Merge pull request #79 from sanjaynagi/cutadapt-fastp-21-07-23

remove cutadapt and add fastp

.github/workflows/github-action-rna-seq-pop.yml → .github/workflows/github-action-rna-seq-pop-paired-end.yml

@@ -1,6 +1,6 @@
-name: rna-seq-pop
+name: rna-seq-pop-paired-end
 
-on: [push, pull_request]
+on: pull_request
 
 jobs:
   run-workflow:
@@ -9,12 +9,7 @@ jobs:
       - name: Set up python3
         uses: actions/setup-python@v2
         with:
-          python-version: '3.7' # Version range or exact version of a Python version to use, using SemVer's version range syntax
-
-      - name: Set up python2
-        uses: actions/setup-python@v2
-        with:
-          python-version: '2.7' # Version range or exact version of a Python version to use, using SemVer's version range syntax
+          python-version: '3.9' # Version range or exact version of a Python version to use, using SemVer's version range syntax
 
       - name: Checkout repository
         uses: actions/checkout@v2
@@ -27,10 +22,3 @@ jobs:
           directory: '.test'
           snakefile: 'workflow/Snakefile'
           args: '--cores 4 --use-conda --configfile .test/config/config_paired_end.yaml --conda-cleanup-pkgs cache'
-
-      - name: Test workflow single-end
-        uses: snakemake/[email protected]
-        with:
-          directory: '.test'
-          snakefile: 'workflow/Snakefile'
-          args: "--cores 4 --use-conda --configfile .test/config/config_single_end.yaml --conda-cleanup-pkgs cache"

.github/workflows/github-action-rna-seq-pop-single-end.yml

@@ -0,0 +1,24 @@
+name: rna-seq-pop-single-end
+
+on: pull_request
+
+jobs:
+  run-workflow:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Set up python3
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.9' # Version range or exact version of a Python version to use, using SemVer's version range syntax
+
+      - name: Checkout repository
+        uses: actions/checkout@v2
+        with:
+          submodules: recursive
+
+      - name: Test workflow single-end
+        uses: snakemake/[email protected]
+        with:
+          directory: '.test'
+          snakefile: 'workflow/Snakefile'
+          args: "--cores 4 --use-conda --configfile .test/config/config_single_end.yaml --conda-cleanup-pkgs cache"

.test/config/config_paired_end.yaml

@@ -32,10 +32,7 @@ contrasts:
       - 'ContTia_PiriTia'
 
 QualityControl:
-      cutadapt:
-            activate: False
-            adaptors:
-      fastqc:
+      fastp-trim:
             activate: True
       mosdepth:
             activate: True

.test/config/config_single_end.yaml

@@ -35,10 +35,7 @@ contrasts:
 
 
 QualityControl:
-      cutadapt:
-            activate: False
-            adaptors:
-      fastqc:
+      fastp-trim:
             activate: True
       mosdepth:
             activate: True
@@ -82,7 +79,7 @@ VariantAnalysis:
             missingness: 0.4
 
       selection:
-            activate: False
+            activate: True
             missingness: 0.5
             # Do we want to run pbs (Needs three conditions, two more closely related and a slight outgroup)
             pbs:

config/exampleconfig.yaml

@@ -41,9 +41,8 @@ contrasts:
 
 
 QualityControl:
-      cutadapt:
+      trim-reads:
             activate: False
-            adaptors:
       fastqc:
             activate: True
       mosdepth:

workflow/Snakefile

@@ -28,7 +28,7 @@ else:
 
 include: "rules/common.smk"
 
