Feat sage

README.md

@@ -35,17 +35,17 @@ LOGAN supports either
 LOGAN supports inputs of either 
 1) paired end fastq files
 
-`--fastq_input`- A glob can be used to include all FASTQ files. Like `--fastq_input "*R{1,2}.fastq.gz"`. Globbing requires quotes
+`--fastq_input`- A glob can be used to include all FASTQ files. Like `--fastq_input "*R{1,2}.fastq.gz"`. Globbing requires quotes.
 
 2) Pre aligned BAM files with BAI indices 
 
-`--bam_input`- A glob can be used to include all FASTQ files. Like `--bam_input "*.bam"`. Globbing requires quotes
+`--bam_input`- A glob can be used to include all FASTQ files. Like `--bam_input "*.bam"`. Globbing requires quotes.
 
 3) A sheet that indicates the sample name and either FASTQs or BAM file locations
 
 `--fastq_file_input`-  A headerless tab delimited sheet that has the sample name, R1, and R2 file locations
 
-`--bam_file_input` -  A headerless tab delimited sheet that has the sample name, bam and bai file locations
+`--bam_file_input` -  A headerless tab delimited sheet that has the sample name, bam, and bam index (bai) file locations
 
 ### Operating Modes
 
@@ -64,30 +64,50 @@ No flags are required
 
 Adding flags determines SNV (germline and/or somatic), SV, and/or CNV calling modes
 
-`--vc`- Enables somatic SNV calling using mutect2, vardict, varscan, octopus, MUSE (TN only), and lofreq (TN only)
+`--vc`- Enables somatic SNV calling using mutect2, vardict, varscan, octopus, sage, MUSE (TN only), and lofreq (TN only)
+
 
 `--germline`- Enables germline using DV
 
 `--sv`- Enables somatic SV calling using Manta and SVABA
 
-`--vc`- Enables somatic CNV calling using FREEC, Sequenza, and Purple (hg38 only)
+`--cnv`- Enables somatic CNV calling using FREEC, Sequenza, and Purple (hg38 only)
+
+
 
 #### Optional Arguments
 `--indelrealign` - Enables indel realignment when running alignment steps. May be helpful for certain callers (VarScan, VarDict)
 
-`--callers`- Comma separated argument for callers, the default is to use all available. Example: `--callers mutect2,octopus,vardict,varscan`
+`--callers`- Comma separated argument for callers, the default is to use all available.  
+Example: `--callers mutect2,octopus`
+
+`--cnvcallers`- - Comma separated argument for cnvcallers. Adding flag allows only certain callers to run.  
+Example: `--cnvcallers purple`
+
 
 ## Running LOGAN
+Example of Tumor_Normal calling mode 
+```bash
+# copy the logan config files to your current directory
+logan init
+# preview the logan jobs that will run 
+logan run --mode local -profile ci_stub --genome hg38 --sample_sheet samplesheet.tsv --outdir out --fastq_input "*R{1,2}.fastq.gz" -preview --vc --sv --cnv
+# run a stub/dryrun of the logan jobs 
+logan run --mode local -profile ci_stub --genome hg38 --sample_sheet samplesheet.tsv --outdir out --fastq_input "*R{1,2}.fastq.gz" -stub --vc --sv --cnv
+# launch a logan run on slurm with the test dataset
+logan run --mode slurm -profile biowulf,slurm --genome hg38 --sample_sheet samplesheet.tsv --outdir out --fastq_input "*R{1,2}.fastq.gz" --vc --sv --cnv 
+```
+
 Example of Tumor only calling mode 
 ```bash
 # copy the logan config files to your current directory
 logan init
 # preview the logan jobs that will run 
-logan run --mode local -profile ci_stub --genome hg38 --outdir out --fastq_input "*R{1,2}.fastq.gz" -preview --vc --sv --cnv
+logan run --mode local -profile ci_stub --genome hg38 --outdir out --fastq_input "*R{1,2}.fastq.gz" --callers octopus,mutect2 -preview --vc --sv --cnv
 # run a stub/dryrun of the logan jobs 
-logan run --mode local -profile ci_stub --genome hg38 --outdir out --fastq_input "*R{1,2}.fastq.gz" -stub --vc --sv --cnv
+logan run --mode local -profile ci_stub --genome hg38 --outdir out --fastq_input "*R{1,2}.fastq.gz" --callers octopus,mutect2 -stub --vc --sv --cnv
 # launch a logan run on slurm with the test dataset
-logan run --mode slurm -profile biowulf,slurm --genome hg38 --outdir out --fastq_input "*R{1,2}.fastq.gz" --vc --sv --cnv
+logan run --mode slurm -profile biowulf,slurm --genome hg38 --outdir out --fastq_input "*R{1,2}.fastq.gz" --callers octopus,mutect2 --vc --sv --cnv
 ```
 
