0.6.1 release

conda_pkg/README.md

@@ -0,0 +1,57 @@
+### Installation of CPSR using Conda
+
+This is an alternative installation approach that does not require Docker on your machine. At the moment it works only for Linux systems.
+
+A prerequisite is that you have Conda installed. First download the Conda package manager. Get it with:
+
+```
+wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh
+bash miniconda.sh -b -p ./miniconda
+```
+
+Run the following to add Conda into your PATH. You can even put that into your `~/.bashrc` or `~/.zshrc` to avoid re-running this in the future:
+
+```
+. ./miniconda/etc/profile.d/conda.sh
+```
+
+#### Alternative 1
+Create a new environment (`-n cpsr`), install the _cpsr_ Conda package directly from Anaconda Cloud:
+
+```
+conda create -n cpsr -c conda-forge -c bioconda -c pcgr cpsr
+
+```
+
+#### Alternative 2
+Build the _cpsr_ package from source, which is useful if you need to use the development code from the repository:
+
+```
+conda install conda-build
+export CHANNELS="-c conda-forge -c bioconda -c pcgr -c defaults"
+conda build $CHANNELS conda_pkg/cpsr
+conda install --use-local $CHANNELS cpsr
+```
+
+For both alternatives you also need to download the reference data bundle for your genome build:
+
+```
+wget http://insilico.hpc.uio.no/pcgr/pcgr.databundle.20201123.grch37.tar.gz -O grch37.tar.gz
+wget http://insilico.hpc.uio.no/pcgr/pcgr.databundle.20201123.grch38.tar.gz -O grch38.tar.gz
+tar -xzf grch37.tar.gz  # will extract into ./data/grch37/
+tar -xzf grch38.tar.gz  # will extract into ./data/grch38/
+```
+
+There is a chance you'll encounter errors during the installation. Due to ongoing updates of the packages in public repositories, some packages might end up conflicting with each other or missing for your system. So try to stick to the dockerized version of CPSR whenever possible.
+
+### Running condarized CPSR
+
+Activate your environment with:
+
+```
+conda activate cpsr
+```
+
+Run CPSR with `--no-docker` flag. The `--pcgr_dir` argument now doesn't have to contain anything but a `data` directory that you downloaded.
+
+If you encounter errors with VEP, you may need to unset/reset PERL5LIB (e.g. `export PERL5LIB=""`), see the [following issue](https://github.com/bioconda/bioconda-recipes/issues/4390)

cpsr.py

@@ -12,9 +12,9 @@
 import toml
 from argparse import RawTextHelpFormatter
 
-PCGR_VERSION = 'dev'
-CPSR_VERSION = '0.6.0rc'
-DB_VERSION = 'PCGR_DB_VERSION = 20200920'
+PCGR_VERSION = '0.9.1'
+CPSR_VERSION = '0.6.1'
+DB_VERSION = 'PCGR_DB_VERSION = 20201123'
 VEP_VERSION = '101'
 GENCODE_VERSION = '35'
 VEP_ASSEMBLY = 'GRCh38'
@@ -24,7 +24,7 @@
 #global VEP_ASSEMBLY
 
 GE_panels = {
-		0: "CPSR exploratory cancer predisposition panel (n = 216, TCGA + Cancer Gene Census + NCGC + Other)",
+		0: "CPSR exploratory cancer predisposition panel (n = 335, Genomics England PanelApp / TCGA Germline Study / Cancer Gene Census / Other)",
       1: "Adult solid tumours cancer susceptibility (Genomics England PanelApp)",
       2: "Adult solid tumours for rare disease (Genomics England PanelApp)",
       3: "Bladder cancer pertinent cancer susceptibility (Genomics England PanelApp)",
@@ -72,7 +72,7 @@
 
 def __main__():
 
