Merge pull request #9 from GeneDx/add-deletions

Add deletions

Dockerfile

@@ -1,43 +1,44 @@
 # source Image
-FROM ubuntu:18.04
+FROM ubuntu:20.04
 
 # set noninterative mode
 ENV DEBIAN_FRONTEND noninteractive
 
 # apt-get update and install global requirements
 RUN apt-get clean all && \
-  apt-get update && \
-  apt-get upgrade -y && \
-  apt-get install -y  \
-      build-essential \
-      libbz2-dev \
-      libcurl4-openssl-dev \
-      liblzma-dev \
-      libncurses5-dev \
-      libnss-sss \
-      libssl-dev \
-      r-base \
-      zlib1g-dev
+    apt-get update && \
+    apt-get upgrade -y && \
+    apt-get install -y  \
+        autoconf \
+        autogen \
+        build-essential \
+        curl \
+        libbz2-dev \
+        libcurl4-openssl-dev \
+        libhts3 \
+        libhts-dev \
+        liblzma-dev \
+        libncurses5-dev \
+        libnss-sss \
+        libssl-dev \
+        libxml2-dev \
+        ncbi-blast+ \
+        r-base \
+        r-bioc-biostrings \
+        r-bioc-rsamtools \
+        r-cran-biocmanager \
+        r-cran-devtools \
+        r-cran-stringr \
+        r-cran-optparse \
+        zlib1g-dev
 
 # apt-get clean and remove cached source lists
 RUN apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
 # install global r requirements
 RUN echo "r <- getOption('repos'); r['CRAN'] <- 'http://cran.us.r-project.org'; options(repos = r);" > ~/.Rprofile
-RUN Rscript -e "install.packages('optparse')"
-RUN Rscript -e "install.packages('stringr')"
-RUN Rscript -e "source('https://bioconductor.org/biocLite.R'); biocLite('Biostrings')"
-
-# install htslib
-RUN curl -LO https://github.com/samtools/htslib/releases/download/1.10.2/htslib-1.10.2.tar.bz2 && \
-    tar xfj htslib-1.10.2.tar.bz2 && \
-    cd htslib-1.10.2 && \
-    autoheader && \
-    autoconf && \
-    ./configure && \
-    make && \
-    make install
+RUN Rscript -e "library(devtools); install_github('mhahsler/rBLAST')"
 
 # install scramble
 COPY . /app

README.md

@@ -12,54 +12,42 @@ clusters. For how to build see the build section.
 Build
 -----
 
-Install dependencies (Debian/Ubuntu):
+Install dependencies (Ubuntu 20.04):
 
-    $ apt-get update
-    $ apt-get install -y  \
+    apt-get update
+    apt-get install -y  \
+        autoconf \
+        autogen \
         build-essential \
+        curl \
         libbz2-dev \
         libcurl4-openssl-dev \
+        libhts-dev \
         liblzma-dev \
         libncurses5-dev \
         libnss-sss \
         libssl-dev \
-        libhts-dev \
+        libxml2-dev \
+        ncbi-blast+ \
         r-base \
+        r-bioc-biostrings \
+        r-bioc-rsamtools \
+        r-cran-biocmanager \
+        r-cran-devtools \
+        r-cran-stringr \
+        r-cran-optparse \
         zlib1g-dev
 
-Install dependencies (Centos):
-
-    $ yum install -y \
-          epel-release && \
-    $ yum install -y \
-          autoconf \
-          bzip2 \
-          bzip2-devel \
-          libcurl-devel \
-          libcrypto-devel \
-          openssl-devel \
-          R \
-          xz-devel \
-          zlib-devel
-
 Install R packages dependencies:
 
-    $ Rscript -e "install.packages('optparse')"
-    $ Rscript -e "install.packages('stringr')"
-    $ Rscript -e "source('https://bioconductor.org/biocLite.R'); biocLite('Biostrings')"
+    Rscript -e "library(devtools); install_github('mhahsler/rBLAST')"
 
 To build the cluster_identifier (estimated install time <5 minutes):
 
     $ cd cluster_identifier/src
     $ make
 
 That should be it. It will create an executable named `build/cluster_identifier`.
-
-Building requires `HTSlib` and a few other dev packages (installation instructions for Debian/Ubuntu/Centos above).
-Please edit `cluster_identifier/src/Makefile` if `HTSlib` is not installed in the default location.
-
-    /usr/local/include/htslib/*.h
-    /usr/local/lib/libhts.a
 
 Running
 -------
@@ -69,15 +57,18 @@ sequences. Second, `SCRAMble-MEIs.R` analyzes the cluster file for likely MEIs.
 To run SCRAMble cluster_identifier:
 
     $ /path/to/scramble/cluster_identifier/src/build/cluster_identifier \
-        /path/to/install_dir/scramble/validation/test.bam > /path/to/output/clusters.txt
+        /path/to/install_dir/scramble/validation/test.bam > /path/to/output/test.clusters.txt
 
-To run SCRAMble-MEIs (with default settings):
+To run SCRAMble-MEIs and SCRAMble-dels(with default settings):
 
-    $ Rscript --vanilla /path/to/scramble/cluster_analysis/bin/SCRAMble-MEIs.R \
-        --out-name /path/to/output/out.txt 	\
-        --cluster-file /path/to/output/clusters.txt \
+    $ Rscript --vanilla /path/to/scramble/cluster_analysis/bin/SCRAMble.R \
+        --out-name /path/to/output/test 	\
+        --cluster-file /path/to/output/test.clusters.txt \
         --install-dir /path/to/scramble/cluster_analysis/bin \
-        --mei-refs /path/to/scramble/cluster_analysis/resources/MEI_consensus_seqs.fa  
+        --mei-refs /path/to/scramble/cluster_analysis/resources/MEI_consensus_seqs.fa \
+        --ref /path/to/scramble/validation/test.fa \
+        --eval-meis \
+        --eval-dels 
 
