Merge branch 'master' of https://github.com/telatin/covtobed

telatin · telatin · commit 3d76deb74e1d · 2020-07-30T10:41:34.000Z
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -1,4 +1,6 @@
-If you wish to fix a bug or add new features to the software we welcome Pull Requests. 
+# Contributing to `covtobed`
+
+If you wish to fix a bug or add new features to the software we welcome **Pull Requests**. 
 
 We use [GitHub Flow style development](https://guides.github.com/introduction/flow/). 
 
diff --git a/Docker/README.md b/Docker/README.md
@@ -1,18 +1,20 @@
 # Docker container
 
 This directories contains files to generate the Docker/Singularity images that provide:
- * `covtobed` as described in the [README](../README.md)
- * `coverage` a legacy program with some more features that has been used for the EU project _MD-PAEDIGREE_.
+
+* `covtobed` as described in the [README](../README.md)
+* `coverage` a legacy program with some more features that has been used for the EU project _MD-PAEDIGREE_.
  
- ## How to get it
+## How to get it
  
- The Docker image is distributed via [Docker Hub](https://hub.docker.com/r/andreatelatin/covtobed):
+The Docker image is distributed via [Docker Hub](https://hub.docker.com/r/andreatelatin/covtobed):
  
- ```
- sudo docker pull andreatelatin/covtobed
- ```
+```bash
+sudo docker pull andreatelatin/covtobed
+```
  
 The Singularity image can be pulled from Docker Hub as well. A snapshot (v. 0.3) is available from [Zenodo](https://zenodo.org/record/1063493):
-```
+
+```bash
 singularity pull andreatelatin/covtobed
 ```
diff --git a/Dockerfile b/Dockerfile
@@ -1,16 +1,23 @@
 FROM ubuntu:14.04
-MAINTAINER Andrea Telatin <andrea@telatin.com>
 COPY Docker/coverage /bin/coverage
 COPY Docker/v2.3.0.tar.gz /
 RUN mkdir /covtobed
 COPY *.cpp *.h /covtobed/
-RUN apt-get update && apt-get install -y software-properties-common
+RUN apt-get update && apt-get install -y --no-install-recommends software-properties-common=0.92.37.8 \
+     && apt-get clean \
+     && rm -rf /var/lib/apt/lists/*
 
 RUN add-apt-repository universe && apt-get update
-RUN apt-get install -y build-essential cmake wget libz-dev
+RUN apt-get install -y --no-install-recommends build-essential=11.6ubuntu6 cmake=2.8.12.2-0ubuntu3 wget=1.15-1ubuntu1  zlib1g-dev=1:1.2.8.dfsg-1ubuntu1.1 \
+     && apt-get clean \
+     && rm -rf /var/lib/apt/lists/*
 RUN tar xvfz "v2.3.0.tar.gz"
-RUN mkdir /bamtools-2.3.0/build && cd /bamtools-2.3.0/build && cmake .. && make
+RUN mkdir /bamtools-2.3.0/build 
+WORKDIR /bamtools-2.3.0/build
+RUN cmake .. 
+RUN make
 RUN cp /bamtools-2.3.0/lib/libbamtools* /usr/lib/x86_64-linux-gnu/
 
-RUN cd /covtobed && c++ -std=c++11 *.cpp  -I/bamtools-2.3.0/include/  /usr/lib/x86_64-linux-gnu/libbamtools.a   \
+WORKDIR /covtobed 
+RUN c++ -std=c++11 ./*.cpp  -I/bamtools-2.3.0/include/  /usr/lib/x86_64-linux-gnu/libbamtools.a   \
 	 -o /bin/covtobed -lz;
diff --git a/OptionParser.cpp b/OptionParser.cpp
@@ -26,8 +26,8 @@ namespace optparse {
 ////////// auxiliary (string) functions { //////////
 class str_wrap {
 public:
-  str_wrap(const string& l, const string& r) : lwrap(l), rwrap(r) {}
-  str_wrap(const string& w) : lwrap(w), rwrap(w) {}
+  explicit str_wrap(const string& l, const string& r) : lwrap(l), rwrap(r) {}
+  explicit str_wrap(const string& w) : lwrap(w), rwrap(w) {}
   string operator() (const string& s) { return lwrap + s + rwrap; }
   const string lwrap, rwrap;
 };
diff --git a/README.md b/README.md
@@ -5,18 +5,18 @@
 [![Bioconda installs](https://img.shields.io/conda/dn/bioconda/covtobed)](https://anaconda.org/bioconda/covtobed)
 [![TravisCI Build Status](https://travis-ci.org/telatin/covtobed.svg?branch=master)](https://travis-ci.org/telatin/covtobed)
 [![Docker build](https://img.shields.io/docker/cloud/build/andreatelatin/covtobed)](https://hub.docker.com/r/andreatelatin/covtobed)
-[![Singularity Zenodo Record](https://img.shields.io/badge/singularity-available-yellow)](https://zenodo.org/record/3600261)
-
+[![Codacy Badge](https://app.codacy.com/project/badge/Grade/36944efb0d2b44cca850964e96c036a4)](https://www.codacy.com/manual/telatin/covtobed?utm_source=github.com&amp;utm_medium=referral&amp;utm_content=telatin/covtobed&amp;utm_campaign=Badge_Grade)
+[![status](https://joss.theoj.org/papers/0ed74df9f40a58a852bf3fff512acd2b/status.svg)](https://joss.theoj.org/papers/0ed74df9f40a58a852bf3fff512acd2b)
 
 ### a tool to generate BED coverage tracks from BAM files
 
 Reads one (or more) [alignment](https://en.wikipedia.org/wiki/Sequence_alignment) files
 (sorted [BAM](https://en.wikipedia.org/wiki/SAM_(file_format))) and prints a [BED](https://en.wikipedia.org/wiki/BED_(file_format)) with the [coverage](https://en.wikipedia.org/wiki/Coverage_(genetics)). It will join consecutive bases with the same coverage, and can be used to only print a BED file with the regions having a specific coverage range. 
 
-:book: [Read more in the wiki](https://github.com/telatin/covtobed/wiki)
+:book: **[Read more in the wiki](https://github.com/telatin/covtobed/wiki)** - this is the **main** documentation source
 
 
-[![covtobed example](img/coverage_bam_to_bed.png)](https://github.com/telatin/covtobed/wiki)
+[![covtobed example](img/covtobed-vignette.png)](https://github.com/telatin/covtobed/wiki)
 
 
 ## Usage
@@ -58,7 +58,7 @@ Command:
 covtobed -m 0 -x 5 test/demo.bam
 ```
 Output:
-```
+```text
 [...]
 NC_001416.1     0       2       0
 NC_001416.1     2       6       1
@@ -69,29 +69,30 @@ NC_001416.1     169     170     4
 NC_001416.1     201     206     4
 [...]
 ```
+
 See the full example output from different tools [:open_file_folder: here](https://github.com/telatin/covtobed/blob/master/test/output/README.md)
 
 ## Install
 
- * To install with Miniconda:
+* To install with Miniconda:
 
-```
+```bash
 conda install -c bioconda covtobed
 ```
 