 We currently support the hg38, hg19 (in progress), and mm10 genomes. 

bin/flowcell_lane.py

@@ -40,19 +40,6 @@ def usage(message = '', exitcode = 0):
     sys.exit(exitcode)
 
 
-def reader(fname):
-    """Returns correct file object handler or reader for gzipped
-    or non-gzipped FastQ files based on the file extension. Assumes
-    gzipped files endwith the '.gz' extension.
-    """
-    if fname.endswith('.gz'):
-        # Opens up file with gzip handler
-        return gzip.open
-    else:
-        # Opens up file normal, uncompressed handler
-        return open
-
-
 def get_flowcell_lane(sequence_identifer):
     """Returns flowcell and lane information for different fastq formats.
     FastQ files generated with older versions of Casava or downloaded from
@@ -130,10 +117,10 @@ def md5sum(filename, blocksize = 65536):
     md5 = md5sum(filename)
 
     # Get Flowcell and Lane information
-    handle = reader(filename)
+    handle = gzip.open if filename.endswith('.gz') else open
     meta = {'flowcell': [], 'lane': [], 'flowcell_lane': []}
     i = 0  # keeps track of line number
-    with handle(filename, 'r') as file:
+    with handle(filename, 'rt') as file:
         print('sample_name\ttotal_read_pairs\tflowcell_ids\tlanes\tflowcell_lanes\tmd5_checksum')
         for line in file:
             line = line.strip()

conf/genomes.config

@@ -28,15 +28,18 @@ params {
             octopus_gforest= "--forest /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/octopus/germline.v0.7.4.forest"
             SEQUENZAGC = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/SEQUENZA/hg38_gc50Base.txt.gz"
             chromosomes = ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']
+            //HMFTOOLS
+            GENOMEVER = "38"
+            HOTSPOTS = "-hotspots /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/hmftools/v5_34/ref/38/variants/KnownHotspots.somatic.38.vcf.gz"
+            PANELBED = "-panel_bed /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/hmftools/v5_34/ref/38/variants/ActionableCodingPanel.38.bed.gz"
+            HCBED = "-high_confidence_bed /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/hmftools/v5_34/ref/38/variants/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_nosomaticdel_noCENorHET7.bed.gz"
+            ENSEMBLCACHE = "-ensembl_data_dir /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/hmftools/v5_34/ref/38/common/ensembl_data"
             //PURPLE
-            GERMLINEHET = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/PURPLE/GermlineHetPon.38.vcf.gz"
-            GCPROFILE = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/PURPLE/GC_profile.1000bp.38.cnp"
-            DIPLODREG = '/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/PURPLE/DiploidRegions.38.bed.gz'
-            ENSEMBLCACHE = '/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/PURPLE/ensembl_data/'
-            DRIVERS = '/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/PURPLE/DriverGenePanel.38.tsv'
-            HOTSPOTS = '/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/PURPLE/KnownHotspots.somatic.38.vcf.gz'
-
-        }
+            GERMLINEHET = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/hmftools/v5_34/ref/38/copy_number/AmberGermlineSites.38.tsv.gz"
+            GCPROFILE = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/hmftools/v5_34/ref/38/copy_number/GC_profile.1000bp.38.cnp"
+            DIPLODREG = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/hmftools/v5_34/ref/38/copy_number/DiploidRegions.38.bed.gz"
+            DRIVERS = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/hmftools/v5_34/ref/38/common/DriverGenePanel.38.tsv"
+        }  
 
         'hg19' {
             genome = "/data/CCBR_Pipeliner/db/PipeDB/lib/hg19.with_extra.fa"
@@ -65,8 +68,14 @@ params {
             octopus_gforest= "" //"--forest /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/octopus/germline.v0.7.4.forest"
             SEQUENZAGC = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/SEQUENZA/hg38_gc50Base.txt.gz"
             chromosomes = ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']
+            //HMFTOOLS
+            GENOMEVER = "37"
+            HOTSPOTS = "-hotspots /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/hmftools/v5_34/ref/38/variants/KnownHotspots.38.vcf.gz"
+            PANELBED = "-panel_bed /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/hmftools/v5_34/ref/38/variants/ActionableCodingPanel.38.bed.gz"
+            HCBED = "-high_confidence_bed /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/hmftools/v5_34/ref/38/variants/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_nosomaticdel_noCENorHET7.bed.gz"
+            ENSEMBLCACHE = "-ensembl_data_dir /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/hmftools/v5_34/ref/38/common/ensembl_data"
              //PURPLE
-            GERMLINEHET = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/PURPLE/GermlineHetPon.38.vcf.gz"
+            GERMLINEHET = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/hmftools/v5_34/ref/38/copy_number/AmberGermlineSites.38.tsv.gz"
             GCPROFILE = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/PURPLE/GC_profile.1000bp.38.cnp"
             DIPLODREG = '/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/PURPLE/DiploidRegions.38.bed.gz'
             ENSEMBLCACHE = '/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/PURPLE/ensembl_data/'

