Skip to content
GitLab
Projects
Groups
Snippets
/
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
hem
hamlet
Commits
4a0dc089
Commit
4a0dc089
authored
Jun 24, 2020
by
van den Berg
Browse files
Merge branch 'devel' into 'master'
Merge development into master See merge request
!7
parents
86c18017
2c1d312f
Pipeline
#3879
failed with stages
in 32 minutes and 23 seconds
Changes
47
Pipelines
2
Hide whitespace changes
Inline
Side-by-side
.gitignore
View file @
4a0dc089
...
...
@@ -28,7 +28,6 @@ config-cluster.yml
# git has its own built in compression methods
*.7z
*.dmg
*.gz
*.iso
*.jar
*.rar
...
...
Snakefile.deps
deleted
100644 → 0
View file @
86c18017
from snakemake.remote.NCBI import RemoteProvider as NCBIRemoteProvider
import os
NCBI = NCBIRemoteProvider(email='RedmarvandenBerg@lumc.nl')
output_dir = '/tmp/deps'
temp_dir = '/tmp/temp'
#### SETTINGS ####
ctat_resource = 'https://data.broadinstitute.org/Trinity/CTAT_RESOURCE_LIB/__genome_libs_pre-StarFv1.3/GRCh38_gencode_v26_CTAT_lib_July192017.source_data.tar.gz'
ctat_resource_tar_gz = ctat_resource.split('/')[-1]
ctat_resource_folder = ctat_resource_tar_gz.split('.')[0]
gsnap = 'http://research-pub.gene.com/gmap/src/gmap-gsnap-2014-12-31.v2.tar.gz'
gsnap_tar_gz = gsnap.split('/')[-1]
gsnap_folder = 'gmap-2014-12-31'
gmap_index = 'ftp.ncbi.nlm.nih.gov/genomes/archive/old_genbank/Eukaryotes/vertebrates_mammals/Homo_sapiens/GRCh38/seqs_for_alignment_pipelines/GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.gz'
gmap_gz = gmap_index.split('/')[-1]
# GRCH38_no_alt_analysis_set, see the readme for details
# https://ftp.ncbi.nlm.nih.gov/genomes/archive/old_genbank/Eukaryotes/vertebrates_mammals/Homo_sapiens/GRCh38/seqs_for_alignment_pipelines/README_ANALYSIS_SETS
GRCH38_no_alt_analysis_set_url = 'ftp.ncbi.nlm.nih.gov/genomes/archive/old_genbank/Eukaryotes/vertebrates_mammals/Homo_sapiens/GRCh38/seqs_for_alignment_pipelines'
GRCH38_no_alt_analysis_set_filename = os.path.join(GRCH38_no_alt_analysis_set_url, 'GCA_000001405.15_GRCh38_no_alt_analysis_set')
GRCH38_no_alt_analysis_set_fasta_gz = f'{GRCH38_no_alt_analysis_set_filename}.fna.gz'
GRCH38_no_alt_analysis_set_fasta = f'{GRCH38_no_alt_analysis_set_filename}.fna'
GRCH38_no_alt_analysis_set_fai = f'{GRCH38_no_alt_analysis_set_filename}.fna.fai'
GRCH38_no_alt_analysis_set_dict = f'{GRCH38_no_alt_analysis_set_filename}.dict'
#### RULES ####
rule all:
input:
#f'{output_dir}/FLT3.fasta',
#f'{output_dir}/KMT2A.fasta',
f'{output_dir}/{ctat_resource_folder}',
#f'{output_dir}/{gsnap_folder}',
f'{output_dir}/{gsnap_folder}/bin/gsnap',
#f'{output_dir}/GCA_000001405.15_GRCh38_no_alt_analysis_set.fna'
f'{output_dir}/{os.path.basename(GRCH38_no_alt_analysis_set_fasta_gz)}',
f'{output_dir}/{os.path.basename(GRCH38_no_alt_analysis_set_fai)}',
