Merge pull request #2 from ctglab/UCL

This PR introduces the gencode notation

.gitignore

@@ -12,3 +12,4 @@ ENEO_output/
 genome_index/
 temp_gatk/
 *pycache*
+test_res/

.test/config/config.yaml

@@ -105,7 +105,7 @@ resources:
   gtf: "test_data/chr6_105.gtf"
   hla_script: ../workflow/scripts/HLA_typing.py
   indel: "test_data/indels_chr6.vcf.gz"
-  intervals_coding: ../workflow/supplementary_res/intervals_coding.BED.gz
+  intervals_coding: test_data/exons_target.BED.gz
   REDI: "test_data/REDI_chr6.BED.gz"
   t1k_file: ../workflow/supplementary_res/hlaidx_rna_seq.fa
   toml_script: ../workflow/scripts/createTOML.py

setup/resources.json

@@ -17,19 +17,19 @@
     },
     "REDI": {
         "filetype": "table",
-        "url": "http://srv00.recas.ba.infn.it/webshare/ATLAS/donwload/TABLE1_hg38.txt.gz" 
+        "url": "http://srv00.recas.ba.infn.it/webshare/ATLAS/download/TABLE1_hg38_v3.txt.gz" 
     },
     "genome": {
         "filetype": "fasta",
-        "url": "https://ftp.ensembl.org/pub/release-105/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz" 
+        "url": "https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_47/GRCh38.p14.genome.fa.gz" 
     },
     "transcriptome": {
         "filetype": "fasta",
-        "url": "https://ftp.ensembl.org/pub/current/fasta/homo_sapiens/cdna/Homo_sapiens.GRCh38.cdna.all.fa.gz"
+        "url": "https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_47/gencode.v47.transcripts.fa.gz"
     },
     "gtf": {
         "filetype": "gtf",
-        "url": "https://ftp.ensembl.org/pub/release-105/gtf/homo_sapiens/Homo_sapiens.GRCh38.105.gtf.gz" 
+        "url": "https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_47/gencode.v47.primary_assembly.annotation.gtf.gz" 
     },
     "vep_cache": {
         "filetype": "archive",

