First Working commit of FastRemap implementation to the SAFARI reposi…

…tory

.gitmodules

@@ -0,0 +1,8 @@
+[submodule "zlib"]
+	path = zlib
+	url = https://github.com/madler/zlib
+	ignore = dirty 
+[submodule "seqan2"]
+	path = seqan2
+	url = https://github.com/seqan/seqan
+	ignore = dirty 

Makefile

@@ -0,0 +1,26 @@
+CC = g++
+SRCDIR = src
+SRCEXT = cpp 
+OBJEXT = o 
+BUILDDIR = build
+LDFLAGS = -L./zlib -lz -lpthread
+CFLAGS = -c -O3 -Wall -std=c++2a -pthread -I ./seqan2/include -I./seqan2/include -I./zlib -DSEQAN_HAS_ZLIB=1 
+SOURCES = $(shell find $(SRCDIR) -type f -name *.$(SRCEXT))
+
+
+OBJECTS = $(patsubst $(SRCDIR)/%,$(BUILDDIR)/%,$(SOURCES:.$(SRCEXT)=.o))
+OBJECTS := $(patsubst $(SRCDIR)/%,$(BUILDDIR)/%,$(SOURCES:.$(SRCEXT)=.$(OBJEXT)))
+OBJECTS = $(SOURCES:.cpp=.o) 
+
+EXECUTABLE = bin/FastRemap 
+
+$(EXECUTABLE): $(OBJECTS)
+	$(CC) -std=c++11 $(OBJECTS) -o $@ $(LDFLAGS) 
+	cp bin/FastRemap ./
+
+.cpp.o:
+	$(CC) $(CFLAGS) $< -o $@
+
+clean:
+	rm -f $(BUILDDIR)/*.o $(SRCDIR)/*.o bin/FastRemap 
+

README.md

@@ -1,2 +1,43 @@
-# FastRemap
-A tool for quickly remapping reads between genome assemblies
+# FastRemap: A Tool for Quickly Remapping Reads between Genome Assemblies 
+
+## FastRemap:
+    - Currently only supports BAM files as input 
+    - if not using gcc 10 or higher, can use the following library: https://github.com/tcbrindle/span
+
+## To clone: 
+```
+git clone --recurse-submodules git@github.com:CMU-SAFARI/FastRemap.git FastRemap 
+```
+
+## To compile:
+### zlib: 
+```
+FastRemap/zlib$ ./configure
+FastRemap/zlib$ make
+```
+
+### FastRemap: 
+may need to use '-lstdc++fs' in LDFLAGS depending on compiler / system. 
+```
+FastRemap$ make 
+```
+
+## To run: 
+```
+./FastRemap bam [chain file] [input bam file] [unmapped file] [out file]
+```
+test using the small sample files in test_data folder 
+- input / output files should be paths relative to the current directory. 
+- e.g., 
+	./FastRemap bam test_data/ce6ToCe10.over.chain test_data/little.bam test.unmapped test.out
+
+optional arguments
+- --append-tags (-a) to append tags in output bam file 
+- --mean (-m) to set insert size 
+- --stdev (-s) to set insert_size_stdev
+- --times (-t) to set insert_size_fold 
+
+## To validate and compare two bam outputs: 
+```
+python ./validation/compare_outputs.py [input bam file 1] [input bam file 2] 
+```

bin/.gitignore

@@ -0,0 +1 @@
+!.gitignore

build/.gitignore

@@ -0,0 +1 @@
+!.gitignore

src/CMakeLists.txt

@@ -0,0 +1,33 @@
+if(NOT CMAKE_BUILD_TYPE)
+  set(CMAKE_BUILD_TYPE Release)
+endif()
+
+set(CMAKE_CXX_FLAGS_RELEASE "-O3")
+
+cmake_minimum_required (VERSION 3.4)
+project (seqan3_tutorial CXX)
+set(CMAKE_CXX_STANDARD 17)  
+
+#set(CMAKE_INCLUDE_PATH ${CMAKE_INCLUDE_PATH} "/usr/local/opt/boost\@1.76") 
+#SET(CMAKE_LIBRARY_PATH ${CMAKE_LIBRARY_PATH} "/usr/local/opt/boost\@1.76/lib") 
+
+#set(BOOST_ROOT "/usr/local/opt/boost\@1.76") 
+#set(_boost_INCLUDE_SEARCH_DIRS ${_boost_INCLUDE_SEARCH_DIRS} "/usr/local/opt/boost\@1.76") 
+#set(Boost_DEBUG 1) 
+#set(Boost_USE_STATIC_LIBS OFF) 
+#set(Boost_USE_MULTITHREADED ON)  
+#set(Boost_USE_STATIC_RUNTIME OFF) 
+#find_package(Boost COMPONENTS) 
+
+
+# add seqan3 to search path
+list(APPEND CMAKE_PREFIX_PATH "${CMAKE_CURRENT_SOURCE_DIR}/../seqan2")
+
+# require seqan3 with a version between >=3.0.0 and <4.0.0
+find_package (seqan2 2.0 REQUIRED)
+
+# build app with seqan3
+#include_directories(${Boost_INCLUDE_DIR}) 
+add_executable (FastRemap main.cpp utils.cpp mapbam.cpp) 
+target_link_libraries (FastRemap seqan2::seqan2)  # ${Boost_LIBRARIES}) 
+