-welcome(version="v1.0.4")
+welcome(version="v1.0.5")
 
 include: "rules/qc.smk"
 include: "rules/diffexp.smk"

workflow/envs/pythonGenomics.yaml

@@ -1,15 +1,260 @@
+name: /home/sanj/projects/IR/rna-seq-busia/.test/.snakemake/conda/05a9e65ff79282deacacf9adbc9a0eb2_
 channels:
-  - conda-forge
   - bioconda
+  - conda-forge
 dependencies:
-  - python=3.7
-  - scikit-allel=1.2.1
-  - matplotlib=2.2.5
-  - pandas=1.2.1
-  - seaborn=0.11.1
-  - xlsxwriter=1.1.5
-  - xlrd=1.2.0
-  - bcftools=1.11
-  - adjusttext
-  - tqdm
-  - statsmodels
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - adjusttext=0.7.3.1=py_1
+  - alsa-lib=1.2.8=h166bdaf_0
+  - arrow-cpp=10.0.1=h3e2b116_4_cpu
+  - asciitree=0.3.3=py_2
+  - attr=2.5.1=h166bdaf_1
+  - aws-c-auth=0.6.21=hd93a3ba_3
+  - aws-c-cal=0.5.20=hd3b2fe5_3
+  - aws-c-common=0.8.5=h166bdaf_0
+  - aws-c-compression=0.2.16=hf5f93bc_0
+  - aws-c-event-stream=0.2.17=h57874a7_1
+  - aws-c-http=0.7.0=h96ef541_0
+  - aws-c-io=0.13.12=h57ca295_1
+  - aws-c-mqtt=0.7.13=h0b5698f_12
+  - aws-c-s3=0.2.1=h5d7e488_4
+  - aws-c-sdkutils=0.1.7=hf5f93bc_0
+  - aws-checksums=0.1.14=h6027aba_0
+  - aws-crt-cpp=0.18.16=h26430d7_8
+  - aws-sdk-cpp=1.9.379=h56135f1_7
+  - bcftools=1.11=h7c999a4_0
+  - bokeh=3.2.1=pyhd8ed1ab_0
+  - brotli=1.0.9=h166bdaf_9
+  - brotli-bin=1.0.9=h166bdaf_9
+  - brotli-python=1.0.9=py39h5a03fae_9
+  - bzip2=1.0.8=h7f98852_4
+  - c-ares=1.19.1=hd590300_0
+  - ca-certificates=2023.5.7=hbcca054_0
+  - cached-property=1.5.2=hd8ed1ab_1
+  - cached_property=1.5.2=pyha770c72_1
+  - cairo=1.16.0=ha61ee94_1014
+  - certifi=2023.5.7=pyhd8ed1ab_0
+  - charset-normalizer=3.2.0=pyhd8ed1ab_0
+  - click=8.1.6=unix_pyh707e725_0
+  - cloudpickle=2.2.1=pyhd8ed1ab_0
+  - colorama=0.4.6=pyhd8ed1ab_0
+  - contourpy=1.1.0=py39h7633fee_0
+  - cycler=0.11.0=pyhd8ed1ab_0
+  - cytoolz=0.12.0=py39hb9d737c_1
+  - dask=2023.7.1=pyhd8ed1ab_0
+  - dask-core=2023.7.1=pyhd8ed1ab_0
+  - dbus=1.13.6=h5008d03_3
+  - distributed=2023.7.1=pyhd8ed1ab_0
+  - entrypoints=0.4=pyhd8ed1ab_0
+  - expat=2.5.0=hcb278e6_1
+  - fasteners=0.17.3=pyhd8ed1ab_0
+  - fftw=3.3.10=nompi_hc118613_108
+  - font-ttf-dejavu-sans-mono=2.37=hab24e00_0
+  - font-ttf-inconsolata=3.000=h77eed37_0
+  - font-ttf-source-code-pro=2.038=h77eed37_0
