.github/workflows/build.yml

@@ -1,9 +1,13 @@
 # copied from Daniel Cook's Seq collection
 name: "Build Bamtocov"
 
-on: 
-  - push
-  - pull_request
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+  workflow_dispatch:
+
 
 jobs:
   build:
@@ -40,7 +44,7 @@ jobs:
       uses: actions/cache@v1
       with:
         path: $HOME/htslib
-        key: ${{ runner.os }}-htslib-1.10
+        key: ${{ runner.os }}-htslib-1.12
 
     # Install Dependencies
     - name: Install dependencies (Linux)
@@ -49,21 +53,17 @@ jobs:
         sudo apt-get update
         sudo apt-get -qy install bwa make build-essential cmake libncurses-dev ncurses-dev libbz2-dev lzma-dev liblzma-dev \
              curl libssl-dev libtool autoconf automake libcurl4-openssl-dev
-
-    # Setup htslib
     - name: Install htslib (linux)
       if: runner.os == 'Linux'
       run: |
         cd
         git clone --recursive https://github.com/samtools/htslib.git
         cd htslib && git checkout 1.11 && autoheader && autoconf && ./configure --enable-libcurl
-        cd
-        sudo make -j 4 -C htslib install
+        sudo make -j 4 install
+        sudo ldconfig
         #echo "::set-env name=LD_LIBRARY_PATH::${LD_LIBRARY_PATH}:${HOME}/htslib"
-        echo "LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:${HOME}/htslib" >> $GITHUB_ENV
-        ls -lh $HOME/htslib/*.so
- 
-
+        #ls -lh $HOME/htslib/*.so
+        
     - name: Install hstlib (macos)
       if: runner.os == 'macOS'
       run: |
@@ -73,32 +73,38 @@ jobs:
       with:
         version: ${{ matrix.nimversion }}
 
-    - uses: actions-rs/toolchain@v1
-      with:
-        toolchain: stable
-    - uses: actions-rs/cargo@v1
-
 
     # Build and Test
     - name: Build macOS executable
       if: runner.os == 'macOS'
       run: |
         nimble build -y --verbose 
         ls -l bin/
+        
         bin/bamtocov --version
-        bash tests/all.sh
         
-    - name: Build Linux executable
+        bin/bamtocov input/mini.bam
+
+        bin/bamtocounts --version
+        bin/bamtocounts input/regions.bed input/mini.bam --debug --header
+        # TESTS
+        #bash tests/all.sh
+        
+        
+    - name: Build and Test Linux executable
       if: runner.os == 'Linux'
       run: |
         nimble build -y --verbose
         ls -l bin/
+        
         bin/bamtocov --version
-        bash tests/all.sh
-      
-    - name: Upload Artifact
-      if: success()
-      uses: actions/upload-artifact@v1.0.0
-      with:
-        name: bamtocov_${{ matrix.os }}
-        path: bin/
+        bin/bamtocounts --version
+        bin/bamtocov input/mini.bam
+        bin/bamtocounts input/regions.bed input/mini.bam --debug --header
+        #bash tests/all.sh
+        tests/bin/shpec tests/shpec/bamtocov.sh
+        tests/unit/bamtocov-base.sh
+        bin/bamtocov --regions input/regions.bed -o report.txt input/mini.bam > /dev/null
+        cat report.txt
+        echo "WHERE: $HOME/htslib" 
+        cat $HOME/htslib/version.h 

.github/workflows/docker-image.yml

@@ -0,0 +1,14 @@
+name: Docker Image CI
+
+on: workflow_dispatch
+
+jobs:
+
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Build the Docker image
+      run: docker build . --file benchmark/Dockerfile --tag bamtocovbenchmark:$(date +%s)

