hg38 support

.gitignore

@@ -3,4 +3,5 @@
 *.o
 Release_sophia/sophia
 Release_sophiaAnnotate/sophiaAnnotate
+Release_sophiaMref/sophiaMref
 include/strtk.hpp

README.md

@@ -1,5 +1,30 @@
 # SOPHIA Tool for Structural Variation Calling
 
+SOPHIA is a Structural Variant(SV) detection algorithm based on the supplementary alignment(SA) concept of the aligner BWA-mem, combined with filters based on expert-knowledge to increase specificity. 
+
+Currently, SOPHIA only is optimized for the hg38 assembly of the human genome. 
+It uses a large panel of normals for filtering artifacts (most often due to mapping difficulties) and common SVs in the germline.
+The parameters for filtering results are hand-tuned against the clinical gold standard FISH of V(D)J rearrangements.
+Results from the hand-tuned parameter set were tested against hallmark findings from disease datasets where hallmark SVs were known (CDKN2A in various TCGA datasets, EGFR in TCGA-GBM, GFI1B, MYCN and PRDM6 in ICGC-PEDBRAIN-MB etc.) 
+
+For a detailed description of the algorithm, please refer to Umut Topraks's dissertation at https://doi.org/10.11588/heidok.00027429, in particular chapter 2. Section 2.2.1 describes the method in more details.
+
+SOPHIA is a very fast and resource-light algorithm. It uses 2GB RAM, 2 CPU cores and runs in ~3.5 hours for 50x coverage WGS, and can detect variants with a single pass of the input BAM files. No local assembly is done.
+
+> This is a fork of the original [SOPHIA](https://bitbucket.org/utoprak/sophia/src/master/) bitbucket repository.
+
+Sophia is included in the [SophiaWorkflow](https://github.com/DKFZ-ODCF/SophiaWorkflow) that uses the [Roddy Workflow Management Systems](https://github.com/TheRoddyWMS/Roddy).
+
+
+### Citing
+
+You can cite Sophia as follows:
+
+    Integrative Analysis of Omics Datasets.
+    Doctoral dissertation, German Cancer Research Center (DKFZ), Heidelberg.
+    Umut Toprak (2019).
+    DOI 10.11588/heidok.000274296
+
 ## Runtime Dependencies
 
 The only dependency is Boost 1.70.0 (currently). E.g. you can do
@@ -41,7 +66,7 @@ Note that the build-scripts are for when you manage your dependencies with Conda
 
 ### Static Build
 
-If you want to compile statically you need to install glibc and boost static libraries (not possible with Conda, in the moment) and do
+If you want to compile statically you need to install glibc and boost static libraries (currently, not possible with Conda) and do
 
 ```bash
 source activate sophia
@@ -52,3 +77,17 @@ STATIC=true build-sophia.sh
 cd ../Release_sophiaAnnotate
 STATIC=true build-sophiaAnnotate.sh
 ```
+
+## Changes
+
+* 35.1.0 (upcoming)
+  * Minor: Nominally added support for hg38 (hg37 support remains)
+  * Minor: Added `--assemblyname` option, defaulting to "hg37" when omitted (old behaviour)
+    > WARNING: hg38 support was not excessively tested. In particular, yet hardcoded parameters may have to be adjusted.
+  * Minor: Build script for `sophiaMref`
+  * Patch: Code readability improvements, `.editorconfig` file, and `clang-format` configuration
+  * Patch: Improved compilation instructions
+  * Patch: Use `namespace::std` to get rid of `std::` noise in the code
+
+* 9e3b6ed
+  * Last version in [bitbucket](https://bitbucket.org/compbio_charite/sophia/src/master/)

Release_sophia/build-sophia.sh

@@ -14,7 +14,7 @@ install_strtk
 CPP=x86_64-conda_cos6-linux-gnu-g++
 INCLUDES="-I../include -I$CONDA_PREFIX/include"
 
-CPP_OPTS="-L$CONDA_PREFIX/lib -std=c++1z $INCLUDES -O3 -Wall -Wextra -static -static-libgcc -static-libstdc++ -flto -c -fmessage-length=0 -Wno-attributes"
+CPP_OPTS="-L$CONDA_PREFIX/lib -std=c++17 $INCLUDES -O3 -Wall -Wextra -static -static-libgcc -static-libstdc++ -flto -c -fmessage-length=0 -Wno-attributes"
 