docker/logan_base/Dockerfile

@@ -20,16 +20,18 @@ WORKDIR /opt2
 RUN apt-get update \
  && apt-get -y upgrade \
  && DEBIAN_FRONTEND=noninteractive apt-get install -y \
-      bc    
+      bc \
+      openjdk-17-jdk   
 
 # Common bioinformatics tools 
 # bwa/0.7.17-4  bowtie/1.2.3  bowtie2/2.3.5.1 
 # bedtools/2.27.1  bedops/2.4.37  samtools/1.10 
 # bcftools/1.10.2  vcftools/0.1.16  
-# Previous tools already installed trimmomatic/0.39  tabix/1.10.2
+# Previous tools already installed  tabix/1.10.2 trimmomatic/0.39 
 RUN DEBIAN_FRONTEND=noninteractive apt-get install -y \
-      tabix \
-      trimmomatic 
+    tabix \
+    libhts-dev
+
 
 # Install BWA-MEM2 v2.2.1
 RUN wget https://github.com/bwa-mem2/bwa-mem2/releases/download/v2.2.1/bwa-mem2-2.2.1_x64-linux.tar.bz2 \
@@ -44,13 +46,17 @@ RUN wget https://github.com/biod/sambamba/releases/download/v0.8.1/sambamba-0.8.
     && mv /opt2/sambamba-0.8.1-linux-amd64-static /opt2/sambamba \
     && chmod a+rx /opt2/sambamba
 
-# Install GATK4 (GATK/4.3.0.0)
-# Requires Java8 or 1.8
-RUN wget https://github.com/broadinstitute/gatk/releases/download/4.3.0.0/gatk-4.3.0.0.zip \
-    && unzip /opt2/gatk-4.3.0.0.zip \
-    && rm /opt2/gatk-4.3.0.0.zip \
-    && /opt2/gatk-4.3.0.0/gatk --list
-ENV PATH="/opt2/gatk-4.3.0.0:$PATH"
+# Install GATK4 (GATK/4.4.0.0)
+# Requires Java17 
+RUN wget https://github.com/broadinstitute/gatk/releases/download/4.4.0.0/gatk-4.4.0.0.zip \
+    && unzip /opt2/gatk-4.4.0.0.zip \
+    && rm /opt2/gatk-4.4.0.0.zip \
+    && /opt2/gatk-4.4.0.0/gatk --list
+ENV PATH="/opt2/gatk-4.4.0.0:$PATH"
+
+# Use DISCVRSeq For CombineVariants Replacement
+RUN wget https://github.com/BimberLab/DISCVRSeq/releases/download/1.3.62/DISCVRSeq-1.3.62.jar 
+ENV DISCVRSeq_JAR="/opt2/DISCVRSeq-1.3.62.jar"
 
 # Install last release of GATK3 (GATK/3.8-1)
 # Only being used for the CombineVariants
@@ -168,29 +174,57 @@ RUN wget https://github.com/AstraZeneca-NGS/VarDictJava/releases/download/v1.8.3
 ENV PATH="/opt2/VarDict-1.8.3/bin:$PATH"
 
 # Fastp From Opengene github
-RUN wget http://opengene.org/fastp/fastp.0.23.2 \
+RUN wget http://opengene.org/fastp/fastp.0.23.4 \
     && mkdir fastp \
-    && mv fastp.0.23.2 fastp/fastp \
+    && mv fastp.0.23.4 fastp/fastp \
     && chmod a+x fastp/fastp
 ENV PATH="/opt2/fastp:$PATH"
 
-# HMFtools for PURPLE/COBALT/AMBER
-RUN wget https://github.com/hartwigmedical/hmftools/releases/download/amber-v3.9/amber-3.9.jar \
-    && wget https://github.com/hartwigmedical/hmftools/releases/download/cobalt-v1.15.1/cobalt_v1.15.1.jar \
-    && wget https://github.com/hartwigmedical/hmftools/releases/download/purple-v3.9/purple_v3.9.jar \
-    && mkdir hmftools \
-    && mv amber-3.9.jar hmftools/amber.jar \
-    && mv cobalt_v1.15.1.jar hmftools/cobalt.jar \
-    && mv purple_v3.9.jar hmftools/purple.jar \
-    && chmod a+x hmftools/amber.jar
-ENV PATH="/opt2/hmftools:$PATH"
+# ASCAT 
+RUN Rscript -e 'devtools::install_github("VanLoo-lab/ascat/ASCAT")'
 
