Pseudo-PR: First release review!

.travis.yml

@@ -23,10 +23,15 @@ install:
   - sudo ln -s /tmp/nextflow/nextflow /usr/local/bin/nextflow
   # Install nf-core/tools
   - pip install nf-core
-  # Reset
+  # Reset 
   - mkdir ${TRAVIS_BUILD_DIR}/tests && cd ${TRAVIS_BUILD_DIR}
 
 script:
+  # Create and download test data
+  - |
+    touch tests/genome.fa tests/genes.gtf
+    wget http://github.com/nf-core/test-datasets/raw/rnafusion/testdata/human/reads_1.fq.gz -O tests/reads_1.fq.gz
+    wget http://github.com/nf-core/test-datasets/raw/rnafusion/testdata/human/reads_2.fq.gz -O tests/reads_2.fq.gz
   # Lint the pipeline code
   - nf-core lint ${TRAVIS_BUILD_DIR}
-  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --genome GRCh38
+  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker

Dockerfile

@@ -2,8 +2,24 @@
 FROM nfcore/base
 
 LABEL authors="rickard.hammaren@scilifelab.se, phil.ewels@scilifelab.se, martin.proks@scilifelab.se" \
-    description="Docker image containing all requirements for NGI-RNAfusion pipeline"
+    description="Docker image containing all requirements for nfcore/rnafusion pipeline"
 
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
-ENV PATH /opt/conda/envs/nf-core-rnafusion-1.0/bin:$PATH
+ENV PATH /opt/conda/envs/nf-core-rnafusion-1.0/bin:$PATH
+
+WORKDIR /script-db
+# Download FusionGDB
+RUN apt-get update && apt-get install -y wget \
+    && wget --no-check-certificate https://ccsm.uth.edu/FusionGDB/tables/TCGA_ChiTaRS_combined_fusion_information_on_hg19.txt -O TCGA_ChiTaRS_combined_fusion_information_on_hg19.txt \
+    && wget --no-check-certificate https://ccsm.uth.edu/FusionGDB/tables/TCGA_ChiTaRS_combined_fusion_ORF_analyzed_gencode_h19v19.txt -O TCGA_ChiTaRS_combined_fusion_ORF_analyzed_gencode_h19v19.txt \
+    && wget --no-check-certificate https://ccsm.uth.edu/FusionGDB/tables/uniprot_gsymbol.txt -O uniprot_gsymbol.txt \
+    && wget --no-check-certificate https://ccsm.uth.edu/FusionGDB/tables/fusion_uniprot_related_drugs.txt -O fusion_uniprot_related_drugs.txt \
+    && wget --no-check-certificate https://ccsm.uth.edu/FusionGDB/tables/fusion_ppi.txt -O fusion_ppi.txt \
+    && wget --no-check-certificate https://ccsm.uth.edu/FusionGDB/tables/fgene_disease_associations.txt -O fgene_disease_associations.txt \
+    && ln -s /opt/conda/envs/nf-core-rnafusion-1.0/bin/python3 /bin/python3
+
+COPY ./FusionGDB.sql .
+RUN sqlite3 fusions.db < FusionGDB.sql
+
+WORKDIR /

README.md

@@ -8,33 +8,48 @@
 ![Singularity Container available](
 https://img.shields.io/badge/singularity-available-7E4C74.svg)
 
-### Introduction
-
 **nfcore/rnafusion** uses RNA-seq data to detect fusions genes.
 
-The workflow processes raw single-read (limited tools available) or paired-end data from FastQ input ([FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)), detect fusion genes ([STAR-Fusion](https://github.com/STAR-Fusion/STAR-Fusion), [Fusioncatcher](https://github.com/ndaniel/fusioncatcher), [Ericscript](https://sites.google.com/site/bioericscript/), [Pizzly](https://github.com/pmelsted/pizzly), [Squid](https://github.com/Kingsford-Group/squid)), visualizes the fusions ([FusionInspector](https://github.com/FusionInspector/FusionInspector)), performs quality-control on the results ([MultiQC](http://multiqc.info)) and finally generates custom summary report.
+The workflow processes RNA-sequencing data from FastQ files. It runs quality control on the raw data ([FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)), detects fusion genes ([STAR-Fusion](https://github.com/STAR-Fusion/STAR-Fusion), [Fusioncatcher](https://github.com/ndaniel/fusioncatcher), [Ericscript](https://sites.google.com/site/bioericscript/), [Pizzly](https://github.com/pmelsted/pizzly), [Squid](https://github.com/Kingsford-Group/squid)), gathers information ([FusionGDB](https://ccsm.uth.edu/FusionGDB/index.html)), visualizes the fusions ([FusionInspector](https://github.com/FusionInspector/FusionInspector)), performs quality-control on the results ([MultiQC](http://multiqc.info)) and finally generates custom summary report.
+
+![Final summary report](docs/images/example-summary-report.png)
 
-**Note: Make sure to read the installation guide before running the pipeline.**
+The pipeline works with both single-end and paired-end data, though not all fusion detection tools work with single-end data (Ericscript, Pizzly, Squid and FusionInspector).
 
 The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It comes with docker / singularity containers making installation trivial and results highly reproducible.
 