 if [[ "${STATIC:-false}" == "true" ]]; then
     CPP_OPTS="-static -static-libgcc -static-libstdc++ $CPP_OPTS"
@@ -23,11 +23,27 @@ fi
 $CPP $CPP_OPTS -o "Alignment.o" "../src/Alignment.cpp"
 $CPP $CPP_OPTS -o "Breakpoint.o" "../src/Breakpoint.cpp"
 $CPP $CPP_OPTS -o "ChosenBp.o" "../src/ChosenBp.cpp"
+$CPP $CPP_OPTS -o "GlobalAppConfig.o" "../src/GlobalAppConfig.cpp"
 $CPP $CPP_OPTS -o "ChrConverter.o" "../src/ChrConverter.cpp"
+$CPP $CPP_OPTS -o "Hg37ChrConverter.o" "../src/Hg37ChrConverter.cpp"
+$CPP $CPP_OPTS -o "Hg38ChrConverter.o" "../src/Hg38ChrConverter.cpp"
 $CPP $CPP_OPTS -o "SamSegmentMapper.o" "../src/SamSegmentMapper.cpp"
 $CPP $CPP_OPTS -o "Sdust.o" "../src/Sdust.cpp"
 $CPP $CPP_OPTS -o "SuppAlignment.o" "../src/SuppAlignment.cpp"
 $CPP $CPP_OPTS -o "HelperFunctions.o" "../src/HelperFunctions.cpp"
-$CPP $CPP_OPTS -o "sophia.o" "../sophia.cpp"
-
-$CPP -L$CONDA_PREFIX/lib -flto -o "sophia"  Alignment.o Breakpoint.o ChosenBp.o ChrConverter.o SamSegmentMapper.o Sdust.o SuppAlignment.o HelperFunctions.o sophia.o -lboost_program_options
+$CPP $CPP_OPTS -o "sophia.o" "../src/sophia.cpp"
+
+$CPP -L$CONDA_PREFIX/lib -flto -o "sophia"  \
+    Alignment.o \
+    Breakpoint.o \
+    ChosenBp.o \
+    ChrConverter.o \
+    Hg37ChrConverter.o \
+    Hg38ChrConverter.o \
+    SamSegmentMapper.o \
+    Sdust.o \
+    SuppAlignment.o \
+    HelperFunctions.o \
+    GlobalAppConfig.o \
+    sophia.o \
+    -lboost_program_options

Release_sophiaAnnotate/build-sophiaAnnotate.sh

@@ -13,7 +13,7 @@ install_strtk
 
 CPP=x86_64-conda_cos6-linux-gnu-g++
 INCLUDES="-I../include -I$CONDA_PREFIX/include"
-CPP_OPTS="-L$CONDA_PREFIX/lib -std=c++1z $INCLUDES -O3 -Wall -Wextra -static -static-libgcc -static-libstdc++ -flto -c -fmessage-length=0 -Wno-attributes"
+CPP_OPTS="-L$CONDA_PREFIX/lib -std=c++17 $INCLUDES -O3 -Wall -Wextra -static -static-libgcc -static-libstdc++ -flto -c -fmessage-length=0 -Wno-attributes"
 
 if [[ "${STATIC:-false}" == "true" ]]; then
     CPP_OPTS="-static -static-libgcc -static-libstdc++ $CPP_OPTS"
@@ -22,7 +22,10 @@ fi
 $CPP $CPP_OPTS -o "AnnotationProcessor.o" "../src/AnnotationProcessor.cpp"
 $CPP $CPP_OPTS -o "Breakpoint.o" "../src/Breakpoint.cpp"
 $CPP $CPP_OPTS -o "BreakpointReduced.o" "../src/BreakpointReduced.cpp"
+$CPP $CPP_OPTS -o "GlobalAppConfig.o" "../src/GlobalAppConfig.cpp"
 $CPP $CPP_OPTS -o "ChrConverter.o" "../src/ChrConverter.cpp"
+$CPP $CPP_OPTS -o "Hg37ChrConverter.o" "../src/Hg37ChrConverter.cpp"
+$CPP $CPP_OPTS -o "Hg38ChrConverter.o" "../src/Hg38ChrConverter.cpp"
 $CPP $CPP_OPTS -o "DeFuzzier.o" "../src/DeFuzzier.cpp"
 $CPP $CPP_OPTS -o "GermlineMatch.o" "../src/GermlineMatch.cpp"
 $CPP $CPP_OPTS -o "MrefEntry.o" "../src/MrefEntry.cpp"
@@ -32,6 +35,24 @@ $CPP $CPP_OPTS -o "SuppAlignment.o" "../src/SuppAlignment.cpp"
 $CPP $CPP_OPTS -o "SuppAlignmentAnno.o" "../src/SuppAlignmentAnno.cpp"
 $CPP $CPP_OPTS -o "SvEvent.o" "../src/SvEvent.cpp"
 $CPP $CPP_OPTS -o "HelperFunctions.o" "../src/HelperFunctions.cpp"
-$CPP $CPP_OPTS -o "sophiaAnnotate.o" "../sophiaAnnotate.cpp"
-
-$CPP -L$CONDA_PREFIX/lib -flto -o "sophiaAnnotate"  AnnotationProcessor.o Breakpoint.o BreakpointReduced.o ChrConverter.o DeFuzzier.o GermlineMatch.o MrefEntry.o MrefEntryAnno.o MrefMatch.o SuppAlignment.o SuppAlignmentAnno.o SvEvent.o HelperFunctions.o sophiaAnnotate.o -lz -lboost_system -lboost_iostreams
+$CPP $CPP_OPTS -o "sophiaAnnotate.o" "../src/sophiaAnnotate.cpp"
+
+$CPP -L$CONDA_PREFIX/lib -flto -o "sophiaAnnotate" \
+    AnnotationProcessor.o \
+    Breakpoint.o \
+    BreakpointReduced.o \
+    ChrConverter.o \
+    Hg37ChrConverter.o \
+    Hg38ChrConverter.o \
+    DeFuzzier.o \
+    GermlineMatch.o \
+    MrefEntry.o \
+    MrefEntryAnno.o \
+    MrefMatch.o \
+    SuppAlignment.o \
+    SuppAlignmentAnno.o \
+    SvEvent.o \
+    HelperFunctions.o \
+    GlobalAppConfig.o \
+    sophiaAnnotate.o \
+    -lz -lboost_system -lboost_iostreams