+  - font-ttf-ubuntu=0.83=hab24e00_0
+  - fontconfig=2.14.2=h14ed4e7_0
+  - fonts-conda-ecosystem=1=0
+  - fonts-conda-forge=1=0
+  - fonttools=4.41.0=py39hd1e30aa_0
+  - freetype=2.12.1=hca18f0e_1
+  - fsspec=2023.6.0=pyh1a96a4e_0
+  - gettext=0.21.1=h27087fc_0
+  - gflags=2.2.2=he1b5a44_1004
+  - glib=2.76.4=hfc55251_0
+  - glib-tools=2.76.4=hfc55251_0
+  - glog=0.6.0=h6f12383_0
+  - graphite2=1.3.13=h58526e2_1001
+  - gsl=2.6=he838d99_2
+  - gst-plugins-base=1.21.3=h4243ec0_1
+  - gstreamer=1.21.3=h25f0c4b_1
+  - gstreamer-orc=0.4.34=hd590300_0
+  - h5py=3.9.0=nompi_py39h4dfffb9_100
+  - harfbuzz=6.0.0=h8e241bc_0
+  - hdf5=1.14.0=nompi_h5231ba7_103
+  - htslib=1.11=hd3b49d5_2
+  - icu=70.1=h27087fc_0
+  - idna=3.4=pyhd8ed1ab_0
+  - importlib-metadata=6.8.0=pyha770c72_0
+  - importlib-resources=6.0.0=pyhd8ed1ab_1
+  - importlib_metadata=6.8.0=hd8ed1ab_0
+  - importlib_resources=6.0.0=pyhd8ed1ab_1
+  - jack=1.9.22=h11f4161_0
+  - jinja2=3.1.2=pyhd8ed1ab_1
+  - joblib=1.3.0=pyhd8ed1ab_1
+  - jpeg=9e=h0b41bf4_3
+  - keyutils=1.6.1=h166bdaf_0
+  - kiwisolver=1.4.4=py39hf939315_1
+  - krb5=1.20.1=hf9c8cef_0
+  - lame=3.100=h166bdaf_1003
+  - lcms2=2.15=hfd0df8a_0
+  - ld_impl_linux-64=2.40=h41732ed_0
+  - lerc=4.0.0=h27087fc_0
+  - libabseil=20220623.0=cxx17_h05df665_6
+  - libaec=1.0.6=hcb278e6_1
+  - libarrow=10.0.1=hee49ebd_4_cpu
+  - libblas=3.9.0=17_linux64_openblas
+  - libbrotlicommon=1.0.9=h166bdaf_9
+  - libbrotlidec=1.0.9=h166bdaf_9
+  - libbrotlienc=1.0.9=h166bdaf_9
+  - libcap=2.66=ha37c62d_0
+  - libcblas=3.9.0=17_linux64_openblas
+  - libclang=15.0.7=default_h7634d5b_2
+  - libclang13=15.0.7=default_h9986a30_2
+  - libcrc32c=1.1.2=h9c3ff4c_0
+  - libcups=2.3.3=h36d4200_3
+  - libcurl=7.87.0=h6312ad2_0
+  - libdb=6.2.32=h9c3ff4c_0
+  - libdeflate=1.17=h0b41bf4_0
+  - libedit=3.1.20191231=he28a2e2_2
+  - libev=4.33=h516909a_1
+  - libevent=2.1.10=h9b69904_4
+  - libexpat=2.5.0=hcb278e6_1
+  - libffi=3.4.2=h7f98852_5
+  - libflac=1.4.3=h59595ed_0
+  - libgcc-ng=13.1.0=he5830b7_0
+  - libgcrypt=1.10.1=h166bdaf_0
+  - libgfortran-ng=13.1.0=h69a702a_0
+  - libgfortran5=13.1.0=h15d22d2_0
+  - libglib=2.76.4=hebfc3b9_0
+  - libgomp=13.1.0=he5830b7_0
+  - libgoogle-cloud=2.5.0=h5d50b59_1
+  - libgpg-error=1.47=h71f35ed_0
+  - libgrpc=1.51.1=h05bd8bd_0
