

docs/content/workflows/HiC.rst

@@ -7,7 +7,7 @@ What it does
 ------------
 
 The snakePipes HiC workflow allows users to process their HiC data from raw fastq files to
-corrected HiC matrices and TADs. The workflow utilized mapping by BWA, followed by analysis
+corrected HiC matrices and TADs. The workflow utilized mapping by bwa or bwa-mem2 , followed by analysis
 using `HiCExplorer <https://www.nature.com/articles/s41467-017-02525-w>`__. The workflow follows the `example workflow described in the documentation of HiCExplorer <https://hicexplorer.readthedocs.io/en/latest/content/mES-HiC_analysis.html>`__, which explains each step in detail and would be useful for new users to have a look at. The output matrices
 are produced in the `.hdf5 <https://en.wikipedia.org/wiki/Hierarchical_Data_Format>`__ format.
 
@@ -123,7 +123,7 @@ Structure of output directory
 In addition to the FASTQ module results (see :ref:`running_snakePipes`), the workflow produces the following outputs::
 
     .
-    |--BWA
+    |--bwa
     |--FASTQ
     |--HiC_matrices
     |   |--logs
@@ -133,7 +133,7 @@ In addition to the FASTQ module results (see :ref:`running_snakePipes`), the wor
     |--TADs
         |--logs
 
-* **BWA** folder contains the mapping results in BAM format. The files were obtained after running `BWA <https://github.com/lh3/bwa>`__ on each of the paired-end reads individually.
+* **bwa** folder contains the mapping results in BAM format. The files were obtained after running `bwa <https://github.com/lh3/bwa>`__ on each of the paired-end reads individually.
 
 * **HiC_matrices** folder accommodates the contact matrices generated by `hicBuildMatrix <https://hicexplorer.readthedocs.io/en/latest/content/tools/hicBuildMatrix.html>`__. In case of merging samples or merging bins the initial matrix is saved in this folder along with the merged ones.
 

snakePipes/__init__.py

@@ -1 +1 @@
-__version__ = '2.5.4'
+__version__ = '2.6.0'

snakePipes/shared/organisms/GRCh38_gencode40.yaml

@@ -1,7 +1,9 @@
 blacklist_bed: /data/repository/organisms/GRCh38_gencode_40/akundaje/blacklist.bed
 bowtie2_index: /data/repository/organisms/GRCh38_gencode_40/Indices/BowtieIndex/genome
 bwa_index: /data/repository/organisms/GRCh38_gencode_40/Indices/BWAIndex/genome
+bwa_mem2_index: /data/repository/organisms/GRCh38_gencode_40/Indices/BWAMEM2Index/genome
 bwameth_index: /data/repository/organisms/GRCh38_gencode_40/Indices/BWAmethIndex/genome.fa
+bwameth2_index:
 extended_coding_regions_gtf: /data/repository/organisms/GRCh38_gencode_40/gencode/release-40/genes.slop.gtf
 genes_bed: /data/repository/organisms/GRCh38_gencode_40/gencode/release-40/genes.bed
 genes_gtf: /data/repository/organisms/GRCh38_gencode_40/gencode/release-40/genes.gtf

snakePipes/shared/organisms/GRCz10.yaml

@@ -5,7 +5,9 @@ genome_2bit: "/data/repository/organisms/GRCz10_ensembl/genome_fasta/genome.2bit
 bowtie2_index: "/data/repository/organisms/GRCz10_ensembl/BowtieIndex/genome"
 hisat2_index: "/data/repository/organisms/GRCz10_ensembl/HISAT2Index/genome"
 bwa_index: "/data/repository/organisms/GRCz10_ensembl/BWAindex/genome.fa"
+bwa_mem2_index: "/data/repository/organisms/GRCz10_ensembl/BWA2index/genome.fa"
 bwameth_index: "/data/repository/organisms/GRCz10_ensembl/BWAmethIndex/genome.fa"
+bwameth2_index:
 known_splicesites: "/data/repository/organisms/GRCz10_ensembl/ensembl/release-91/HISAT2/splice_sites.txt"
 star_index: "/data/repository/organisms/GRCz10_ensembl/STARIndex/2.7.10a/"
 genes_bed: "/data/repository/organisms/GRCz10_ensembl/ensembl/release-91/genes.bed"