- * Both **covtobed**, and the legacy program [**coverage**](https://github.com/telatin/covtobed/wiki/Using-coverage) are available as a single Docker container available from Docker Hub [![Docker build](https://img.shields.io/docker/cloud/build/andreatelatin/covtobed)](https://hub.docker.com/r/andreatelatin/covtobed)
-:
-```
+* Both **covtobed**, and the legacy program [**coverage**](https://github.com/telatin/covtobed/wiki/Using-coverage) are available as a single Docker container available from Docker Hub [![Docker build](https://img.shields.io/docker/cloud/build/andreatelatin/covtobed)](https://hub.docker.com/r/andreatelatin/covtobed):
+
+```bash
 sudo docker pull andreatelatin/covtobed
 sudo docker run --rm -ti andreatelatin/covtobed coverage -h
 ```
 
  * Download Singularity image by `singularity pull docker://andreatelatin/covtobed`, then:
-```
+
+```bash
 singularity exec covtobed.simg coverage -h
 ```
 
-
 ## Performance
 
 *covtobed* is generally faster than *bedtools*. More details are in the [benchmark](benchmark) page.
@@ -107,17 +108,38 @@ c++ -std=c++11 *.cpp -I/path/to/bamtools/ -L${HOME}/path/to/lib/ -lbamtools -o c
 
 ## Issues, Limitations and how to contribute
 
- - This program will read the coverage from *sorted BAM* files. The *CRAM* format is not supported at the moment.
- - If you find a problem feel free to [raise an issue](https://github.com/telatin/covtobed/issues), we will try to address it as soon as possible
- - [Contributions](CONTRIBUTING.md) are welcome via PR.
+* This program will read the coverage from *sorted BAM* files. The *CRAM* format is not supported at the moment.
+* If you find a problem feel free to [raise an issue](https://github.com/telatin/covtobed/issues), we will try to address it as soon as possible
+* [Contributions](CONTRIBUTING.md) are welcome via PR.
 
 ## Acknowledgements
 
 This tools uses [libbamtools](https://github.com/pezmaster31/bamtools) by Derek Barnett, Erik Garrison, Gabor Marth and Michael Stromberg, and [cpp-optparse](https://github.com/weisslj/cpp-optparse) by Johannes Weißl. Both tools and this program are released with MIT license.
 