 Running with Docker
 -------------------
@@ -88,12 +79,16 @@ SCRAMble is also distributed with a `Dockerfile`. Running SCRAMble using `docker
     $ docker build -t scramble:latest .
     $ docker run -it --rm scramble:latest bash
     # cluster_identifier \
-        /app/validation/test.bam > clusters.txt
-    # Rscript --vanilla /app/cluster_analysis/bin/SCRAMble-MEIs.R \
-        --out-name ${PWD}/out.txt \
-        --cluster-file ${PWD}/clusters.txt \
+        /app/validation/test.bam > /app/validation/test.clusters.txt
+    # Rscript --vanilla /app/cluster_analysis/bin/SCRAMble.R \
+        --out-name ${PWD}/test \
+        --cluster-file /app/validation/test.clusters.txt \
         --install-dir /app/cluster_analysis/bin \
-        --mei-refs /app/cluster_analysis/resources/MEI_consensus_seqs.fa
+        --mei-refs /app/cluster_analysis/resources/MEI_consensus_seqs.fa \
+        --ref /app/validation/test.fa \
+        --eval-dels \
+        --eval-meis
+
 
 Output
 ------
@@ -108,7 +103,7 @@ The columns are as follows:
 | 4.   | Clipped read consensus                   |
 | 5.   | Anchored read consensus                  |
 
-The output of SCRAMble-MEIs.R is a tab delimited text file with MEI calls. If no MEIs are present an output file will still be produced with only the header.
+Calling `SCRAMble.R` with `--eval-meis` produces a tab delimted file. If a reference `.fa` file is provided, then a VCF is produced as well. The `<out-name>_MEIs.txt` output is a tab delimited text file with MEI calls. If no MEIs are present an output file will still be produced with only the header.
 The columns are as follows:
 
 |      |                               |                                                                                              |
@@ -130,13 +125,34 @@ The columns are as follows:
 | 15.  | TSD                           | Target site duplication sequence if polyA clipped read cluster found                         |
 | 16.  | TSD_length                    | Length of target site duplication if polyA clipped read cluster found                        |
 
-R Dependencies
---------------
-SCRAMBLE-MEIs.R was developed on R version 3.1.1 (2014-07-10) and uses the following libraries:
 
-    [1] Biostrings_2.34.1   XVector_0.6.0       IRanges_2.0.1
-    [4] S4Vectors_0.4.0     BiocGenerics_0.12.1 stringr_0.6.2
-    [7] optparse_1.4.4
+Calling `SCRAMble.R` with `--eval-dels` produced a VCF and a tab delimted file. The `<out-name>_PredictedDeletions.txt` output is a tab delimited text file with deletion calls. If no deletions are present an output file will still be produced with only the header.
+The columns are as follows:
+
+|      |                               |                                                                                              |
+| ---: | ----------------------------- | -------------------------------------------------------------------------------------------- |
+| 1.   | CONTIG                      | Chromosome                                           |
+| 2.   | DEL.START                    | Deletion start coordinate (0-based)       |
+| 3.   | DEL.END                      | Deletion end coordinate (0-based)         |
+| 4.   | REF.ANCHOR.BASE              | Reference based at deletion start               |
+| 5.   | DEL.LENGTH                   | Deletion length |
+| 6.   | RIGHT.CLUSTER                | Name of right cluster  |
+| 7.   | RIGHT.CLUSTER.COUNTS    | Number of supporting reads in right cluster |
+| 8.   | LEFT.CLUSTER              | Name of left cluster                             |
+| 9.   | LEFT.CLUSTER.COUNTS                  | Number of supporting reads in left cluster             |
+| 10.  | LEN.RIGHT.ALIGNMENT                  | Length of right-clipped consensus sequence involved in alignment       |
+| 11.  | SCORE.RIGHT.ALIGNMENT                   | BLAST alignment bitscore for right-clipped consensus       |
+| 12.  | PCT.COV.RIGHT.ALIGNMENT                | Percent length of right-clipped consensus involved in alignment                                             |
+| 13.  | PCT.IDENTITY.RIGHT.ALIGNMENT                     | Percent identity of right-clipped consensus in alignment                   |
+| 14.  | LEN.LEFT.ALIGNMENT         | Length of left-clipped consensus sequence involved in alignment       |
+| 15.  | SCORE.LEFT.ALIGNMENT                           | BLAST alignment bitscore for left-clipped consensus       |                         |
+| 16.  | PCT.COV.LEFT.ALIGNMENT                    | Percent length of left-clipped consensus involved in alignment                           
+| 17.  | PCT.IDENTITY.LEFT.ALIGNMENT                    | Percent identity of right-clipped consensus in alignment                   |   
+| 18.  | INS.SIZE                    | Length of insert within deleted sequence (for two-end deletions only)
+| 19.  | INS.SEQ                    | Inserted sequence (for two-end deletions only)
+| 20.  | RIGHT.CLIPPED.SEQ                    | Clipped consensus sequence for right-clipped cluster
+| 21.  | LEFT.CLIPPED.SEQ                    | Clipped consensus sequence for left-clipped cluster
+
 
 
 Disclaimers