Merge branch 'master' into bump_versions

Docker/Dockerfile

@@ -0,0 +1,36 @@
+FROM ubuntu:20.04
+
+LABEL base.image="ubuntu:20.04"
+LABEL dockerfile.version="1"
+LABEL software="BBTools"
+LABEL software.version="38.96"
+LABEL description="A set of tools labeled as \"Bestus Bioinformaticus\""
+LABEL website="https://jgi.doe.gov/data-and-tools/bbtools/bb-tools-user-guide/"
+LABEL license="https://jgi.doe.gov/disclaimer/"
+LABEL maintainer="Chienchi Lo"
+LABEL maintainer.email="[email protected]"
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV LANG=en_US.UTF-8
+ENV JAVA_HOME=/usr/java/openjdk-13
+ENV PATH=/usr/java/openjdk-13/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
+ENV JAVA_VERSION=13.0.1
+ENV JAVA_URL=https://download.java.net/java/GA/jdk13.0.1/cec27d702aa74d5a8630c65ae61e4305/9/GPL/openjdk-13.0.1_linux-x64_bin.tar.gz
+ENV JAVA_SHA256=2e01716546395694d3fad54c9b36d1cd46c5894c06f72d156772efbcf4b41335
+
+
+RUN apt-get update && apt-get install -y build-essential file python \
+  wget samtools curl && \
+  apt-get autoclean && rm -rf /var/lib/apt/lists/*
+
+# openjdk-13-jre \
+RUN /bin/sh -c set -eux; curl -fL -o /openjdk.tgz "$JAVA_URL"; 	echo "$JAVA_SHA256 */openjdk.tgz" | sha256sum -c -; mkdir -p "$JAVA_HOME"; tar --extract --file /openjdk.tgz --directory "$JAVA_HOME" --strip-components 1; rm /openjdk.tgz; ln -sfT "$JAVA_HOME" /usr/java/default; ln -sfT "$JAVA_HOME" /usr/java/latest; for bin in "$JAVA_HOME/bin/"*; do 	base="$(basename "$bin")"; [ ! -e "/usr/bin/$base" ]; 	update-alternatives --install "/usr/bin/$base" "$base" "$bin" 20000; 	done; java -Xshare:dump; java --version; javac --version
+
+RUN wget https://sourceforge.net/projects/bbmap/files/BBMap_38.96.tar.gz && \
+  tar -xzf BBMap_38.96.tar.gz && \
+  rm BBMap_38.96.tar.gz
+
+ENV PATH="${PATH}:/bbmap"\
+ LC_ALL=C
+
+WORKDIR /data

README.md

@@ -2,7 +2,7 @@
 
 ## Summary
 
-This workflow is replicate the [QA protocol](https://jgi.doe.gov/data-and-tools/bbtools/bb-tools-user-guide/data-preprocessing/) implemented at JGI for Illumina reads and use the program “rqcfilter2” from BBTools(38:44) which implements them as a pipeline. 
+This workflow is a replicate of the [QA protocol](https://jgi.doe.gov/data-and-tools/bbtools/bb-tools-user-guide/data-preprocessing/) implemented at JGI for Illumina reads and use the program “rqcfilter2” from BBTools(38:96) which implements them as a pipeline. 
 
 ## Required Database
 
@@ -27,15 +27,18 @@ Description of the files:
 
 ## The Docker image and Dockerfile can be found here
 
-[microbiomedata/bbtools:38.44](https://hub.docker.com/r/microbiomedata/bbtools)
+[microbiomedata/bbtools:38.92](https://hub.docker.com/r/microbiomedata/bbtools)
 