+| Tool            | Single-end reads | CPU (recommended) | RAM (recommended) |
+| --------------- |:----------------:|:-----------------:|:-----------------:|
+| [Star-Fusion](https://github.com/STAR-Fusion/STAR-Fusion/wiki) | Yes              | >=16 cores        | ~30GB             |
+| [Fusioncatcher](https://github.com/ndaniel/fusioncatcher/blob/master/doc/manual.md) | Yes              | >=16 cores        | ~60GB             |
+| [Ericscript](https://sites.google.com/site/bioericscript/getting-started) | **No**           | >=16 cores        | ~30GB             |
+| [Pizzly](https://github.com/pmelsted/pizzly) | **No**           | >=16 cores        | ~30GB             |
+| [Squid](https://github.com/Kingsford-Group/squid) | **No**           | >=16 cores        | ~30GB             |
+| [FusionInspector](https://github.com/FusionInspector/FusionInspector/wiki) | **No**           | >=16 cores        | ~30GB             |
+
+> **TL;DR:** Make sure to download all required references for each tool. More details can be found in section [tools](docs/tools.md).
+
 ```bash
 nextflow run nf-core/rnafusion --reads '*_R{1,2}.fastq.gz' --genome GRCh38 -profile docker --star_fusion --fusioncatcher --ericscript --pizzly --squid --fusion_inspector
 ```
 
-### Documentation
+For available parameters or help run:
+
+```bash
+nextflow run nf-core/rnafusion --help
+```
+
+## Documentation
+
 The nf-core/rnafusion pipeline comes with documentation about the pipeline, found in the `docs/` directory:
 
 1. [Installation](docs/installation.md)
 2. Pipeline configuration
-    * [Tools](docs/tools.md)
+    * [Download references for tools](docs/references.md)
     * [Local installation](docs/configuration/local.md)
-    * [Swedish UPPMAX cluster](docs/configuration/uppmax.md)
     * [Adding your own system](docs/configuration/adding_your_own.md)
 3. [Running the pipeline](docs/usage.md)
 4. [Output and how to interpret the results](docs/output.md)
 5. [Troubleshooting](docs/troubleshooting.md)
 
-### Final summary output
-
-![Final summary report](docs/images/example-summary-report.png)
+Use predefined configuration for desired Institution cluster provided at [nfcore/config](https://github.com/nf-core/configs) repository.

bin/create_mqc_section.py

@@ -1,15 +1,16 @@
 #!/usr/bin/env python3
 from collections import OrderedDict
-from yaml import dump
 import argparse
-import yaml
 import sys
 import os
+import yaml
+from yaml import dump
+
 
 OUTPUT = 'fusion_genes_config_mqc.yaml'
 TEMPLATE = OrderedDict([
     ('id', 'fusion_genes'),
-    ('s', 'Fusion genes'),
+    ('section_name', 'Fusion genes'),
     ('description', 'Number of fusion genes found by various tools'),
     ('plot_type', 'bargraph'),
     ('pconfig', {
@@ -24,22 +25,24 @@ def findings(p_yaml, p_sample_name):
     result = {}
 
     if p_yaml is None:
-        return
+        return None
 
     # Counts per tool
     for tool, fusions in p_yaml.items():
         result[tool] = len(fusions) if fusions is not None else 0
 
     # If only one tool was found, there is no need to make intercept
     if len(result) == 1:
-        template['data'] = { p_sample_name: result }
-        return OrderedDict(template)
+        template['data'] = {p_sample_name: result}
+    else:
+        # Intersect
+        result['together'] = len(
+            set.intersection(*map(set, [fusions for _, fusions in p_yaml.items()]))
+        )
+
+        # Group results
+        template['data'] = {p_sample_name: result}
 
-    # Intersect
-    result['together'] = len(set.intersection(*map(set, [fusions for _, fusions in p_yaml.items()])))
-
-    # Group results
-    template['data'] = { p_sample_name: result }
     return OrderedDict(template)
 
 def summary(p_input, p_sample_name):
@@ -49,22 +52,44 @@ def summary(p_input, p_sample_name):
         with open(p_input, 'r') as stream, open(OUTPUT, 'w') as out_file:
             yaml_data = yaml.safe_load(stream)
             # Conversion to nice yaml file
-            yaml.add_representer(OrderedDict, lambda dumper, data: dumper.represent_mapping('tag:yaml.org,2002:map', data.items()))
+            yaml.add_representer(
+                OrderedDict,
+                lambda dumper, data:
+                dumper.represent_mapping('tag:yaml.org,2002:map', data.items())
+            )
             # Find and store
-            out_file.write(dump(findings(yaml_data, p_sample_name), default_flow_style=False, allow_unicode=True))
+            out_file.write(
+                dump(
+                    findings(yaml_data, p_sample_name),
+                    default_flow_style=False,
+                    allow_unicode=True
+                )
+            )
             stream.close()
             out_file.close()
     except IOError as error:
         sys.exit(error)
     except yaml.YAMLError as error:
         sys.exit(error)
-    except Exception as error:
-        sys.exit(error)
 
+def main():
+    parser = argparse.ArgumentParser(
+        description='Tool for generating Fusion MultiQC section'
+    )
+    parser.add_argument(
+        '-i', '--input',
+        help='Input file',
+        type=str,
+        required=True
+    )
+    parser.add_argument(
+        '-s', '--sample',
+        help='Sample name',
+        type=str,
+        required=True
+    )
+    args = parser.parse_args()
+    summary(args.input, args.sample)
 
 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="""Utility for generating data structure for MultiQC""")
-    parser.add_argument('-i', '--input', nargs='?', help='Input file', type=str, required=True)
-    parser.add_argument('-s', '--sample', nargs='?', help='Sample name', type=str, required=True)
-    args = parser.parse_args()
-    summary(args.input, args.sample)
+    main()