+  - libiconv=1.17=h166bdaf_0
+  - liblapack=3.9.0=17_linux64_openblas
+  - libllvm15=15.0.7=hadd5161_1
+  - libnghttp2=1.51.0=hdcd2b5c_0
+  - libnsl=2.0.0=h7f98852_0
+  - libogg=1.3.4=h7f98852_1
+  - libopenblas=0.3.23=pthreads_h80387f5_0
+  - libopus=1.3.1=h7f98852_1
+  - libpng=1.6.39=h753d276_0
+  - libpq=15.1=h2baec63_3
+  - libprotobuf=3.21.12=h3eb15da_0
+  - libsndfile=1.2.0=hb75c966_0
+  - libsqlite=3.42.0=h2797004_0
+  - libssh2=1.10.0=haa6b8db_3
+  - libstdcxx-ng=13.1.0=hfd8a6a1_0
+  - libsystemd0=252=h2a991cd_0
+  - libthrift=0.16.0=h491838f_2
+  - libtiff=4.5.0=h6adf6a1_2
+  - libtool=2.4.7=h27087fc_0
+  - libudev1=253=h0b41bf4_0
+  - libutf8proc=2.8.0=h166bdaf_0
+  - libuuid=2.38.1=h0b41bf4_0
+  - libvorbis=1.3.7=h9c3ff4c_0
+  - libwebp-base=1.3.1=hd590300_0
+  - libxcb=1.13=h7f98852_1004
+  - libxkbcommon=1.5.0=h79f4944_1
+  - libxml2=2.10.3=hca2bb57_4
+  - libzlib=1.2.13=hd590300_5
+  - locket=1.0.0=pyhd8ed1ab_0
+  - lz4=4.3.2=py39h724f13c_0
+  - lz4-c=1.9.4=hcb278e6_0
+  - markupsafe=2.1.3=py39hd1e30aa_0
+  - matplotlib=3.7.2=py39hf3d152e_0
+  - matplotlib-base=3.7.2=py39h0126182_0
+  - mpg123=1.31.3=hcb278e6_0
+  - msgpack-python=1.0.5=py39h4b4f3f3_0
+  - munkres=1.1.4=pyh9f0ad1d_0
+  - mysql-common=8.0.32=h14678bc_0
+  - mysql-libs=8.0.32=h54cf53e_0
+  - ncurses=6.4=hcb278e6_0
+  - networkx=3.1=pyhd8ed1ab_0
+  - nomkl=1.0=h5ca1d4c_0
+  - nspr=4.35=h27087fc_0
+  - nss=3.89=he45b914_0
+  - numcodecs=0.11.0=py39h227be39_1
+  - numexpr=2.8.4=py39h5ef5dce_100
+  - numpy=1.25.1=py39h6183b62_0
+  - openjpeg=2.5.0=hfec8fc6_2
+  - openssl=1.1.1u=hd590300_0
+  - orc=1.8.2=hfdbbad2_2
+  - packaging=23.1=pyhd8ed1ab_0
+  - pandas=2.0.3=py39h40cae4c_1
+  - parquet-cpp=1.5.1=2
+  - partd=1.4.0=pyhd8ed1ab_0
+  - patsy=0.5.3=pyhd8ed1ab_0
+  - pcre2=10.40=hc3806b6_0
+  - perl=5.32.1=4_hd590300_perl5
+  - pillow=9.4.0=py39h2320bf1_1
+  - pip=23.2=pyhd8ed1ab_0
+  - pixman=0.40.0=h36c2ea0_0
+  - platformdirs=3.9.1=pyhd8ed1ab_0
+  - ply=3.11=py_1
+  - pomegranate=0.14.8=py39h7c9e3ff_0
+  - pooch=1.7.0=pyha770c72_3
+  - psutil=5.9.5=py39h72bdee0_0
+  - pthread-stubs=0.4=h36c2ea0_1001
+  - pulseaudio=16.1=h4ab2085_1
+  - pyarrow=10.0.1=py39hacc6ce7_4_cpu
+  - pyparsing=3.0.9=pyhd8ed1ab_0
+  - pyqt=5.15.7=py39h5c7b992_3
+  - pyqt5-sip=12.11.0=py39h227be39_3