snakePipes/shared/organisms/GRCz11.yaml

@@ -5,7 +5,9 @@ genome_2bit: "/data/repository/organisms/GRCz11_ensembl/genome_fasta/genome.2bit
 bowtie2_index: "/data/repository/organisms/GRCz11_ensembl/BowtieIndex/genome"
 hisat2_index: "/data/repository/organisms/GRCz11_ensembl/HISAT2Index/genome"
 bwa_index: "/data/repository/organisms/GRCz11_ensembl/BWAindex/genome.fa"
+bwa_mem2_index:  
 bwameth_index: "/data/repository/organisms/GRCz11_ensembl/BWAmethIndex/genome.fa"
+bwameth2_index: 
 known_splicesites: "/data/repository/organisms/GRCz11_ensembl/ensembl/release-100/HISAT2/splice_sites.txt"
 star_index: "/data/repository/organisms/GRCz11_ensembl/STARIndex/2.7.10a/"
 genes_bed: "/data/repository/organisms/GRCz11_ensembl/ensembl/release-100/genes.bed"

snakePipes/shared/organisms/SchizoSPombe_ASM294v2.yaml

@@ -5,6 +5,9 @@ genome_2bit: "/data/repository/organisms/SchizoSPombe_ASM294v2_ensembl/genome_fa
 bowtie2_index: "/data/repository/organisms/SchizoSPombe_ASM294v2_ensembl/BowtieIndex/genome"
 hisat2_index: "/data/repository/organisms/SchizoSPombe_ASM294v2_ensembl/HISAT2Index/genome"
 bwa_index: "/data/repository/organisms/SchizoSPombe_ASM294v2_ensembl/BWAindex/genome.fa"
+bwa_mem2_index: "/data/repository/organisms/SchizoSPombe_ASM294v2_ensembl/BWA2index/genome.fa"
+bwameth_index: "/data/repository/organisms/SchizoSPombe_ASM294v2_ensembl/BWAmethIndex/genome.fa"
+bwameth2_index: 
 known_splicesites: "/data/repository/organisms/SchizoSPombe_ASM294v2_ensembl/ensembl/release-35/HISAT2/splice_sites.txt"
 star_index: "/data/repository/organisms/SchizoSPombe_ASM294v2_ensembl/STARIndex/2.7.10a/"
 genes_bed: "/data/repository/organisms/SchizoSPombe_ASM294v2_ensembl/Ensembl/release-35/genes.bed"

snakePipes/shared/organisms/dm6.yaml

@@ -5,6 +5,9 @@ genome_2bit: "/data/repository/organisms/dm6_ensembl/genome_fasta/genome.2bit"
 bowtie2_index: "/data/repository/organisms/dm6_ensembl/BowtieIndex/genome"
 hisat2_index: "/data/repository/organisms/dm6_ensembl/HISAT2Index/genome"
 bwa_index: "/data/repository/organisms/dm6_ensembl/BWAindex/genome.fa"
+bwa_mem2_index: "/data/repository/organisms/dm6_ensembl/BWA2index/genome.fa"
+bwameth_index: "/data/repository/organisms/dm6_ensembl/BWAmethIndex/genome.fa"
+bwameth2_index:
 known_splicesites: "/data/repository/organisms/dm6_ensembl/ensembl/release-96/HISAT2/splice_sites.txt"
 star_index: "/data/repository/organisms/dm6_ensembl/STARIndex/2.7.10a/"
 genes_bed: "/data/repository/organisms/dm6_ensembl/Ensembl/release-96/genes.bed"

snakePipes/shared/organisms/hg38.yaml

@@ -5,6 +5,9 @@ genome_2bit: "/data/repository/organisms/GRCh38_ensembl/genome_fasta/genome.2bit
 bowtie2_index: "/data/repository/organisms/GRCh38_ensembl/BowtieIndex/genome"
 hisat2_index: "/data/repository/organisms/GRCh38_ensembl/HISAT2Index/genome"
 bwa_index: "/data/repository/organisms/GRCh38_ensembl/BWAindex/genome.fa"
+bwa_mem2_index: "/data/repository/organisms/GRCh38_ensembl/BWA2index/genome.fa"
+bwameth_index: "/data/repository/organisms/GRCh38_ensembl/BWAmethIndex/genome.fa"
+bwameth2_index: 
 known_splicesites: "/data/repository/organisms/GRCh38_ensembl/gencode/release_31/HISAT2/splice_sites.txt"
 star_index: "/data/repository/organisms/GRCh38_ensembl/STARIndex/2.7.10a/"
 genes_bed: "/data/repository/organisms/GRCh38_ensembl/gencode/release_31/genes.bed"