f'{output_dir}/{os.path.basename(GRCH38_no_alt_analysis_set_fasta)}',
f'{output_dir}/{os.path.basename(GRCH38_no_alt_analysis_set_dict)}'
rule download_flt3:
input:
NCBI.remote('NM_004119.2.fasta', db='nuccore')
output:
f'{output_dir}/FLT3.fasta'
run:
shell('sleep 5s; cp {input} {output}')
rule download_kmt2a:
input:
NCBI.remote('NM_001197104.1.fasta', db='nuccore')
output:
f'{output_dir}/KMT2A.fasta'
run:
shell('sleep 5s; cp {input} {output}')
rule download_genome_star_fusion_lib:
params:
ctat_resource
output:
f'{temp_dir}/GRCh38_gencode_v26_CTAT_lib_July192017.source_data.tar.gz'
run:
shell('mkdir -p {temp_dir} && wget {params} --output-document={output}')
rule unpack_genome_star_fusion_lib:
input:
f'{temp_dir}/{ctat_resource_tar_gz}'
output:
f'{output_dir}/{ctat_resource_folder}'
run:
shell('tar -zxvf {input} -C {output_dir}')
rule download_SIMD_gsnap:
params:
gsnap
output:
f'{temp_dir}/{gsnap_tar_gz}'
run:
shell('mkdir -p {temp_dir} && wget {params} --output-document={output}')
rule unpack_SIMD_gsnap:
input:
f'{temp_dir}/{gsnap_tar_gz}'
output:
f'{output_dir}/{gsnap_folder}'
run:
shell('tar -zxvf {input} -C {output_dir}')
rule compile_SIMD_gsnap:
input:
f'{output_dir}/{gsnap_folder}'
output:
f'{output_dir}/{gsnap_folder}/bin/gsnap'
run:
shell('cd {input} && ./configure --prefix {input} && make && make install')
rule download_gmap_index:
params:
gmap_index
output:
f'{temp_dir}/{gmap_gz}'
run:
shell('mkdir -p {temp_dir} && wget {params} --output-document={output}')
rule build_gmap_index:
input:
gzip = f'{temp_dir}/{gmap_gz}',
gmap_bin = f'{output_dir}/{gsnap_folder}/bin'
output:
f'{output_dir}/GCA_000001405.15_GRCh38_no_alt_analysis_set.sources'
run:
shell('{input.gmap_bin}/gmap_build -D {output_dir} -d GCA_000001405.15_GRCh38_no_alt_analysis_set -g {input.gzip} -B {input.gmap_bin}')
rule download_GRCH38_no_alt_fasta:
params:
GRCH38_no_alt_analysis_set_fasta_gz
output:
f'{output_dir}/{os.path.basename(GRCH38_no_alt_analysis_set_fasta_gz)}'
run:
shell('wget {params} --output-document={output}')
rule unpack_GRCH38_no_alt:
input:
f'{output_dir}/{os.path.basename(GRCH38_no_alt_analysis_set_fasta_gz)}'
output:
f'{output_dir}/{os.path.basename(GRCH38_no_alt_analysis_set_fasta)}'
run:
shell('gunzip --decompress --keep --to-stdout {input} > {output}')
rule download_GRCH38_no_alt_fai:
params:
GRCH38_no_alt_analysis_set_fai
output:
f'{output_dir}/{os.path.basename(GRCH38_no_alt_analysis_set_fai)}'
run:
shell('wget {params} --output-document={output}')
rule picard_index_GRCH38_no_alt:
input:
f'{output_dir}/{os.path.basename(GRCH38_no_alt_analysis_set_fasta)}'
output:
f'{output_dir}/{os.path.basename(GRCH38_no_alt_analysis_set_dict)}'
conda:
srcdir('includes/snv-indels/envs/align_vars.yml')
shell:
'picard CreateSequenceDictionary R={input} O={output}'
environment.yml
View file @
4a0dc089
...
...