-   panels = "0 = CPSR exploratory cancer predisposition panel (n = 216, TCGA + Cancer Gene Census + NCGC + Other)\n"
+   panels = "0 = CPSR exploratory cancer predisposition panel (n = 335, Genomics England PanelApp / TCGA Germline Study / Cancer Gene Census / Other)\n"
    panels = panels + "1 = Adult solid tumours cancer susceptibility (Genomics England PanelApp)\n"
    panels = panels + "2 = Adult solid tumours for rare disease (Genomics England PanelApp)\n"
    panels = panels + "3 = Bladder cancer pertinent cancer susceptibility (Genomics England PanelApp)\n"
@@ -137,9 +137,10 @@ def __main__():
    optional.add_argument('--docker-uid', dest='docker_user_id', help='Docker user ID. Default is the host system user ID. If you are experiencing permission errors,\n try setting this up to root (`--docker-uid root`), default: %(default)s')
    optional.add_argument('--no-docker', action='store_true', dest='no_docker', default=False, help='Run the CPSR workflow in a non-Docker mode, default: %(default)s')
    optional.add_argument('--ignore_noncoding', action='store_true',dest='ignore_noncoding',default=False,help='Do not list non-coding variants in HTML report')
-   optional.add_argument('--incidental_findings', action='store_true',dest='incidental_findings',default=False, help='Include variants found in ACMG-recommended list for incidental findings (v2.0)')
+   optional.add_argument('--secondary_findings', action='store_true',dest='secondary_findings',default=False, help='Include variants found in ACMG-recommended list for secondary findings (v2.0)')
    optional.add_argument('--gwas_findings', action='store_true',dest='gwas_findings',default=False, help='Report overlap with low to moderate cancer risk variants (tag SNPs) identified from genome-wide association studies')
    optional.add_argument('--classify_all', action='store_true',dest='classify_all',help='Provide CPSR variant classifications (TIER 1-5) also for variants with exising ClinVar classifications in output TSV')
+   optional.add_argument('--clinvar_ignore_noncancer', action='store_true', help='Ignore (exclude from report) ClinVar-classified variants reported only for phenotypes/conditions NOT related to cancer')
    optional.add_argument('--maf_upper_threshold', type=float, default = 0.9, dest = 'maf_upper_threshold',help='Upper MAF limit (gnomAD global population frequency) for variants to be included in the report, default: %(default)s')
    optional.add_argument('--debug',action='store_true',default=False, help='Print full docker commands to log, default: %(default)s')
    required.add_argument('--query_vcf', help='VCF input file with germline query variants (SNVs/InDels).', required = True)
@@ -471,21 +472,24 @@ def run_cpsr(arg_dict, host_directories, config_options):
    virtual_panel_id = -1
    ignore_noncoding = 0
    gwas_findings = 0
-   incidental_findings = 0
+   secondary_findings = 0
    classify_all = 0
+   clinvar_ignore_noncancer = 0
 
    diagnostic_grade_set = "OFF"
-   incidental_findings_set = "OFF"
+   secondary_findings_set = "OFF"
    gwas_findings_set = "OFF"
 
+   if arg_dict['clinvar_ignore_noncancer']:
+      clinvar_ignore_noncancer = 1
    if arg_dict['classify_all']:
       classify_all = 1
    if arg_dict['gwas_findings']:
       gwas_findings = 1
       gwas_findings_set = "ON"
-   if arg_dict['incidental_findings']:
-      incidental_findings = 1
-      incidental_findings_set = "ON"
+   if arg_dict['secondary_findings']:
+      secondary_findings = 1
+      secondary_findings_set = "ON"
    if arg_dict['diagnostic_grade_only']:
       diagnostic_grade_only = 1
       diagnostic_grade_set = "ON"
@@ -607,7 +611,7 @@ def run_cpsr(arg_dict, host_directories, config_options):
    else:
       logger.info("Virtual gene panel: " + str(GE_panels[virtual_panel_id]))
       logger.info("Diagnostic-grade genes in virtual panels (GE PanelApp): " + str(diagnostic_grade_set))
-   logger.info("Include incidential findings (ACMG recommended list v2.0): " + str(incidental_findings_set))
+   logger.info("Include incidential findings (ACMG recommended list v2.0): " + str(secondary_findings_set))
    logger.info("Include low to moderate cancer risk variants from genome-wide association studies: " + str(gwas_findings_set))
    logger.info("Reference population, germline variant frequencies (gnomAD): " + str(config_options['popgen']['pop_gnomad']).upper())
    logger.info("Genome assembly: " + str(arg_dict['genome_assembly']))
@@ -725,7 +729,7 @@ def run_cpsr(arg_dict, host_directories, config_options):
          str(PCGR_VERSION) + " " + str(CPSR_VERSION) + " " + str(arg_dict['genome_assembly']) + " " + \
          str(virtual_panel_id) + " " + str(custom_bed) + " " + str(arg_dict['maf_upper_threshold']) + " " + \
          str(diagnostic_grade_only) + " " + data_dir + " " + str(ignore_noncoding) + " " + \
-         str(incidental_findings) + " " + str(gwas_findings) + " " + str(classify_all) + docker_command_run_end)
+         str(clinvar_ignore_noncancer) + " " + str(secondary_findings) + " " + str(gwas_findings) + " " + str(classify_all) + docker_command_run_end)
       check_subprocess(logger, cpsr_report_command)
       logger.info("Finished")
 