+  - pysocks=1.7.1=pyha2e5f31_6
+  - python=3.9.15=h47a2c10_0_cpython
+  - python-dateutil=2.8.2=pyhd8ed1ab_0
+  - python-tzdata=2023.3=pyhd8ed1ab_0
+  - python_abi=3.9=3_cp39
+  - pytz=2023.3=pyhd8ed1ab_0
+  - pyyaml=6.0=py39hb9d737c_5
+  - qt-main=5.15.6=h18908ee_6
+  - re2=2022.06.01=h27087fc_1
+  - readline=8.2=h8228510_1
+  - requests=2.31.0=pyhd8ed1ab_0
+  - s2n=1.3.31=hae46d1a_0
+  - scikit-allel=1.3.6=py39h40cae4c_0
+  - scikit-learn=1.3.0=py39hc236052_0
+  - scipy=1.11.1=py39h6183b62_0
+  - seaborn=0.12.2=hd8ed1ab_0
+  - seaborn-base=0.12.2=pyhd8ed1ab_0
+  - setuptools=68.0.0=pyhd8ed1ab_0
+  - sip=6.7.9=py39h3d6467e_0
+  - six=1.16.0=pyh6c4a22f_0
+  - snappy=1.1.10=h9fff704_0
+  - sortedcontainers=2.4.0=pyhd8ed1ab_0
+  - statsmodels=0.14.0=py39h0f8d45d_1
+  - tblib=1.7.0=pyhd8ed1ab_0
+  - threadpoolctl=3.2.0=pyha21a80b_0
+  - tk=8.6.12=h27826a3_0
+  - toml=0.10.2=pyhd8ed1ab_0
+  - tomli=2.0.1=pyhd8ed1ab_0
+  - toolz=0.12.0=pyhd8ed1ab_0
+  - tornado=6.3.2=py39hd1e30aa_0
+  - tqdm=4.65.0=pyhd8ed1ab_1
+  - typing-extensions=4.7.1=hd8ed1ab_0
+  - typing_extensions=4.7.1=pyha770c72_0
+  - tzdata=2023c=h71feb2d_0
+  - unicodedata2=15.0.0=py39hb9d737c_0
+  - urllib3=2.0.4=pyhd8ed1ab_0
+  - wheel=0.40.0=pyhd8ed1ab_1
+  - xcb-util=0.4.0=h516909a_0
+  - xcb-util-image=0.4.0=h166bdaf_0
+  - xcb-util-keysyms=0.4.0=h516909a_0
+  - xcb-util-renderutil=0.3.9=h166bdaf_0
+  - xcb-util-wm=0.4.1=h516909a_0
+  - xkeyboard-config=2.38=h0b41bf4_0
+  - xlrd=1.2.0=pyh9f0ad1d_1
+  - xlsxwriter=3.1.2=pyhd8ed1ab_0
+  - xorg-kbproto=1.0.7=h7f98852_1002
+  - xorg-libice=1.1.1=hd590300_0
+  - xorg-libsm=1.2.4=h7391055_0
+  - xorg-libx11=1.8.4=h0b41bf4_0
+  - xorg-libxau=1.0.11=hd590300_0
+  - xorg-libxdmcp=1.1.3=h7f98852_0
+  - xorg-libxext=1.3.4=h0b41bf4_2
+  - xorg-libxrender=0.9.10=h7f98852_1003
+  - xorg-renderproto=0.11.1=h7f98852_1002
+  - xorg-xextproto=7.3.0=h0b41bf4_1003
+  - xorg-xproto=7.0.31=h7f98852_1007
+  - xyzservices=2023.7.0=pyhd8ed1ab_0
+  - xz=5.2.6=h166bdaf_0
+  - yaml=0.2.5=h7f98852_2
+  - zarr=2.15.0=pyhd8ed1ab_1
+  - zict=3.0.0=pyhd8ed1ab_0
+  - zipp=3.16.2=pyhd8ed1ab_0
+  - zlib=1.2.13=hd590300_5
+  - zstd=1.5.2=hfc55251_7
+prefix: /home/sanj/projects/IR/rna-seq-busia/.test/.snakemake/conda/05a9e65ff79282deacacf9adbc9a0eb2_