 # SvABA
 RUN wget -O svaba_1.2.0 https://github.com/walaj/svaba/releases/download/v1.2.0/svaba \
     && mkdir svaba \ 
-    && mv svaba_1.2.0 svaba/svaba
+    && mv svaba_1.2.0 svaba/svaba \
+    && chmod a+x svaba/svaba
+
 ENV PATH="/opt2/svaba:$PATH"
 
+# LOFREQ
+RUN git clone https://github.com/CSB5/lofreq \
+    && cd /opt2/lofreq \
+    && ./bootstrap \
+    && ./configure --prefix=/opt2/lofreq/ \
+    && make \
+    && make install 
+
+ENV PATH="/opt2/lofreq/bin:$PATH"
+
+# MUSE
+RUN wget -O muse_2.0.4.tar.gz https://github.com/wwylab/MuSE/archive/refs/tags/v2.0.4.tar.gz \
+    && tar -xzf muse_2.0.4.tar.gz \ 
+    && cd MuSE-2.0.4 \
+    && ./install_muse.sh \
+    && mv MuSE /opt2/ \
+    && chmod a+x /opt2/MuSE \
+    && rm -R /opt2/MuSE-2.0.4 \
+    && rm /opt2/muse_2.0.4.tar.gz
+
+ENV PATH="/opt2/MuSE:$PATH"
+
+# HMFtools for PURPLE/COBALT/AMBER
+RUN wget https://github.com/hartwigmedical/hmftools/releases/download/amber-v4.0/amber-4.0.jar \
+    && wget https://github.com/hartwigmedical/hmftools/releases/download/cobalt-v1.16/cobalt_v1.16.jar \
+    && wget https://github.com/hartwigmedical/hmftools/releases/download/purple-v4.0/purple_v4.0.jar \
+    && wget https://github.com/hartwigmedical/hmftools/releases/download/sage-v3.4/sage_v3.4.jar \ 
+    && mkdir hmftools \
+    && mv amber-4.0.jar hmftools/amber.jar \
+    && mv cobalt_v1.16.jar hmftools/cobalt.jar \
+    && mv purple_v4.0.jar hmftools/purple.jar \
+    && mv sage.v3.4.jar hmftools/sage.jar \
+    && chmod a+x hmftools/amber.jar
+ENV PATH="/opt2/hmftools:$PATH"
 
 # Add Dockerfile and argparse.bash script
 # and export environment variables

docker/logan_base/build.sh

@@ -1,14 +1,17 @@
+
 # Build image
 #docker buildx create --platform linux/amd64 --use
 #docker buildx use upbeat_ganguly
 #docker buildx inspect upbeat_ganguly
 #docker buildx build --platform linux/amd64 -f Dockerfile -t dnousome/ccbr_logan_base:v0.3.0 -t dnousome/ccbr_logan_base:latest --push .
 
-docker build --platform linux/amd64 --tag ccbr_logan_base:v0.3.0 -f Dockerfile . 
-docker tag ccbr_logan_base:v0.3.0 dnousome/ccbr_logan_base:v0.3.0
-docker tag ccbr_logan_base:v0.3.0 dnousome/ccbr_logan_base
+docker build --platform linux/amd64 --tag ccbr_logan_base:v0.3.5 -f Dockerfile . 
+
+docker tag ccbr_logan_base:v0.3.5 dnousome/ccbr_logan_base:v0.3.5
+docker tag ccbr_logan_base:v0.3.5 dnousome/ccbr_logan_base
 
-docker push dnousome/ccbr_logan_base:v0.3.0
+
+docker push dnousome/ccbr_logan_base:v0.3.5
 docker push dnousome/ccbr_logan_base:latest
 
 
@@ -21,4 +24,3 @@ docker push dnousome/ccbr_logan_base:latest
 # Push image to DockerHub
 #docker push nciccbr/ccbr_wgs_base:v0.1.0
 #docker push nciccbr/ccbr_wgs_base:latest
-

docker/logan_base/meta.yml

@@ -1,4 +1,4 @@
 dockerhub_namespace: dnousome
 image_name: ccbr_logan_base
-version: v0.3.4
+version: v0.3.5
 container: "$(dockerhub_namespace)/$(image_name):$(version)"