 ## Input files
 
 1. database path, 
 2. fastq (illumina paired-end interleaved fastq), 
 3. output path
-4. memory (optional) ex: "jgi_rqcfilter.memory": "35G"
-5. threads (optional) ex: "jgi_rqcfilter.threads": "16"
+4. input_interleaved (boolean)
+5. forwards reads fastq file (when input_interleaved is false)
+6. reverse reads fastq file (when input_interleaved is false)
+7. memory (optional) ex: "jgi_rqcfilter.memory": "35G"
+8. threads (optional) ex: "jgi_rqcfilter.threads": "16"
 
 ```
 {
@@ -46,6 +49,9 @@ Description of the files:
         "/global/cfs/cdirs/m3408/ficus/8434.3.102077.ATGTCA.fastq.gz"
     ], 
     "jgi_rqcfilter.outdir": "/global/cfs/cdirs/m3408/ficus_rqcfiltered",
+    "jgi_rqcfilter.input_interleaved": true,
+    "jgi_rqcfilter.input_fq1":[],
+    "jgi_rqcfilter.input_fq2":[],
     "jgi_rqcfilter.memory": "35G",
     "jgi_rqcfilter.threads": "16"
 }

docs/index.rst

@@ -11,6 +11,28 @@ Workflow Overview
 
 This workflow utilizes the program “rqcfilter2” from BBTools to perform quality control on raw Illumina reads. The workflow performs quality trimming, artifact removal, linker trimming, adapter trimming, and spike-in removal (using BBDuk), and performs human/cat/dog/mouse/microbe removal (using BBMap).
 
+The following parameters are used for "rqcfilter2" in this workflow::
+ - qtrim=r     :  Quality-trim from right ends before mapping.
+ - trimq=0     :  Trim quality threshold.
+ - maxns=3     :  Reads with more Ns than this will be discarded.
+ - maq=3       :  Reads with average quality (before trimming) below this will be discarded.
+ - minlen=51   :  Reads shorter than this after trimming will be discarded.  Pairs will be discarded only if both are shorter.
+ - mlf=0.33    :  Reads shorter than this fraction of original length after trimming will be discarded.
+ - phix=true   :  Remove reads containing phiX kmers.
+ - khist=true  :  Generate a kmer-frequency histogram of the output data.
+ - kapa=true   :  Remove and quantify kapa tag
+ - trimpolyg=5 :  Trim reads that start or end with a G polymer at least this long
+ - clumpify=true       :  Run clumpify; all deduplication flags require this.
+ - removehuman=true    :  Remove human reads via mapping.
+ - removedog=true      :  Remove dog reads via mapping.
+ - removecat=true      :  Remove cat reads via mapping.
+ - removemouse=true    :  Remove mouse reads via mapping.
+ - barcodefilter=false :  Disable improper barcodes filter
+ - chastityfilter=false:  Remove illumina reads failing chastity filter.
+ - trimfragadapter=true:  Trim all known Illumina adapter sequences, including TruSeq and Nextera.
+ - removemicrobes=true :  Remove common contaminant microbial reads via mapping, and place them in a separate file.
+
+ 
 Workflow Availability
 ---------------------
 
@@ -39,7 +61,7 @@ Workflow Dependencies
 Third party software (This is included in the Docker image.)  
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-- `BBTools v38.90 <https://jgi.doe.gov/data-and-tools/bbtools/>`_ (License: `BSD-3-Clause-LBNL <https://bitbucket.org/berkeleylab/jgi-bbtools/src/master/license.txt>`_)
+- `BBTools v38.96 <https://jgi.doe.gov/data-and-tools/bbtools/>`_ (License: `BSD-3-Clause-LBNL <https://bitbucket.org/berkeleylab/jgi-bbtools/src/master/license.txt>`_)
 
 Requisite database
 ~~~~~~~~~~~~~~~~~~
@@ -79,8 +101,11 @@ A JSON file containing the following information:
 1.	the path to the database
 2.	the path to the interleaved fastq file (input data) 
 3.	the path to the output directory
-4.	(optional) parameters for memory 
-5.	(optional) number of threads requested
+4.      input_interleaved (boolean)
+5.      forwards reads fastq file (when input_interleaved is false) 
+6.      reverse reads fastq file (when input_interleaved is false)     
+7.	(optional) parameters for memory 
+8.	(optional) number of threads requested
 
 
 An example input JSON file is shown below:
@@ -92,6 +117,9 @@ An example input JSON file is shown below:
         "jgi_rqcfilter.input_files": [
             "/path/to/SRR7877884-int-0.1.fastq.gz "
         ],
+        "jgi_rqcfilter.input_interleaved": true,
+        "jgi_rqcfilter.input_fq1":[],
+        "jgi_rqcfilter.input_fq2":[],
         "jgi_rqcfilter.outdir": "/path/to/rqcfiltered",
         "jgi_rqcfilter.memory": "35G",
         "jgi_rqcfilter.threads": "16"

input.json

@@ -10,5 +10,8 @@
         "/global/cfs/cdirs/m3408/ficus/8434.1.102069.ACAGTG.fastq.gz", 
         "/global/cfs/cdirs/m3408/ficus/8434.3.102077.ATGTCA.fastq.gz"
     ], 
-    "jgi_rqcfilter.outdir": "/global/cfs/cdirs/m3408/ficus_rqcfiltered"
-}
+    "jgi_rqcfilter.input_fq1":[],
+    "jgi_rqcfilter.input_fq2":[],
+    "jgi_rqcfilter.outdir": "/global/cfs/cdirs/m3408/ficus_rqcfiltered",
+    "jgi_rqcfilter.input_interleaved": true
+}