snakePipes/shared/organisms/mm10_gencodeM19.yaml

@@ -5,6 +5,9 @@ genome_2bit: "/data/repository/organisms/GRCm38_ensembl/genome_fasta/genome.2bit
 bowtie2_index: "/data/repository/organisms/GRCm38_ensembl/BowtieIndex/genome"
 hisat2_index: "/data/repository/organisms/GRCm38_ensembl/HISAT2Index/genome"
 bwa_index: "/data/repository/organisms/GRCm38_ensembl/BWAindex/genome.fa"
+bwa_mem2_index: "/data/repository/organisms/GRCm38_ensembl/BWA2index/genome.fa"
+bwameth_index: "/data/repository/organisms/GRCm38_ensembl/BWAmethIndex/genome.fa"
+bwameth2_index: 
 known_splicesites: "/data/repository/organisms/GRCm38_ensembl/gencode/m19/HISAT2/splice_sites.txt"
 star_index: "/data/repository/organisms/GRCm38_ensembl/STARIndex/2.7.10a/"
 genes_bed: "/data/repository/organisms/GRCm38_ensembl/gencode/m19/genes.bed"

snakePipes/shared/organisms/mm39_ens106.yaml

@@ -5,6 +5,9 @@ genome_2bit: "/data/repository/organisms/GRCm39_ensembl_106/genome_fasta/genome.
 bowtie2_index: "/data/repository/organisms/GRCm39_ensembl_106/Indices/BowtieIndex/genome"
 hisat2_index: "/data/repository/organisms/GRCm39_ensembl_106/Indices/HISAT2Index/genome"
 bwa_index: "/data/repository/organisms/GRCm39_ensembl_106/Indices/BWAindex/genome.fa"
+bwa_mem2_index: "/data/repository/organisms/GRCm39_ensembl_106/Indices/BWAMEM2Index/genome"
+bwameth_index: "/data/repository/organisms/GRCm39_ensembl_106/Indices/BWAmethIndex/genome.fa"
+bwameth2_index: 
 known_splicesites: "/data/repository/organisms/GRCm39_ensembl_106/ensembl/release-106/HISAT2/genome.ss"
 star_index: "/data/repository/organisms/GRCm39_ensembl_106/Indices/STARIndex/2.7.10a/"
 genes_bed: "/data/repository/organisms/GRCm39_ensembl_106/ensembl/release-106/genes.bed"

snakePipes/shared/rules/WGBS.snakefile

@@ -25,12 +25,12 @@ if pairedEnd and not fromBAM:
             r1=fastq_dir + "/{sample}" + reads[0] + ".fastq.gz",
             r2=fastq_dir + "/{sample}" + reads[1] + ".fastq.gz"
         output:
-            sbam=temp("bwameth/{sample}.bam")
+            sbam=temp(aligner+"/{sample}.bam")
         log:
-            err="bwameth/logs/{sample}.map_reads.err",
-            out="bwameth/logs/{sample}.map_reads.out"
+            err=aligner+"/logs/{sample}.map_reads.err",
+            out=aligner+"/logs/{sample}.map_reads.out"
         params:
-            bwameth_index=bwameth_index,
+            bwameth_index=bwameth_index if aligner=="bwameth" else bwameth2_index,
             tempDir = tempDir
         threads: lambda wildcards: 20 if 20<max_thread else max_thread
         conda: CONDA_WGBS_ENV
@@ -47,12 +47,12 @@ elif not pairedEnd and not fromBAM:
         input:
             r1=fastq_dir + "/{sample}" + reads[0] + ".fastq.gz",
         output:
-            sbam=temp("bwameth/{sample}.bam")
+            sbam=temp(aligner+"/{sample}.bam")
         log:
-            err="bwameth/logs/{sample}.map_reads.err",
-            out="bwameth/logs/{sample}.map_reads.out"
+            err=aligner+"/logs/{sample}.map_reads.err",
+            out=aligner+"/logs/{sample}.map_reads.out"
         params:
-            bwameth_index=bwameth_index,
+            bwameth_index=bwameth_index if aligner=="bwameth" else bwameth2_index,
             tempDir = tempDir
         threads: lambda wildcards: 20 if 20<max_thread else max_thread
         conda: CONDA_WGBS_ENV
@@ -67,12 +67,12 @@ elif not pairedEnd and not fromBAM:
 if not fromBAM:
     rule index_bam:
         input:
-            "bwameth/{sample}.bam"
+            aligner+"/{sample}.bam"
         output:
-            temp("bwameth/{sample}.bam.bai")
+            temp(aligner+"/{sample}.bam.bai")
         log:
-            err="bwameth/logs/{sample}.index_bam.err",
-            out="bwameth/logs/{sample}.index_bam.out"
+            err=aligner+"/logs/{sample}.index_bam.err",
+            out=aligner+"/logs/{sample}.index_bam.out"
         conda: CONDA_SHARED_ENV
         shell: """
             samtools index "{input}" > {log.out} 2> {log.err}
@@ -81,8 +81,8 @@ if not fromBAM:
 if not skipBamQC:
     rule markDupes:
         input:
-            "bwameth/{sample}.bam",
-            "bwameth/{sample}.bam.bai"
+            aligner+"/{sample}.bam",
+            aligner+"/{sample}.bam.bai"
         output:
             "Sambamba/{sample}.markdup.bam"
         log:

snakePipes/shared/rules/bwa-mem2.snakefile

@@ -0,0 +1,53 @@
+if pairedEnd:
+    rule bwamem2:
+        input:
+            r1 = fastq_dir+"/{sample}"+reads[0]+".fastq.gz",
+            r2 = fastq_dir+"/{sample}"+reads[1]+".fastq.gz"
+        output:
+            align_summary = "bwa-mem2/{sample}.bwa-mem2_summary.txt", #samtools flagstat
+            bam = temp("bwa-mem2/{sample}.sorted.bam")
+        log: "bwa-mem2/logs/{sample}.sort.log"
+        params:
+            bwa_index = bwa_mem2_index,
+            alignerOpts = str(alignerOpts or ''),
+            tempDir = tempDir
+        threads: lambda wildcards: 8 if 8<max_thread else max_thread
+        conda: CONDA_DNA_MAPPING_ENV
+        shell:"""
+            TMPDIR={params.tempDir}
+            MYTEMP=$(mktemp -d ${{TMPDIR:-/tmp}}/snakepipes.XXXXXXXXXX);
+            bwa-mem2 mem \
+            -t 6 \
+            -R '@RG\\tID:{wildcards.sample}\\tDS:{wildcards.sample}\\tPL:ILLUMINA\\tSM:{wildcards.sample}' {params.alignerOpts} \
+            {params.bwa_index} {input.r1} {input.r2} | \
+            samtools view -Sb - | \
+            samtools sort -m 2G -@ 2 -O bam - > {output.bam} 2> {log};
+            rm -rf $MYTEMP
+            samtools flagstat {output.bam} > {output.align_summary}
+        """
+else:
+    rule bwamem2:
+        input:
+            fastq_dir+"/{sample}"+reads[0]+".fastq.gz"
+        output:
+            align_summary = "bwa-mem2/{sample}.bwa-mem2_summary.txt", #samtools flagstat
+            bam = temp("bwa-mem2/{sample}.sorted.bam")
+        log: "bwa-mem2/logs/{sample}.sort.log"
+        params:
+            bwa_index = bwa_mem2_index,
+            alignerOpts = str(alignerOpts or ''),
+            tempDir = tempDir
+        threads : lambda wildcards: 12 if 12<max_thread else max_thread
+        conda: CONDA_DNA_MAPPING_ENV
+        shell: """
+            TMPDIR={params.tempDir}
+            MYTEMP=$(mktemp -d ${{TMPDIR:-/tmp}}/snakepipes.XXXXXXXXXX);
+            bwa-mem2 mem \
+            -t {threads} \
+            -R '@RG\\tID:{wildcards.sample}\\tDS:{wildcards.sample}\\tPL:ILLUMINA\\tSM:{wildcards.sample}' {params.alignerOpts}\
+            {params.bwa_index} {input} | \
+            samtools view -Sbu - | \
+            samtools sort -m 2G -T $MYTEMP/{wildcards.sample} -@ 2 -O bam - > {output.bam} 2> {log};
+            rm -rf $MYTEMP
+            samtools flagstat {output.bam} > {output.align_summary}
+        """