v3.0.2 release prep

.gitignore

@@ -16,6 +16,7 @@ examples/
 hdf5-1.8.14/
 tensorflow/
 hdf5-1.8.14.tar.gz
+htslib/
 
 #generated
 .depend
@@ -26,8 +27,9 @@ hdf5-1.8.14.tar.gz
 .pydevproject
 .settings/*
 
-#commit log file
+#commit log file and path
 src/gitcommit.h
+src/softwarepath.h
 
 #plots
 *.png

Makefile

@@ -1,30 +1,43 @@
 CC = gcc
 CXX = g++
 DEBUG = -g
-LIBFLAGS =
+LIBFLAGS = -lrt 
+LDFLAGS ?= -ldl -llzma -lbz2 -lm -lz
 CXXFLAGS = -Wall -O2 -fopenmp -std=c++14
 CFLAGS = -Wall -std=c99 -O2
 
+SPACE:= ;
+SPACE+=;
+null :=
+space := ${null} ${null}
+${space} := ${space}
+
+CURRENT_PATH := $(subst $(lastword $(notdir $(MAKEFILE_LIST))),,$(subst $(SPACE),\$(SPACE),$(shell realpath '$(strip $(MAKEFILE_LIST))')))
+PATH_SPACEFIX := $(subst ${space},\${space},${CURRENT_PATH})
+
+ifeq ($(zstd),1)
+	LDFLAGS += -lzstd
+endif
+
 #hdf5
 H5_LIB = ./hdf5-1.8.14/hdf5/lib/libhdf5.a
 H5_INCLUDE = -I./hdf5-1.8.14/hdf5/include
-LIBFLAGS += -Wl,-rpath,$(dir $(abspath $(lastword $(MAKEFILE_LIST))))hdf5-1.8.14/hdf5/lib -L hdf5-1.8.14/hdf5/lib -lhdf5
 
 #hts
 HTS_LIB = ./htslib/libhts.a
 HTS_INCLUDE = -I./htslib
-LIBFLAGS += -Wl,-rpath,$(dir $(abspath $(lastword $(MAKEFILE_LIST))))htslib -L htslib/ -lhts
 
 #tensorflow
-TENS_LIB = ./tensorflow/include/tensorflow/c/c_api.h
+TENS_DEPEND = tensorflow/include/tensorflow/c/c_api.h
+TENS_LIB = -Wl,-rpath,${PATH_SPACEFIX}tensorflow/lib -L tensorflow/lib
 TENS_INCLUDE = -I./tensorflow/include
-LIBFLAGS += -Wl,-rpath,$(dir $(abspath $(lastword $(MAKEFILE_LIST))))tensorflow/lib -L tensorflow/lib -ltensorflow
+LIBFLAGS = -ltensorflow
 
 #fast5
 FAST5_INCLUDE = -I./fast5/include
 
 #add include flags for each library
-CXXFLAGS += $(H5_INCLUDE) $(HTS_INCLUDE) $(FAST5_INCLUDE) $(TENS_INCLUDE)
+CPPFLAGS += $(H5_INCLUDE) $(HTS_INCLUDE) $(FAST5_INCLUDE) $(TENS_INCLUDE)
 
 MAIN_EXECUTABLE = bin/DNAscent
 
@@ -47,12 +60,12 @@ tensorflow/include/tensorflow/c/c_api.h:
 	if [ ! -e tensorflow/include/tensorflow/c/c_api.h ]; then \
 		mkdir tensorflow; \
 		cd tensorflow; \
-		wget https://storage.googleapis.com/tensorflow/libtensorflow/libtensorflow-gpu-linux-x86_64-1.15.0.tar.gz; \
-		tar -xzf libtensorflow-gpu-linux-x86_64-1.15.0.tar.gz || exit 255; \
+		wget https://storage.googleapis.com/tensorflow/libtensorflow/libtensorflow-gpu-linux-x86_64-2.4.1.tar.gz; \
+		tar -xzf libtensorflow-gpu-linux-x86_64-2.4.1.tar.gz || exit 255; \
 		cd ..; \
 	fi 
 
-SUBDIRS = src src/scrappie src/pfasta
+SUBDIRS = src src/scrappie src/pfasta src/sgsmooth
 CPP_SRC := $(foreach dir, $(SUBDIRS), $(wildcard $(dir)/*.cpp))
 C_SRC := $(foreach dir, $(SUBDIRS), $(wildcard $(dir)/*.c))
 EXE_SRC = src/DNAscent.cpp
@@ -61,27 +74,31 @@ EXE_SRC = src/DNAscent.cpp
 src/gitcommit.h: .git/HEAD .git/index
 	echo "const char *gitcommit = \"$(shell git rev-parse HEAD)\";" > $@
 