.gitignore

@@ -1,8 +1,8 @@
 nimcache/
 nimblecache/
 htmldocs/
-bin/*
-*.bai
+bin/bam*
+./bin
 profiling
 multiqc/
 .DS_Store
@@ -17,3 +17,16 @@ bamtocov_*
 *.fa.pac
 *.fa.sa
 *sam
+bamtocov-chrom*
+_test
+./shpec
+shunit2/
+.vscode
+shpec/
+_data/
+bin/covtotarget
+bin/gff2bed
+trash
+static/
+hts_nim_static_builder
+bin/*

CITATION.cff

@@ -0,0 +1,58 @@
+# This CITATION.cff file was generated with cffinit.
+# Visit https://bit.ly/cffinit to generate yours today!
+
+cff-version: 1.2.0
+title: >-
+  BamToCov, an efficient toolkit for sequence
+  coverage calculations
+message: >-
+  Please cite this dataset using the metadata from
+  'preferred-citation'.
+type: software
+authors:
+  - given-names: Andrea
+    family-names: Telatin
+    email: andrea.telatin@quadram.ac.uk
+    affiliation: Quadram Institute Bioscience
+    orcid: 'https://orcid.org/0000-0001-7619-281X'
+  - given-names: Giovanni
+    family-names: Birolo
+    email: giovanni.birolo@unito.it
+    affiliation: University of Turin
+identifiers:
+  - type: doi
+    value: 10.1101/2021.11.12.466787
+    description: >-
+      BamToCov: an efficient toolkit for sequence
+      coverage calculations
+url: 'https://telatin.github.io/bamtocov/'
+abstract: >
+  Motivation: Many genomics applications require the
+  computation of nucleotide coverage of a reference
+  genome or the ability to determine how many reads
+  map to a reference region. 
+
+
+  Results: BamToCov is a toolkit for rapid and
+  flexible coverage computation that relies on a
+  memory efficient algorithm and is designed for
+  integration in pipelines; this is possible as a
+  result of reading alignment files from streams. The
+  tools in the suite can process sorted BAM or CRAM
+  files, allowing the user to extract coverage
+  information via different filtering approaches and
+  also save the output in different formats (BED, Wig
+  or counts). 
+
+  The BamToCov algorithm can also handle
+  strand-specific and/or physical coverage analyses.
+
+
+  Availability: This program, accessory utilities,
+  and their documentation are freely available at
+  https://github.com/telatin/BamToCov.
+keywords:
+  - bioinformatics
+  - sequence coverage
+  - next-generation sequencing
+license: MIT

CONTRIBUTING.md

@@ -0,0 +1,11 @@
+# Contributing to `bamtocov`
+
+## Pull Requests
+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/). 
+
+Please fork the repo, make the change, then submit a Pull Request against out master branch, with details about what the change is and what it fixes/adds. 
+We will then review your changes and merge them, or provide feedback on enhancements.
+
+## Issues
+If you find bugs, or if you would like to make suggestions or feature requests, feel free to open an [issue](https://github.com/telatin/bamtocov/issues).