setup/setup_env.yml

@@ -0,0 +1,108 @@
+name: eneo_setup
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - alsa-lib=1.2.12=h4ab18f5_0
+  - bcftools=1.21=h8b25389_0
+  - bedtools=2.31.1=hf5e1c6e_2
+  - bzip2=1.0.8=h4bc722e_7
+  - c-ares=1.34.2=heb4867d_0
+  - ca-certificates=2024.8.30=hbcca054_0
+  - cairo=1.18.0=hebfffa5_3
+  - expat=2.6.3=h5888daf_0
+  - 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=h77eed37_3
+  - fontconfig=2.14.2=h14ed4e7_0
+  - fonts-conda-ecosystem=1=0
+  - fonts-conda-forge=1=0
+  - freetype=2.12.1=h267a509_2
+  - gatk4=4.5.0.0=py36hdfd78af_0
+  - giflib=5.2.2=hd590300_0
+  - graphite2=1.3.13=h59595ed_1003
+  - gsl=2.7=he838d99_0
+  - harfbuzz=9.0.0=hda332d3_1
+  - htslib=1.21=h5efdd21_0
+  - icu=75.1=he02047a_0
+  - keyutils=1.6.1=h166bdaf_0
+  - krb5=1.21.3=h659f571_0
+  - lcms2=2.16=hb7c19ff_0
+  - ld_impl_linux-64=2.43=h712a8e2_2
+  - lerc=4.0.0=h27087fc_0
+  - libblas=3.9.0=25_linux64_openblas
+  - libcblas=3.9.0=25_linux64_openblas
+  - libcups=2.3.3=h4637d8d_4
+  - libcurl=8.10.1=hbbe4b11_0
+  - libdeflate=1.21=h4bc722e_0
+  - libedit=3.1.20191231=he28a2e2_2
+  - libev=4.33=hd590300_2
+  - libexpat=2.6.3=h5888daf_0
+  - libffi=3.4.2=h7f98852_5
+  - libgcc=14.2.0=h77fa898_1
+  - libgcc-ng=14.2.0=h69a702a_1
+  - libgfortran=14.2.0=h69a702a_1
+  - libgfortran-ng=14.2.0=h69a702a_1
+  - libgfortran5=14.2.0=hd5240d6_1
+  - libglib=2.82.2=h2ff4ddf_0
+  - libgomp=14.2.0=h77fa898_1
+  - libiconv=1.17=hd590300_2
+  - libjpeg-turbo=3.0.0=hd590300_1
+  - libmpdec=4.0.0=h4bc722e_0
+  - libnghttp2=1.64.0=h161d5f1_0
+  - libopenblas=0.3.28=pthreads_h94d23a6_0
+  - libpng=1.6.44=hadc24fc_0
+  - libsqlite=3.47.0=hadc24fc_0
+  - libssh2=1.11.0=h0841786_0
+  - libstdcxx=14.2.0=hc0a3c3a_1
+  - libstdcxx-ng=14.2.0=h4852527_1
+  - libtiff=4.7.0=h6565414_0
+  - libuuid=2.38.1=h0b41bf4_0
+  - libwebp-base=1.4.0=hd590300_0
+  - libxcb=1.17.0=h8a09558_0
+  - libxcrypt=4.4.36=hd590300_1
+  - libzlib=1.3.1=hb9d3cd8_2
+  - ncurses=6.5=he02047a_1
+  - openjdk=17.0.13=he018374_0
+  - openssl=3.3.2=hb9d3cd8_0
+  - pcre2=10.44=hba22ea6_2
+  - perl=5.32.1=7_hd590300_perl5
+  - pip=24.2=pyh145f28c_1
+  - pixman=0.43.2=h59595ed_0
+  - pthread-stubs=0.4=hb9d3cd8_1002
+  - python=3.13.0=h9ebbce0_100_cp313
+  - python_abi=3.13=5_cp313
+  - readline=8.2=h8228510_1
+  - tabix=1.11=hdfd78af_0
+  - tk=8.6.13=noxft_h4845f30_101
+  - xorg-libice=1.1.1=hb9d3cd8_1
+  - xorg-libsm=1.2.4=he73a12e_1
+  - xorg-libx11=1.8.10=h4f16b4b_0
+  - xorg-libxau=1.0.11=hb9d3cd8_1
+  - xorg-libxdmcp=1.1.5=hb9d3cd8_0
+  - xorg-libxext=1.3.6=hb9d3cd8_0
+  - xorg-libxfixes=6.0.1=hb9d3cd8_0
+  - xorg-libxi=1.8.2=hb9d3cd8_0
+  - xorg-libxrandr=1.5.4=hb9d3cd8_0
+  - xorg-libxrender=0.9.11=hb9d3cd8_1
+  - xorg-libxt=1.3.0=hb9d3cd8_2
+  - xorg-libxtst=1.2.5=hb9d3cd8_3
+  - xorg-xorgproto=2024.1=hb9d3cd8_1
+  - xz=5.2.6=h166bdaf_0
+  - zlib=1.3.1=hb9d3cd8_2
+  - zstd=1.5.6=ha6fb4c9_0
+  - pip:
+    - click==8.1.7
+    - coloredlogs==15.0.1
+    - cyvcf2==0.31.1
+    - humanfriendly==10.0
+    - numpy==2.1.2
+    - pandas==2.2.3
+    - python-dateutil==2.9.0.post0
+    - pytz==2024.2
+    - pyyaml==6.0.2
+    - six==1.16.0
+    - tzdata==2024.2

workflow/profile/sge_profile/config.yaml

@@ -0,0 +1,21 @@
+cluster:
+  mkdir -p sge-logs/{rule} &&
+  qsub
+    -pe smp {resources.ncpus}
+    -l mem_free={resources.mem}
+    -l h_rt={resources.time}
+    -N smk-{rule}-{wildcards}
+    -o sge-logs/{rule}/{rule}-{wildcards}-$JOB_ID.out
+    -e sge-logs/{rule}/{rule}-{wildcards}-$JOB_ID.err
+    -q all.q
+default-resources:
+  - mem="8G"
+  - time="01:30:00"
+  - ntasks=1
+local-cores: 1
+latency-wait: 60
+jobs: 500
+keep-going: True
+rerun-incomplete: True
+printshellcmds: True
+scheduler: greedy