-
 ## Authors
 
 Giovanni Birolo ([@gbirolo](https://github.com/gbirolo)), University of Turin, and Andrea Telatin ([@telatin](https://github.com/telatin)), Quadram Institute Bioscience. 
 
 This program was finalized with a Flexible Talent Mobility Award funded by BBSRC through the [Quadram Institute](https://quadram.ac.uk).
+
+## Citation
+
+If you use this tool, why not citing the paper?
+
+> Birolo et al., (2020). covtobed: a simple and fast tool to extract coverage tracks from BAM files. Journal of Open Source Software, 5(47), 2119, https://doi.org/10.21105/joss.02119
+
+BibTeX citation:
+```latex
+@article{Birolo2020,
+  doi = {10.21105/joss.02119},
+  url = {https://doi.org/10.21105/joss.02119},
+  year = {2020},
+  publisher = {The Open Journal},
+  volume = {5},
+  number = {47},
+  pages = {2119},
+  author = {Giovanni Birolo and Andrea Telatin},
+  title = {covtobed: a simple and fast tool to extract coverage tracks from BAM files},
+  journal = {Journal of Open Source Software}
+}
+```
diff --git a/base.cpp b/base.cpp
@@ -16,9 +16,9 @@ using namespace std;
 typedef uint32_t DepthType; // type for depth of coverage, kept it small
 const char ref_char = '>';  // reference prefix for "counts" output
 
-const string VERSION = "%prog 1.1.0"
+const string VERSION = "%prog 1.1.3"
 	"\nCopyright (C) 2014-2019 Giovanni Birolo and Andrea Telatin\n"
-	"License MIT"
+	"https://github.com/telatin/covtobed - License MIT"
 	".\n"
 	"This is free software: you are free to change and redistribute it.\n"
 	"There is NO WARRANTY, to the extent permitted by law.";
@@ -210,6 +210,12 @@ int main(int argc, char *argv[]) {
 		min_mapq = options.get("min_mapq");
 	}
 
+	if (physical_coverage and only_valid) {
+		// https://github.com/telatin/covtobed/issues/11
+		cerr << "Parameters --physical-coverage and  --discard-invalid-alignments are currently mutually exclusive." << endl;
+		exit(0);
+	}
+
 	try {
 		// open input and output
 		Input input(parser.args(), min_mapq, only_valid);
@@ -274,7 +280,7 @@ int main(int argc, char *argv[]) {
 		if (more_alignments) {
 			throw string("Unexpected alignment found, is the BAM sorted?");			
 		}
-	} catch (string msg) {
+	} catch (const string &msg) {
 		parser.error(msg);
 	}
 	return 0;
diff --git a/benchmark/README.md b/benchmark/README.md
@@ -74,9 +74,9 @@ See also [example2.bam benchmark](disk/benchmark2_example2.md).
 
 ### Human whole genome sequencing - Saving to disk
 
-The human genome was downloaded from:
+The human genome alignment file (124,379,080 alignments) was downloaded from:
 
-ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000_genomes_project/data/GBR/HG00114/alignment/HG00114.alt_bwamem_GRCh38DH.20150718.GBR.low_coverage.cram
+:link: ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000_genomes_project/data/GBR/HG00114/alignment/HG00114.alt_bwamem_GRCh38DH.20150718.GBR.low_coverage.cram
 
 | Command | Mean [s] | Min [s] | Max [s] | Relative |                                                                                                                                
 |:---|---:|---:|---:|---:|                                                                                                                                                           
diff --git a/binaries/README.md b/binaries/README.md
@@ -1,6 +1,6 @@
 # Precompiled binaries for Linux and OS X
 
-* Linux: https://github.com/telatin/covtobed/releases/download/v0.3/covtobed
-* OS X:  https://github.com/telatin/covtobed/releases/download/v0.3/covtobed_osx
+* Linux: [https://github.com/telatin/covtobed/releases/download/v0.3/covtobed](https://github.com/telatin/covtobed/releases/download/v0.3/covtobed)
+* OS X: [https://github.com/telatin/covtobed/releases/download/v0.3/covtobed_osx](https://github.com/telatin/covtobed/releases/download/v0.3/covtobed_osx)
 
 The Linux binary has been tested with Ubuntu 14.04, Ubuntu 18.04, Fedora 26 and Fedora 30.
diff --git a/binaries/build_osx.sh b/binaries/build_osx.sh
@@ -14,10 +14,10 @@ SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null && pwd )"
 cd "$SCRIPT_DIR/.."
 