docs/CHANGELOG.md

@@ -1,6 +1,25 @@
 
 ## CHANGELOG
 
+#### 0.6.1 - November 30th 2020
+
+##### Added
+
+ - Increased number of genes in panel 0: All genes in 42 virtual panels related to cancer conditions in Genomics England PanelApp now also contributes toward panel 0
+ - Added option in main script (`--clinvar_ignore_noncancer`) that will exclude any query variants (from HTML report and TSV/JSON output) that have been reported and classified for non-cancer related conditions only (in ClinVar)
+	 - this to exclude variants associated with non-cancer related phenotypes
+ - For the variant biomarker table, the resolution of the reported biomarker mapping is highlighted with designated background colors for the gene (exact/codon - black vs. exon/gene - orange)
+
+##### Fixed
+ - Bug in GWAS hits retrieval, [Issue #30](https://github.com/sigven/cpsr/issues/18)
+ - Custom VCF tags (as specified by user in configuration file) not shown in output TSV files
+
+##### Changed
+ - Removed DisGeNET annotations from output (associations from Open Targets Platform serve same purpose)
+ - Renamed report section __Genomic Biomarkers__ to __Variant Biomarkers__
+ - Option `--incidental_findings` changed back to `--secondary_findings` - recommended term to use according to ACMG
+ - Removed _MOD (mechanism-of-disease)_ from TSV output file
+
 #### 0.6.0rc - September 24th 2020
 
 - Data updates: ClinVar, GWAS catalog, GENCODE, CIViC, CancerMine, UniProt KB, dbNSFP, Pfam, KEGG, Open Targets Platform, Genomics England PanelApp

docs/CHANGELOG.rst

@@ -1,30 +1,78 @@
 CHANGELOG
 ---------
 
-0.6.0 - September 23rd 2020
-^^^^^^^^^^^^^^^^^^^^^^^^^^^
+0.6.1 - November 30th 2020
+^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Added
+'''''
+
+-  Increased number of genes in panel 0: All genes in 42 virtual panels
+   related to cancer conditions in Genomics England PanelApp now also
+   contributes toward panel 0
+-  Added option in main script (``--clinvar_ignore_noncancer``) that
+   will exclude any query variants (from HTML report and TSV/JSON
+   output) that have been reported and classified for non-cancer related
+   conditions only (in ClinVar)
+
+   -  this to exclude variants associated with non-cancer related
+      phenotypes
+
+-  For the variant biomarker table, the resolution of the reported
+   biomarker mapping is highlighted with designated background colors
+   for the gene (exact/codon - black vs. exon/gene - orange)
+
+Fixed
+'''''
+
+-  Bug in GWAS hits retrieval, `Issue
+   #30 <https://github.com/sigven/cpsr/issues/18>`__
+-  Custom VCF tags (as specified by user in configuration file) not
+   shown in output TSV files
+
+Changed
+'''''''
+
+-  Removed DisGeNET annotations from output (associations from Open
+   Targets Platform serve same purpose)
+-  Renamed report section **Genomic Biomarkers** to **Variant
+   Biomarkers**
+-  Option ``--incidental_findings`` changed back to
+   ``--secondary_findings`` - recommended term to use according to ACMG
+-  Removed *MOD (mechanism-of-disease)* from TSV output file
+
+0.6.0rc - September 24th 2020
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+-  Data updates: ClinVar, GWAS catalog, GENCODE, CIViC, CancerMine,
+   UniProt KB, dbNSFP, Pfam, KEGG, Open Targets Platform, Genomics
+   England PanelApp
+-  Software updates: VEP 101
+
+.. _fixed-1:
 