@@ -7,6 +7,6 @@ channels:
-
conda-forge
-
defaults
dependencies
:
-
pytest-workflow
-
pytest-workflow
>=1.4.0
-
python>3.6
-
snakemake=5.9
envs/create_summary.yml
deleted
100644 → 0
View file @
86c18017
name
:
create_summary
channels
:
-
bioconda
-
defaults
-
conda-forge
dependencies
:
-
ca-certificates=2018.03.07
-
certifi=2018.1.18
-
crimson=0.3.0
-
click=6.7
-
libgcc-ng=7.2.0
-
openssl=1.0.2o
-
pip=9.0.3
-
python=3.6.2
-
pyyaml=3.12
-
readline=6.2
-
setuptools=39.0.1
-
sqlite=3.13.0
-
tk=8.5.18
-
wheel=0.31.0
-
xz=5.2.3
-
yaml=0.1.7
-
zlib=1.2.11
includes/expression/envs/calc_ratio.yml
deleted
100644 → 0
View file @
86c18017
name
:
calc_ratio
channels
:
-
bioconda
-
defaults
-
conda-forge
dependencies
:
-
click=6.7
-
pandas=0.20.3
-
pip=9.0.1
-
python=3.6.2
-
mkl=2017.0.3
-
numpy=1.13.1
-
openssl=1.0.2l
-
python-dateutil=2.6.1
-
pytz=2017.2
-
readline=6.2
-
setuptools=27.2.0
-
six=1.10.0
-
sqlite=3.13.0
-
tk=8.5.18
-
wheel=0.29.0
-
xz=5.2.3
-
zlib=1.2.11
includes/expression/envs/count_bases.yml
deleted
100644 → 0
View file @
86c18017
name
:
count_bases
channels
:
-
bioconda
-
r
-
defaults
-
conda-forge
dependencies
:
-
bedtools=2.17.0
-
r=3.3.2
-
r-getopt=1.20.0
-
python=2.7.13
-
pip=9.0.1
-
bzip2=1.0.6
-
cairo=1.14.8
-
curl=7.54.1
-
fontconfig=2.12.1
-
freetype=2.5.5
-
glib=2.50.2
-
gsl=2.2.1
-
harfbuzz=0.9.39
-
icu=54.1
-
jbig=2.1
-
jpeg=9b
-
krb5=1.13.2
-
libffi=3.2.1
-
libgcc=5.2.0
-
libiconv=1.14
-
libpng=1.6.27
-
libssh2=1.8.0
-
libtiff=4.0.6
-
libxml2=2.9.4
-
ncurses=5.9
-
openssl=1.0.2l
-
pango=1.40.3
-
pcre=8.39
-
pixman=0.34.0
-
r-base=3.3.2
-
r-boot=1.3_18
-
r-class=7.3_14
-
r-cluster=2.0.5
-
r-codetools=0.2_15
-
r-foreign=0.8_67
-
r-kernsmooth=2.23_15
-
r-lattice=0.20_34
-
r-mass=7.3_45
-
r-matrix=1.2_7.1
-
r-mgcv=1.8_16
-
r-nlme=3.1_128
-
r-nnet=7.3_12
-
r-recommended=3.3.2
-
r-rpart=4.1_10
-
r-spatial=7.3_11
-
r-survival=2.40_1
-
readline=6.2
-
setuptools=27.2.0
-
sqlite=3.13.0
-
tk=8.5.18
-
wheel=0.29.0
-
xz=5.2.3
-
zlib=1.2.11
includes/expression/envs/count_fragments.yml
deleted
100644 → 0
View file @
86c18017
name
:
count_fragments
channels
:
-
bioconda
-
defaults
-
conda-forge
dependencies
:
-
python=2.7.13
-
bcftools=1.5
-
pysam=0.11.2.2
-
bzip2=1.0.6
-
cairo=1.14.8
-
curl=7.54.1
-
cycler=0.10.0
-
dbus=1.10.20
-
expat=2.1.0
-
fontconfig=2.12.1
-
freetype=2.5.5
-
functools32=3.2.3.2
-
glib=2.50.2
-
gst-plugins-base=1.8.0
-
gstreamer=1.8.0
-
htslib=1.5
-
icu=54.1
-
jpeg=9b
-
krb5=1.13.2
-
libffi=3.2.1
-
libgcc=5.2.0
-
libiconv=1.14
-
libpng=1.6.27
-
libssh2=1.8.0
-
libxcb=1.12
-
libxml2=2.9.4
-
matplotlib=2.0.2
-
mkl=2017.0.3
-
numpy=1.13.1
-
openssl=1.0.2l
-
pcre=8.39
-
pip=9.0.1
-
pixman=0.34.0
-
pycairo=1.10.0
-
pyparsing=2.2.0
-
pyqt=5.6.0
-
python-dateutil=2.4.1
-
pytz=2017.2
-
qt=5.6.2
-
readline=6.2
-
samtools=1.5
