Merge branch 'jts:master' into master

.gitmodules

@@ -1,9 +1,6 @@
 [submodule "htslib"]
 	path = htslib
 	url = https://github.com/samtools/htslib
-[submodule "fast5"]
-	path = fast5
-	url = https://github.com/mateidavid/fast5
 [submodule "minimap2"]
 	path = minimap2
 	url = https://github.com/lh3/minimap2

Makefile

@@ -1,7 +1,7 @@
 #
 
 # Sub directories containing source code, except for the main programs
-SUBDIRS := src src/hmm src/thirdparty src/thirdparty/scrappie src/common src/alignment src/pore_model src/io
+SUBDIRS := src src/hmm src/thirdparty src/thirdparty/scrappie src/common src/alignment src/pore_model src/io src/basemods
 
 #
 # Set libraries, paths, flags and options
@@ -10,7 +10,7 @@ SUBDIRS := src src/hmm src/thirdparty src/thirdparty/scrappie src/common src/ali
 #Basic flags every build needs
 LIBS = -lz
 CXXFLAGS ?= -g -O3
-CXXFLAGS += -std=c++11 -fopenmp -fsigned-char -D_FILE_OFFSET_BITS=64 #D_FILE_OFFSET_BITS=64 makes nanopolish work in 32 bit systems
+CXXFLAGS += -std=c++11 -fopenmp -fsigned-char -D_FILE_OFFSET_BITS=64 
 CFLAGS ?= -O3 -std=c99 -fsigned-char -D_FILE_OFFSET_BITS=64
 LDFLAGS ?=
 CXX ?= g++
@@ -27,7 +27,35 @@ HTS ?= install
 MINIMAP2 ?= install
 SLOW5LIB ?= install
 
-HDF5_VERSION ?= 1.8.14
+MACHINE := $(shell gcc -dumpmachine)
+
+# when building on MacOS we only support gcc, but need to set some paths
+ifneq (,$(findstring apple,$(MACHINE)))
+    SDK := $(shell xcrun --sdk macosx --show-sdk-path)
+    MAC_FLAGS = -isysroot $(SDK) -L/usr/lib
+    MAC=1
+    CXXFLAGS += $(MAC_FLAGS)
+    CFLAGS += $(MAC_FLAGS)
+endif
+
+ARM=0
+
+# set an ARM-specific flag
+ifneq (,$(findstring arm64,$(MACHINE)))
+    ARM=1
+endif
+
+# set an ARM-specific flag
+ifneq (,$(findstring aarch64,$(MACHINE)))
+    ARM=1
+endif
+
+ifeq ($(MAC), 1)
+    HDF5_VERSION ?= 1.13.0
+else
+    HDF5_VERSION ?= 1.8.14
+endif
+
 EIGEN_VERSION ?= 3.3.7
 
 # Check operating system, OSX doesn't have -lrt
@@ -80,26 +108,21 @@ else
     LIBS += -lminimap2
 endif
 
-# Default to build and link the libhts submodule
+# Default to build and link slow5 submodule
 ifeq ($(SLOW5LIB), install)
     SLOW5LIB_LIB = ./slow5lib/lib/libslow5.a
     SLOW5LIB_INCLUDE = -I./slow5lib/include/
 endif
 
 ifeq ($(ARM), 1)
-    MINIMAP2_OPT=arm_neon=1
-else
-    MINIMAP2_OPT=
+    MINIMAP2_OPT += arm_neon=1
 endif
 
-# Include the header-only fast5 library
-FAST5_INCLUDE = -I./fast5/include
-
 # Include the src subdirectories
 NP_INCLUDE = $(addprefix -I./, $(SUBDIRS))
 
 # Add include flags
-CPPFLAGS += $(H5_INCLUDE) $(HTS_INCLUDE) $(MINIMAP2_INCLUDE) $(FAST5_INCLUDE) $(NP_INCLUDE) $(EIGEN_INCLUDE) $(SLOW5LIB_INCLUDE)
+CPPFLAGS += $(H5_INCLUDE) $(HTS_INCLUDE) $(MINIMAP2_INCLUDE) $(NP_INCLUDE) $(EIGEN_INCLUDE) $(SLOW5LIB_INCLUDE)
 
 # Main programs to build
 PROGRAM = nanopolish
@@ -112,13 +135,14 @@ all: depend $(PROGRAM)
 # Build libhts
 #
 htslib/libhts.a:
-	$(MAKE) -C htslib htslib_default_libs="-lz -lm -lbz2" || exit 255
+	cp etc/htslib_config.h htslib/config.h
+	$(MAKE) -C htslib CFLAGS="$(MAC_FLAGS) -g -Wall -O2 -fvisibility=hidden" LDFLAGS="$(MAC_FLAGS) -fvisibility=hidden" htslib_default_libs="-lz -lm -lbz2" NONCONFIGURE_OBJS="" || exit 255
 