+#log the software path
+src/softwarepath.h: 
+	echo "const char *executablePath = \"${PATH_SPACEFIX}\";" > $@
+
 #generate object names
 CPP_OBJ = $(CPP_SRC:.cpp=.o)
 C_OBJ = $(C_SRC:.c=.o)
 
 depend: .depend
 
-.depend: $(CPP_SRC) $(C_SRC) $(EXE_SRC) $(H5_LIB) $(TENS_LIB) src/gitcommit.h
+.depend: $(CPP_SRC) $(C_SRC) $(EXE_SRC) $(H5_LIB) $(TENS_DEPEND) src/gitcommit.h src/softwarepath.h
 	rm -f ./.depend
-	$(CXX) $(CXXFLAGS) -MM $(CPP_SRC) $(C_SRC) > ./.depend;
+	$(CXX) $(CXXFLAGS) $(CPPFLAGS) -MM $(CPP_SRC) $(C_SRC) > ./.depend;
 
 #compile each object
-.cpp.o: src/gitcommit.h
-	$(CXX) -o $@ -c $(CXXFLAGS) -fPIC $<
+.cpp.o: src/gitcommit.h src/softwarepath.h
+	$(CXX) -o $@ -c $(CXXFLAGS) $(CPPFLAGS) -fPIC $<
 
 .c.o:
-	$(CC) -o $@ -c $(CFLAGS) $(H5_INCLUDE) -fPIC $<
+	$(CC) -o $@ -c $(CFLAGS) $(CPPFLAGS) $(H5_INCLUDE) -fPIC $<
 
 
 #compile the main executable
-$(MAIN_EXECUTABLE): src/DNAscent.o $(CPP_OBJ) $(C_OBJ) $(HTS_LIB) $(H5_LIB) $(TENS_LIB) src/gitcommit.h
-	$(CXX) -o $@ $(CXXFLAGS) -fPIC $(CPP_OBJ) $(C_OBJ) $(LIBFLAGS)
+$(MAIN_EXECUTABLE): src/DNAscent.o $(CPP_OBJ) $(C_OBJ) $(HTS_LIB) $(H5_LIB) $(TENS_DEPEND) src/gitcommit.h src/softwarepath.h
+	$(CXX) -o $@ $(CXXFLAGS) $(CPPFLAGS) -fPIC $(CPP_OBJ) $(C_OBJ) $(HTS_LIB) $(H5_LIB) $(TENS_LIB) $(LIBFLAGS) $(LDFLAGS)
 
 clean:
-	rm -f $(MAIN_EXECUTABLE) $(CPP_OBJ) $(C_OBJ) src/DNAscent.o gitcommit.h
+	rm -f $(MAIN_EXECUTABLE) $(CPP_OBJ) $(C_OBJ) src/DNAscent.o src/gitcommit.h src/softwarepath.h

README.md

@@ -11,7 +11,7 @@ git clone --recursive https://github.com/MBoemo/DNAscent.git
 The DNAscent directory will appear in your current directory.  Switch to the latest tagged version and compile the software by running:
 ```shell
 cd DNAscent
-git checkout 2.0.2
+git checkout 3.0.2
 make
 ```
 This will put the DNAscent executable into the DNAscent/bin directory.  A typical compile time for DNAscent and its dependencies is 5 minutes.
@@ -21,6 +21,7 @@ Please see the [documentation](https://dnascent.readthedocs.io) for detailed usa
 
 ## Citation
 Please cite the following if you use DNAscent for your research:
+- Totanes FIG,  Gockel J,  Chapman SE, Bartfai R, Boemo MA, Merrick CJ. Replication origin mapping in the malaria parasite Plasmodium falciparum. bioRxiv. [[bioRxiv](https://doi.org/10.1101/2022.07.27.501677)]
 - Boemo, MA. DNAscent v2: Detecting replication forks in nanopore sequencing data with deep learning. *BMC Genomics* 2021;22:430. [[Journal Link](https://doi.org/10.1186/s12864-021-07736-6)]
 - Muller CA, Boemo MA, Spingardi P, Kessler BM, Kriaucionis S, Simpson JT, Nieduszynski CA. Capturing the dynamics of genome replication on individual ultra-long nanopore sequence reads. *Nature Methods* 2019;16:429-436. [[Journal Link](https://www.nature.com/articles/s41592-019-0394-y)]
 