-
setuptools=27.2.0
-
sip=4.18
-
six=1.10.0
-
sqlite=3.13.0
-
subprocess32=3.2.7
-
tk=8.5.18
-
wheel=0.29.0
-
xz=5.2.3
-
zlib=1.2.11
-
pip
:
-
htseq==0.6.1p1
includes/expression/envs/idsort_aln.yml
deleted
100644 → 0
View file @
86c18017
name
:
idsort_aln
channels
:
-
bioconda
-
defaults
-
conda-forge
dependencies
:
-
picard=1.141
-
java-jdk=8.0.92
includes/fusion/envs/combine_plots.yml
deleted
100644 → 0
View file @
86c18017
name
:
combine_plots
channels
:
-
bioconda
-
defaults
-
conda-forge
dependencies
:
-
click=6.7
-
libxml2=2.9.4
-
libxslt=1.1.29
-
pip=9.0.1
-
python=3.5.3
-
libiconv=1.14
-
openssl=1.0.2l
-
readline=6.2
-
setuptools=27.2.0
-
sqlite=3.13.0
-
tk=8.5.18
-
wheel=0.29.0
-
xz=5.2.2
-
zlib=1.2.8
-
pip
:
-
svgutils==0.2.0
-
lxml==3.8.0
includes/fusion/envs/fusioncatcher.yml
deleted
100644 → 0
View file @
86c18017
name
:
fusioncatcher
channels
:
-
bioconda
-
defaults
-
conda-forge
dependencies
:
-
fusioncatcher=1.00
-
fusioncatcher-seqtk=1.2
-
bbmap=38.49
-
biopython=1.68
-
blas=1.0
-
blat=35
-
bowtie=1.2.0
-
bowtie2=2.3.0
-
bwa=0.7.12
-
ca-certificates=2019.1.23
-
certifi=2019.3.9
-
et_xmlfile=1.0.1
-
freetype=2.9.1
-
intel-openmp=2019.3
-
java-jdk=8.0.92
-
jdcal=1.4.1
-
jpeg=9b
-
libedit=3.1.20181209
-
libffi=3.2.1
-
libgcc=7.2.0
-
libgcc-ng=8.2.0
-
libgfortran-ng=7.3.0
-
libpng=1.6.37
-
libstdcxx-ng=8.2.0
-
libtiff=4.0.10
-
libuuid=1.0.3
-
lzo=2.10
-
lzop=1.04
-
mkl=2018.0.3
-
mmtf-python=1.0.2
-
msgpack-python=0.6.1
-
mysql-connector-c=6.1.6
-
ncurses=6.1
-
numpy=1.13.1
-
oases=0.2.09
-
olefile=0.46
-
openjdk=8.0.152
-
openpyxl=2.5.0a2
-
openssl=1.1.1b
-
parallel=20171222
-
perl=5.26.0
-
perl-threaded=5.26.0
-
picard=2.10.6
-
pigz=2.3
-
pillow=6.0.0
-
pip=19.1.1
-
python=2.7.16
-
readline=7.0
-
reportlab=3.5.19
-
samtools=0.1.19
-
setuptools=41.0.1
-
sqlite=3.28.0
-
sra-tools=2.6.2
-
star=2.5.2b
-
system=5.8
-
tbb=2019.4
-
tk=8.6.8
-
ucsc-fatotwobit=357
-
ucsc-liftover=357
-
velvet=1.2.10
-
wheel=0.33.4
-
xlrd=1.0.0
-
xz=5.2.4
-
zip=3.0
-
zlib=1.2.11
-
zstd=1.3.7
includes/fusion/envs/intersect_fusions.yml
deleted
100644 → 0
View file @
86c18017
name
:
intersect_fusions
channels
:
-
bioconda
-
defaults
-
conda-forge
dependencies
:
-
pip=9.0.1
-
python=2.7
-
grep=2.14
-
fuma=3.0.5
-
bcftools=1.5
-
bzip2=1.0.6
-
cairo=1.14.8
-
curl=7.54.1
-
cycler=0.10.0
-
dbus=1.10.20
-
expat=2.1.0
-
fontconfig=2.12.1
-
freetype=2.5.5
-
functools32=3.2.3.2
-
glib=2.50.2
-
gst-plugins-base=1.8.0
-
gstreamer=1.8.0
-
htseq=0.7.2
-
htslib=1.5
-
icu=54.1
-
jpeg=9b
-
krb5=1.13.2
-
libffi=3.2.1
-
libgcc=5.2.0
-
libiconv=1.14
-
libpng=1.6.27
-
libssh2=1.8.0
-
libxcb=1.12
-
libxml2=2.9.4
-
matplotlib=2.0.2
-
mkl=2017.0.3
-
numpy=1.13.1
-
openssl=1.0.2l
-
pcre=8.39
-
pixman=0.34.0
-
pycairo=1.10.0
-
pyparsing=2.2.0
-
pyqt=5.6.0
-
pysam=0.11.2.2
-