 sed -i.bak 's/#define debug if(.*)/#define debug if(true)/' base.cpp
-c++ -std=c++11 *.cpp -I${HOME}/miniconda3/include/bamtools/ -L${HOME}/miniconda3/lib/ $HOME/miniconda3/lib/libbamtools.a  \
+c++ -std=c++11 ./*.cpp -I"${HOME}"/miniconda3/include/bamtools/ -L$"{HOME}"/miniconda3/lib/ "$HOME"/miniconda3/lib/libbamtools.a  \
  -o binaries/covtobed_mac_debug -lz
 
 sed -i.bak 's/#define debug if(.*)/#define debug if(false)/' base.cpp
-c++ -std=c++11 *.cpp -I${HOME}/miniconda3/include/bamtools/ -L${HOME}/miniconda3/lib/ $HOME/miniconda3/lib/libbamtools.a  \
+c++ -std=c++11 ./*.cpp -I"${HOME}"/miniconda3/include/bamtools/ -L"${HOME}"/miniconda3/lib/ "$HOME"/miniconda3/lib/libbamtools.a  \
  -o binaries/covtobed_mac -lz
 cd -
diff --git a/binaries/build_ubuntu.sh b/binaries/build_ubuntu.sh
@@ -7,13 +7,12 @@ cd "$SCRIPT_DIR/.."
 
 # Make DEBUG
 sed -i 's/#define debug if(.*)/#define debug if(true)/' base.cpp
-c++ -std=c++11 *.cpp  -I/usr/include/bamtools /usr/lib/x86_64-linux-gnu/libbamtools.a  /usr/lib/gcc/x86_64-linux-gnu/5/libstdc++.a \
+c++ -std=c++11 ./*.cpp  -I/usr/include/bamtools /usr/lib/x86_64-linux-gnu/libbamtools.a  /usr/lib/gcc/x86_64-linux-gnu/5/libstdc++.a \
  -o binaries/covtobed_debug -lz
-cd -
 
 
 # Make NORMAL
 sed -i 's/#define debug if(.*)/#define debug if(false)/' base.cpp
-c++ -std=c++11 *.cpp  -I/usr/include/bamtools /usr/lib/x86_64-linux-gnu/libbamtools.a  /usr/lib/gcc/x86_64-linux-gnu/5/libstdc++.a \
+c++ -std=c++11 ./*.cpp  -I/usr/include/bamtools /usr/lib/x86_64-linux-gnu/libbamtools.a  /usr/lib/gcc/x86_64-linux-gnu/5/libstdc++.a \
  -o binaries/covtobed -lz
-cd -
+cd -
diff --git a/binaries/covtobed b/binaries/covtobed
diff --git a/binaries/covtobed_debug b/binaries/covtobed_debug
diff --git a/binaries/covtobed_mac b/binaries/covtobed_mac
diff --git a/binaries/covtobed_mac_debug b/binaries/covtobed_mac_debug
diff --git a/img/covtobed-vignette.png b/img/covtobed-vignette.png
diff --git a/test/output/README.md b/test/output/README.md
@@ -2,8 +2,7 @@
 
 Output of *mosdepth*, *covtobed* and *bedtools genomecov* from the ../demo.bam file
 
-
-```
+```bash
 covtobed ../demo.bam > covtobed.bed
 bedtools genomecov -bga  -ibam ../demo.bam > bedtools.bed
 mosdepth mos ../demo.bam && zcat mos.per-base.bed.gz > mosdepth.bed && rm mos.*
diff --git a/test/test.sh b/test/test.sh
@@ -6,14 +6,15 @@
 # REQUIRES: ./test/demo.bam
 #           ./test/mock.bam
 
-
+REMOVE=0
 if [ ! -e "test/demo.bam" ]; then
 	echo "WARNING: running this test from a bad location"
 	DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null && pwd )"
 	cd "$DIR"/..
 fi
 
 if [ ! -e "./covtobed" ]; then
+	REMOVE=1
 	echo "WARNING:"
 	echo "Binary not found: tring to use pre-compiled...";
 	if [ `uname` == 'Darwin' ]; then
@@ -129,10 +130,14 @@ fi
 echo  " - Checking artificial coverage values:"
 ./covtobed test/test_cov.bam -m 1 |cut -f 1,4| while read LINE;
 do
-	echo $LINE | perl -ne '($exp, $cov)=split /\s+/, $_; if ("$exp" ne "${cov}X") {
+	echo "$LINE" | perl -ne '($exp, $cov)=split /\s+/, $_; if ("$exp" ne "${cov}X") {
 		die "$exp != $cov\n";
 	} else {
 		print "\t#OK expecting $exp, ${cov}X found\n";
 	}'
 done
 echo "ALL TESTS: PASSED"
+
+if [[ $REMOVE -eq 1 ]]; then
+ rm ./covtobed
+fi