docs/source/base.rst

@@ -0,0 +1,46 @@
+.. DNAscent documentation master file, created by
+   sphinx-quickstart on Fri Feb  7 18:58:49 2020.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+DNAscent
+====================================
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Contents:
+
+   installation
+   index
+   detect
+   forkSense
+   visualisation
+   workflows
+   cookbook
+   releaseNotes
+
+Overview
+--------
+
+DNAscent is software designed to detect the modified bases BrdU and EdU in Oxford Nanopore reads.  In an experimental setup where BrdU and EdU are incorporated into nascent DNA by replication forks, this software can be used to answer questions that were traditionally answered by DNA fibre analysis.  
+
+At present, the only Oxford Nanopore flow cells supported by DNAscent are R9.4.1. The Flongle, MinION, GridION, and PromethION platforms are all supported.
+
+DNAscent is under active development by the `Boemo Group <https://www.boemogroup.org/>`_ based in the `Department of Pathology, University of Cambridge <https://www.path.cam.ac.uk/>`_.  We aim to push regular updates and improvements, and incorporating new functionality is an active area of our computational research.
+
+
+Publications
+------------
+
+If you use DNAscent for your research, please cite the following publications:
+
+Totanes FIG,  Gockel J,  Chapman SE, Bartfai R, Boemo MA, Merrick CJ. Replication origin mapping in the malaria parasite Plasmodium falciparum. [`bioRxiv <https://doi.org/10.1101/2022.07.27.501677>`_]
+
+Boemo, MA DNAscent v2: Detecting replication forks in nanopore sequencing data with deep learning. BMC Genomics 2021;22:430. [`Journal DOI <https://doi.org/10.1186/s12864-021-07736-6>`_]
+
+Muller CA, Boemo MA, Spingardi P, Kessler, BM, Kriaucionis S, Simpson JT, Nieduszynski CA. Capturing the dynamics of genome replication on individual ultra-long nanopore sequence reads. Nature Methods 2019;16:429-436. [`Journal DOI <https://doi.org/10.1038/s41592-019-0394-y>`_]
+
+Bugs, Questions, and Comments
+-----------------------------
+
+Should any bugs arise or if you have any questions about usage, please raise a `GitHub issue <https://github.com/MBoemo/DNAscent/issues>`_. If you have comments or suggestions to improve the software or the documentation, please Email Michael Boemo at [email protected].

docs/source/conf.py

@@ -18,11 +18,11 @@
 # -- Project information -----------------------------------------------------
 
 project = 'DNAscent'
-copyright = '2020, Michael A. Boemo'
+copyright = '2022, Michael A. Boemo'
 author = 'Michael A. Boemo'
 
 # The full version, including alpha/beta/rc tags
-release = '2.0.2'
+release = '3.0.2'
 
 
 # -- General configuration ---------------------------------------------------
@@ -41,7 +41,7 @@
 # This pattern also affects html_static_path and html_extra_path.
 exclude_patterns = []
 
-master_doc = 'index'
+master_doc = 'base'
 
 # -- Options for HTML output -------------------------------------------------
 
@@ -53,4 +53,4 @@
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = []
+html_static_path = ['_static']

docs/source/cookbook.rst

@@ -29,73 +29,51 @@ The following barebones script parses the output of ``DNAscent detect``.  We ite
 		strand = splitLine[4]
 	else:
 		posOnRef = int(splitLine[0])
-		probBrdU = float(splitLine[1])
-		sixMerOnRef = splitLine[2]
+		probEdU = float(splitLine[1])
+		probBrdU = float(splitLine[2])
+		sixMerOnRef = splitLine[3]
 
 		#add these values to a container or do some processing here
 
    f.close()
 
-The following barebones script parses the output of ``DNAscent forkSense``.  Note the similarity to the above script: All DNAscent output files were designed to have a very similar format to aid user processing.  
 
-.. code-block:: python
-
-   f = open('path/to/output.forkSense','r')
-
-   for line in f:
-
-	#ignore the header lines
-   	if line[0] == '#':
-		continue
-	
-	#split the line into a list by whitespace
-	splitLine = line.rstrip().split()
-
-	if line[0] == '>':
-
-		readID = splitLine[0][1:]
-		chromosome = splitLine[1]
-		refStart = int(splitLine[2])
-		refEnd = int(splitLine[3])
-		strand = splitLine[4]
-	else:
-		posOnRef = int(splitLine[0])
-		probLeftFork = float(splitLine[1])
-		probRightFork = float(splitLine[2])
-
-		#add these values to a container or do some processing here
-
-   f.close()
-
-And again for ``DNAscent regions``:
+The following example plots a histogram of fork track lengths from bed files generated by DNAscent forkSense.
 
 .. code-block:: python
 
-   f = open('path/to/output.regions','r')
+   import matplotlib
+   from matplotlib import pyplot as plt
 
-   for line in f:
+   fnames = ['leftForks_DNAscent_forkSense.bed','rightForks_DNAscent_forkSense.bed']
 
-	#ignore the header lines
-   	if line[0] == '#':
-		continue
-	
-	#split the line into a list by whitespace
-	splitLine = line.rstrip().split()
+   forkLengths = []
 
-	if line[0] == '>':
+   for fn in fnames:
+   	f = open(fn,'r')
 
-		readID = splitLine[0][1:]
-		chromosome = splitLine[1]
-		refStart = int(splitLine[2])
-		refEnd = int(splitLine[3])
-		strand = splitLine[4]
-	else:
-		regionStart = int(splitLine[0])
-		regionEnd = int(splitLine[1])
-		regionScore = float(splitLine[2])
+	   for line in f:
 
-		#add these values to a container or do some processing here
+		#ignore the header lines
+	   	if line[0] == '#':
+			continue
+		
+		#split the line into a list by whitespace
+		splitLine = line.rstrip().split()
+		
+		lbound = int(splitLine[1])
+		rbound = int(splitLine[2])
+		
+		forkLengths.append(rbound-lbound)
 
-   f.close()
+	   f.close()
 
+   plt.figure()
+   plt.hist(forkLengths)
+   plt.xlabel('Fork Track Length (bp)')
+   plt.ylabel('Count')
+   plt.savefig('forkTrackLen.pdf')
+   plt.close()
+   
+