python-dateutil=2.4.1
-
pytz=2017.2
-
qt=5.6.2
-
readline=6.2
-
samtools=1.5
-
setuptools=27.2.0
-
sip=4.18
-
six=1.10.0
-
sqlite=3.13.0
-
subprocess32=3.2.7
-
tk=8.5.18
-
wheel=0.29.0
-
xz=5.2.3
-
zlib=1.2.11
includes/fusion/envs/plot_fusion.yml
deleted
100644 → 0
View file @
86c18017
name
:
plot_fusion
channels
:
-
bioconda
-
defaults
-
conda-forge
dependencies
:
-
circos=0.69.4
-
icu=58
-
pip=9.0.1
-
fontconfig=2.13
-
freetype=2.9
-
giflib=5.1.4
-
jbig=2.1
-
libgcc=5.2.0
-
libiconv=1.14
-
libpng=1.6
-
libtiff=4.0
-
libwebp=0.5.2
-
libxml2=2.9
-
openssl=1.1
-
perl=5.22.0.1
-
perl-app-cpanminus=1.7039
-
perl-clone=0.38
-
perl-config-general=2.61
-
perl-data-dumper=2.161
-
perl-digest-hmac=1.03
-
perl-digest-perl-md5=1.9
-
perl-encode-locale=1.05
-
perl-exporter-tiny=0.042
-
perl-extutils-makemaker=7.24
-
perl-file-listing=6.04
-
perl-font-ttf=1.05
-
perl-gd=2.56
-
perl-html-parser=3.72
-
perl-html-tagset=3.20
-
perl-http-cookies=6.01
-
perl-http-daemon=6.01
-
perl-http-date=6.02
-
perl-http-message=6.11
-
perl-http-negotiate=6.01
-
perl-io-html=1.001
-
perl-io-socket-ssl=2.024
-
perl-io-string=1.08
-
perl-libwww-perl=6.15
-
perl-list-moreutils=0.413
-
perl-lwp-mediatypes=6.02
-
perl-math-bezier=0.01
-
perl-math-round=0.07
-
perl-math-vecstat=0.08
-
perl-module-implementation=0.09
-
perl-module-runtime=0.014
-
perl-net-http=6.09
-
perl-net-ssleay=1.74
-
perl-ntlm=1.09
-
perl-number-format=1.75
-
perl-params-validate=1.26
-
perl-pathtools=3.40
-
perl-readonly=1.04
-
perl-regexp-common=2016060801
-
perl-scalar-list-utils=1.45
-
perl-set-intspan=1.19
-
perl-statistics-basic=1.6611
-
perl-svg=2.64
-
perl-test-more=1.001002
-
perl-text-format=0.59
-
perl-threaded=5.22.0
-
perl-time-hires=1.9728
-
perl-try-tiny=0.24
-
perl-uri=1.71
-
perl-www-robotrules=6.02
-
perl-xml-parser=2.44
-
perl-xsloader=0.22
-
python=3.6
-
readline=7.0
-
setuptools=27.2.0
-
tk=8.6
-
wheel=0.29.0
-
xz=5.2
-
zlib=1.2
-
r=3.5.1
-
r-base=3.5.1
-
r-boot=1.3_22
-
r-class=7.3_15
-
r-codetools=0.2_16
-
r-foreign=0.8_71
-
r-kernsmooth=2.23_15
-
r-lattice=0.20_38
-
r-mass=7.3_51.4
-
r-matrix=1.2_17
-
r-mgcv=1.8_28
-
r-nlme=3.1_140
-
r-nnet=7.3_12
-
r-recommended=3.5.1
-
r-rpart=4.1_15
-
r-spatial=7.3_11
-
r-survival=2.44_1.1
-
tktable=2.10
-
xorg-kbproto=1.0.7
-
xorg-libice=1.0.9
-
xorg-libsm=1.2.3
-
xorg-libx11=1.6.7
-
xorg-libxau=1.0.9
-
xorg-libxdmcp=1.1.3
-
xorg-libxext=1.3.4
-
xorg-libxrender=0.9.10
-
xorg-renderproto=0.11.1
-
xorg-xextproto=7.3.0
-
xorg-xproto=7.0.31
-
pip
:
-
fsnviz==0.3.0
-
click==6.7
-
crimson==0.3.0
-
jinja2==2.9.5
-
markupsafe==1.0
-
pyyaml==3.12
includes/fusion/envs/star_fusion.yml
deleted
100644 → 0
View file @
86c18017
name
:
star_fusion
channels
:
-
bioconda
-
defaults
-
conda-forge
dependencies
:
-
star-fusion=0.5.4
-
star=2.5.3a
-
blast=2.2.31