Makefile

@@ -0,0 +1,59 @@
+# Create "make test"
+.PHONY: testshpec testshunit2 test clean build
+
+BIN=./bin
+BIN2=./static
+SOURCE=./src
+LIBPATH=$(shell dirname $(shell which samtools) | sed 's/bin/lib/')
+NIM_PATHS= --colors:on --noNimblePath --path:/local/giovanni/bamtocov/nimbledeps/pkgs/hts-0.3.17 --path:/local/giovanni/bamtocov/nimbledeps/pkgs/docopt-0.6.8 --path:/local/giovanni/bamtocov/nimbledeps/pkgs/regex-0.19.0 --path:/local/giovanni/bamtocov/nimbledeps/pkgs/unicodedb-0.9.0 --path:/local/giovanni/bamtocov/nimbledeps/pkgs/lapper-0.1.7 
+VERSION := $(shell grep version bamtocov.nimble  | grep  -o "[0-9]\\+\.[0-9]\.[0-9]\\+")
+LIST=$(BIN)/bamtocov $(BIN)/bamtocounts $(BIN)/covtotarget $(BIN)/bamcountrefs $(BIN)/gff2bed $(BIN)/bamtocounts_legacy $(BIN)/bamtarget
+STATIC=$(BIN2)/bamtocov $(BIN2)/bamtocounts $(BIN2)/covtotarget $(BIN2)/bamcountrefs $(BIN2)/gff2bed $(BIN2)/bamtocounts_legacy $(BIN2)/bamtarget
+
+
+$(BIN)/%: $(SOURCE)/%.nim $(SOURCE)/covutils.nim bamtocov.nimble
+	nim c  $(NIM_PATHS) -d:NimblePkgVersion=$(VERSION) -d:danger --opt:speed  --out:$@ $<
+
+all: $(LIST)
+
+./hts_nim_static_builder:
+	wget "https://github.com/brentp/hts-nim/releases/download/v0.2.8/hts_nim_static_builder"
+	chmod +x hts_nim_static_builder
+
+static: $(STATIC)
+
+
+$(BIN2)/%: $(SOURCE)/%.nim bamtocov.nimble ./hts_nim_static_builder
+	mkdir -p $(BIN2)
+	echo target: $@
+	echo base: $(shell basename $@)
+	./hts_nim_static_builder  -n bamtocov.nimble -s $< -- -d:NimblePkgVersion=$(VERSION)
+	mv ./$(shell basename $@) $(BIN2)
+
+test: testshpec
+
+testall: testbash testshpec testshunit2
+
+testshpec:
+	@echo " --- Test shpec --- "
+	./tests/bin/shpec ./tests/shpec/bamtocov.sh
+
+testshunit2:
+	@echo " --- Test shunit2 --- "
+	./tests/unit/bamtocov-base.sh
+
+testbash:
+	@echo " --- Test (legacy) --- "
+	bash tests/all.sh
+
+
+build:
+	nimble build
+
+
+clean:
+	@echo "Cleaning..."
+	@for i in $(LIST); \
+	do \
+		if [ -e "$$i" ]; then rm -f $$i; echo "Removing $$i"; else echo "$$i Not found"; fi \
+	done

Makefile.old

@@ -0,0 +1,41 @@
+# Create "make test"
+.PHONY: testshpec testshunit2 test clean build
+
+BIN=./bin
+SOURCE=./src
+NIM_PATHS= --colors:on --noNimblePath --path:/local/giovanni/bamtocov/nimbledeps/pkgs/hts-0.3.17 --path:/local/giovanni/bamtocov/nimbledeps/pkgs/docopt-0.6.8 --path:/local/giovanni/bamtocov/nimbledeps/pkgs/regex-0.19.0 --path:/local/giovanni/bamtocov/nimbledeps/pkgs/unicodedb-0.9.0 --path:/local/giovanni/bamtocov/nimbledeps/pkgs/lapper-0.1.7 
+VERSION := $(shell grep version bamtocov.nimble  | grep  -o "[0-9]\\+\.[0-9]\.[0-9]\\+")
+LIST=$(BIN)/bamtocov $(BIN)/bamtoreads $(BIN)/bamtocounts $(BIN)/covtotarget $(BIN)/bamcountrefs $(BIN)/gff2bed $(BIN)/bamtocounts_legacy $(BIN)/bamtarget
+
+$(BIN)/%: $(SOURCE)/%.nim $(SOURCE)/covutils.nim bamtocov.nimble
+	nim c  $(NIM_PATHS) -d:NimblePkgVersion=$(VERSION) -d:release --opt:speed  --out:$@ $<
+
+all: $(LIST)
+
+
+test: testshpec 
+
+testall: testbash testshpec testshunit2
+testshpec:
+	@echo " --- Test shpec --- "
+	./tests/bin/shpec ./tests/shpec/bamtocov.sh
+
+testshunit2:
+	@echo " --- Test shunit2 --- "
+	./tests/unit/bamtocov-base.sh
+
+testbash:
+	@echo " --- Test (legacy) --- "
+	bash tests/all.sh
+
+
+build:
+	nimble build
+
+
+clean:
+	@echo "Cleaning..."
+	@for i in $(LIST); \
+	do \
+		if [ -e "$$i" ]; then rm -f $$i; echo "Removing $$i"; else echo "$$i Not found"; fi \
+	done