 Fixed
 '''''
 
 -  Duplicated entries in incidental findings
 
+.. _changed-1:
+
 Changed
 '''''''
 
--  All arguments to ``cpsr.py`` is now organized with a ``--`` (no
-   positional arguments)
+-  All arguments to ``cpsr.py`` are now non-positional
 -  Arguments to ``cpsr.py`` are divided into two groups: *required* and
    *optional*
 -  ``secondary_findings`` is now coined ``incidental_findings``
--  Option **gwas:gwas_hits** in CPSR configuration file is now option
-   ``--gwas_findings`` in ``cpsr.py``
+-  Option **gwas:gwas_hits** in CPSR configuration file is now optional
+   argument ``--gwas_findings`` in ``cpsr.py``
 -  Option **classification:clinvar_cpsr** in CPSR configuration file is
-   now option ``--classify_all`` in ``cpsr.py``
+   now optional argument ``--classify_all`` in ``cpsr.py``
 -  Option **maf_imits:maf_gnomad** in CPSR configuration file is now
-   option ``--maf_upper_threshold`` in ``cpsr.py``
+   optional argument ``--maf_upper_threshold`` in ``cpsr.py``
 -  Option **secondary_findings:show_sf** in CPSR configuration file is
-   now option ``--incidental_findings`` in ``cpsr.py``
+   now optional argument ``--incidental_findings`` in ``cpsr.py``
 -  Virtual panels is now displayed through HTML (previously static
    ggplot plot)
 -  **Settings** section of report is now divived into three:
@@ -33,13 +81,19 @@ Changed
    -  Report configuration
    -  Virtual panel
 
+-  Classifications of genes as tumor suppressors/oncogenes are now based
+   on a combination of CancerMine citation count and presence in Network
+   of Cancer Genes
+
+.. _added-1:
+
 Added
 '''''
 
--  Missing ACMG criteria for classification of silent and intronic
-   variants outside of splice regions (ACMG_BP7)
+-  Missing ACMG criterion for classification of silent and intronic
+   variants outside of splice regions (*ACMG_BP7*)
 -  Missing ACMG criterion for classification of variants in promoter and
-   untranslated regions (ACMG_BP3)
+   untranslated regions (*ACMG_BP3*)
 -  Possibility to create custom virtual panel - any combination of genes
    from panel 0 provided as a single-column text file with argument
    ``--custom_list``
@@ -52,7 +106,7 @@ Added
 0.5.2 - November 18th 2019
 ^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-.. _changed-1:
+.. _changed-2:
 
 Changed
 '''''''
@@ -63,7 +117,7 @@ Changed
 -  Moved virtual panel identifier from positional argument to optional
    argument (``--panel_id``) in ``cpsr.py``
 
-.. _added-1:
+.. _added-2:
 
 Added
 '''''
@@ -75,7 +129,7 @@ Added
 0.5.1 - October 14th 2019
 ^^^^^^^^^^^^^^^^^^^^^^^^^
 
-.. _fixed-1:
+.. _fixed-2:
 
 Fixed
 '''''
@@ -88,7 +142,7 @@ Fixed
 0.5.0 - September 23rd 2019
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-.. _fixed-2:
+.. _fixed-3:
 
 Fixed
 '''''
@@ -105,7 +159,7 @@ Fixed
 -  Handling of non-coding variants (synonymous, upstream_variants) in
    the report, no longer excluded
 
-.. _added-2:
+.. _added-3:
 
 Added
 '''''

docs/_build/html/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 430fd7bd5058a69516f266833495f846
+config: 8e9d3f30cf8d8e2799e0ca09ed367f82
 tags: 645f666f9bcd5a90fca523b33c5a78b7