Release_sophiaMref/build-sophiaMref.sh

@@ -0,0 +1,56 @@
+#!/bin/bash
+
+set -uex
+trap 'echo "Compilation failed with an error" >> /dev/stderr' ERR
+
+CONDA_PREFIX="${CONDA_PREFIX:?No CONDA_PREFIX -- no active Conda environment}"
+
+install_strtk() {
+    wget -c https://github.com/ArashPartow/strtk/raw/master/strtk.hpp -O ../include/strtk.hpp
+}
+
+install_strtk
+
+CPP=x86_64-conda_cos6-linux-gnu-g++
+INCLUDES="-I../include -I$CONDA_PREFIX/include"
+CPP_OPTS="-L$CONDA_PREFIX/lib -std=c++17 $INCLUDES -O3 -Wall -Wextra -static -static-libgcc -static-libstdc++ -flto -c -fmessage-length=0 -Wno-attributes"
+
+if [[ "${STATIC:-false}" == "true" ]]; then
+    CPP_OPTS="-static -static-libgcc -static-libstdc++ $CPP_OPTS"
+fi
+
+$CPP $CPP_OPTS -o "GlobalAppConfig.o" "../src/GlobalAppConfig.cpp"
+$CPP $CPP_OPTS -o "ChrConverter.o" "../src/ChrConverter.cpp"
+$CPP $CPP_OPTS -o "Hg37ChrConverter.o" "../src/Hg37ChrConverter.cpp"
+$CPP $CPP_OPTS -o "Hg38ChrConverter.o" "../src/Hg38ChrConverter.cpp"
+$CPP $CPP_OPTS -o "HelperFunctions.o" "../src/HelperFunctions.cpp"
+$CPP $CPP_OPTS -o "sophiaMref.o" "../src/sophiaMref.cpp"
+$CPP $CPP_OPTS -o "SuppAlignment.o" "../src/SuppAlignment.cpp"
+$CPP $CPP_OPTS -o "SuppAlignmentAnno.o" "../src/SuppAlignmentAnno.cpp"
+$CPP $CPP_OPTS -o "MrefEntry.o" "../src/MrefEntry.cpp"
+$CPP $CPP_OPTS -o "MrefEntryAnno.o" "../src/MrefEntryAnno.cpp"
+$CPP $CPP_OPTS -o "MrefMatch.o" "../src/MrefMatch.cpp"
+$CPP $CPP_OPTS -o "MasterRefProcessor.o" "../src/MasterRefProcessor.cpp"
+$CPP $CPP_OPTS -o "Breakpoint.o" "../src/Breakpoint.cpp"
+$CPP $CPP_OPTS -o "BreakpointReduced.o" "../src/BreakpointReduced.cpp"
+$CPP $CPP_OPTS -o "GermlineMatch.o" "../src/GermlineMatch.cpp"
+$CPP $CPP_OPTS -o "DeFuzzier.o" "../src/DeFuzzier.cpp"
+
+$CPP -L$CONDA_PREFIX/lib -flto -o "sophiaMref" \
+    GlobalAppConfig.o \
+    ChrConverter.o \
+    Hg37ChrConverter.o \
+    Hg38ChrConverter.o \
+    HelperFunctions.o \
+    SuppAlignment.o \
+    SuppAlignmentAnno.o \
+    MrefEntry.o \
+    MrefEntryAnno.o \
+    MrefMatch.o \
+    MasterRefProcessor.o \
+    Breakpoint.o \
+    BreakpointReduced.o \
+    GermlineMatch.o \
+    DeFuzzier.o \
+    sophiaMref.o \
+    -lz -lboost_system -lboost_iostreams -lboost_program_options