README.md

@@ -3,6 +3,7 @@
 [![Build Bamtocov](https://github.com/telatin/bamtocov/actions/workflows/build.yml/badge.svg)](https://github.com/telatin/bamtocov/actions/workflows/build.yml)
 [![Downloads](https://img.shields.io/conda/dn/bioconda/bamtocov)](https://anaconda.org/bioconda/bamtocov)
 [![Platforms](https://anaconda.org/bioconda/bamtocov/badges/platforms.svg)](https://bioconda.github.io/recipes/bamtocov/README.html)
+[![Paper](https://img.shields.io/badge/paper-bioinformatics-yellow)](https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/btac125/6535233)
 
 [![bamtocov logo](docs/bamtocov-banner.png)](https://telatin.github.io/bamtocov/)
 
@@ -24,9 +25,24 @@ The BamToCov package is available from :package: [BioConda](https://bioconda.git
 conda install -y -c bioconda bamtocov
 ```
 
-## References
+## Benchmarks
+
+Bamtocov has the smallest memory footprint of any other coverage tool, while maintaining reasonable speeds
+
+* Four BAM files used for the benchmarks are [available from Zenodo](https://zenodo.org/record/5636944#.Yf_cMe7P36Y)
+* A [Dockerfile](benchmark/) with an automatic speed test is available in this repository
+
+## See also
 
 * Brent Pedersen,  Aaron Quinlan,
 [hts-nim: scripting high-performance genomic analyses](https://academic.oup.com/bioinformatics/article/34/19/3387/4990493) (Bioinformatics)
 * Giovanni Birolo, Andrea Telatin,
 [covtobed: a simple and fast tool to extract coverage tracks from BAM files](https://joss.theoj.org/papers/10.21105/joss.02119) (JOSS)
+
+Initially we also used [Lapper](https://brentp.github.io/nim-lapper/index.html), 
+and I recommend checking out this library for fast interval operations.
+
+## Cite
+
+Giovanni Birolo, Andrea Telatin, 
+[BamToCov: an efficient toolkit for sequence coverage calculations](https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/btac125/6535233), Bioinformatics, 2022

bamtocov.nimble

@@ -1,6 +1,6 @@
 # Package
 
-version       = "2.2.0"
+version       = "2.8.0"
 author        = "Andrea Telatin, Giovanni Birolo"
 description   = "BAM to Coverage"
 license       = "MIT"
@@ -10,7 +10,7 @@ license       = "MIT"
 requires "hts >= 0.3.1", "docopt >= 0.6.8", "nim >= 1.0.0", "lapper"
 srcDir = "src"
 binDir = "bin"
-bin = @["covtotarget", "bamtocounts", "bamtocov", "bamcountrefs"]
+bin = @["covtotarget", "bamtocounts", "bamtocov", "bamcountrefs", "gff2bed", "bamtarget"]
 skipDirs = @["tests", "docs"]
 skipFiles = @["example.bam"]
 

benchmark/Dockerfile

@@ -0,0 +1,19 @@
+FROM nfcore/base:1.9
+LABEL authors="Andrea Telatin" \
+      description="Docker image containing all software requirements for the telatin/nextflow-example project"
+
+# Install the conda environment
+COPY benchmark/env.yaml /environment.yml
+COPY benchmark/compare.sh /usr/local/bin/
+
+RUN conda install -q -y -c conda-forge mamba && mamba env create -q -n env -f /environment.yml && conda clean -a
+
+# Add conda installation dir to PATH (instead of doing 'conda activate')
+ENV PATH /opt/conda/envs/env/bin:$PATH
+# (alternative: replace the name with $(head -n 1 env.yaml  | cut -f 2 -d " ") or similar
+
+# Dump the details of the installed packages to a file for posterity
+RUN conda env export --name env > workflow.yml
+
+RUN compare.sh all
+RUN cat *md