 minimap2/libminimap2.a:
-	$(MAKE) -C minimap2 $(MINIMAP2_OPT) libminimap2.a || exit 255
+	$(MAKE) -C minimap2 $(MINIMAP2_OPT) CFLAGS="$(MAC_FLAGS) -g -Wall -O2 -Wc++-compat" libminimap2.a || exit 255
 
 slow5lib/lib/libslow5.a:
-	$(MAKE) -C slow5lib || exit 255
+	$(MAKE) -C slow5lib CFLAGS="$(MAC_FLAGS) -g -Wall -O2 -std=c99"|| exit 255
 #
 # If this library is a dependency the user wants HDF5 to be downloaded and built.
 #
@@ -130,7 +154,7 @@ lib/libhdf5.a:
 
 	tar -xzf hdf5-$(HDF5_VERSION).tar.gz || exit 255
 	cd hdf5-$(HDF5_VERSION) && \
-		./configure --enable-threadsafe --disable-hl --libdir=`pwd`/../lib --includedir=`pwd`/../include --prefix=`pwd`/.. || exit 255
+		./configure CFLAGS="$(MAC_FLAGS)" CPPFLAGS="$(MAC_FLAGS)" --enable-threadsafe --disable-hl --libdir=`pwd`/../lib --includedir=`pwd`/../include --prefix=`pwd`/.. || exit 255
 	$(MAKE) -C hdf5-$(HDF5_VERSION) && $(MAKE) -C hdf5-$(HDF5_VERSION) install
 
 # Download and install eigen if not already downloaded

README.md

@@ -5,6 +5,7 @@
 Software package for signal-level analysis of Oxford Nanopore sequencing data. Nanopolish can calculate an improved consensus sequence for a draft genome assembly, detect base modifications, call SNPs and indels with respect to a reference genome and more (see Nanopolish modules, below).
 
 ## Release notes
+* 0.14.0: support modification bam files, compile on M1 apple hardware, support [SLOW5](https://github.com/hasindu2008/slow5lib) files
 
 * 0.13.3: fix conda build issues, better handling of VBZ-compressed files, integration of module for [nano-COP](https://www.nature.com/articles/s41596-020-00469-y)
 
@@ -42,8 +43,9 @@ By default, nanopolish will download and compile all of its required dependencie
 
 * [libhdf5-1.8.14](http://www.hdfgroup.org/HDF5/release/obtain5.html) compiled with multi-threading support `--enable-threadsafe`
 * [eigen-3.2.5](http://eigen.tuxfamily.org)
-* [htslib-1.4](http://github.com/samtools/htslib)
-* [minimap2-d2de282](http://github.com/lh3/minimap2)
+* [htslib-1.15.1](http://github.com/samtools/htslib)
+* [minimap2-fe35e67](http://github.com/lh3/minimap2)
+* [slow5lib-3680e17](https://github.com/hasindu2008/slow5lib)
 
 In order to use the additional python3 scripts within `/scripts`, install the dependencies via
 
@@ -93,11 +95,12 @@ nanopolish eventalign: align signal-level events to k-mers of a reference genome
 Nanopolish needs access to the signal-level data measured by the nanopore sequencer. The first step of any nanopolish workflow is to prepare the input data by telling nanopolish where to find the signal files. If you ran Albacore 2.0 on your data you should run `nanopolish index` on your input reads (-d can be specified more than once if using multiple runs):
 
 ```
-# Index the output of the albacore basecaller
-nanopolish index -d /path/to/raw_fast5s/ -s sequencing_summary.txt albacore_output.fastq
+# Index the output of the basecaller
+nanopolish index -d /path/to/raw_fast5s/ -s sequencing_summary.txt basecalled_output.fastq # for FAST5 inout
+nanopolish index basecalled_output.fastq --slow5 signals.blow5 # for SLOW5 input
 ```
 
-The `-s` option tells nanopolish to read the `sequencing_summary.txt` file from Albacore to speed up indexing. Without this option `nanopolish index` is extremely slow as it needs to read every fast5 file individually. If you basecalled your run in parallel, so you have multiple `sequencing_summary.txt` files, you can use the `-f` option to pass in a file containing the paths to the sequencing summary files (one per line).
+The `-s` option tells nanopolish to read the `sequencing_summary.txt` file from Albacore to speed up indexing. Without this option `nanopolish index` is extremely slow as it needs to read every fast5 file individually. If you basecalled your run in parallel, so you have multiple `sequencing_summary.txt` files, you can use the `-f` option to pass in a file containing the paths to the sequencing summary files (one per line). When using SLOW5 files as the input (FAST5 can be converted to SLOW5 using [slow5tools](https://github.com/hasindu2008/slow5tools)), `-s` option is not required and does not affect indexing performance. 
 
 ### Computing a new consensus sequence for a draft assembly
 

etc/htslib_config.h

@@ -0,0 +1,6 @@
+/* Nanopolish-specific config */
+//#define HAVE_LIBBZ2 1
+//#define HAVE_LIBLZMA 1
+//#define HAVE_LZMA_H 1
+#define HAVE_FSEEKO 1
+#define HAVE_DRAND48 1