Fusions

.gitlab-ci.yml

@@ -8,5 +8,8 @@ variables:
     # The workflow should define `--out_dir`, the CI template sets this.
     # Only common file inputs and option values need to be given here
     # (not things such as -profile)
-    NF_WORKFLOW_OPTS: "--fastq test_data/fastq \
+    NF_BEFORE_SCRIPT: |
-      --ref_genome test_data/SIRV_150601a.fasta --ref_annotation test_data/SIRV_isoforms.gtf"
+       wget -O test_data.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/wf-isoforms_test_data.tar.gz && tar -xzvf  test_data.tar.gz
+    NF_WORKFLOW_OPTS: "--fastq  ERR6053095_chr20.fastq \
+      --ref_genome chr20/hg38_chr20.fa --ref_annotation chr20/gencode.v22.annotation.chr20.gtf \
+      --jaffal_refBase chr20/ --jaffal_genome hg38_chr20 --jaffal_annotation genCode22"

.pre-commit-config.yaml

@@ -23,4 +23,7 @@ repos:
       - id: flake8
         additional_dependencies:
           - flake8-import-order==0.18.1
+          - flake8-docstrings==1.6.0
+          - flake8-rst-docstrings==0.2.5
+          - flake8-forbid-visual-indent==0.0.2
         entry: flake8 bin --import-order-style google --statistics

CHANGELOG.md

@@ -6,13 +6,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [unreleased]
 ### Changed
-- Skip unnecessary conversion to fasta from fastq
+
-- Fastqingress metadata map
 
 ## [v0.1.4]
+### Added
+- JAFFAL fusion detectoion subworkflow
 ### Changed
 - Args parser for fastqingress
 - Set out_dir option type to ensure output is written to correct directory on Windows
+- Skip unnecessary conversion to fasta from fastq
+- Fastqingress metadata map
+- Changed workflow name to wf-transcriptomes
 
 ## [v0.1.3]
 ### Changed

Dockerfile

@@ -15,6 +15,11 @@ RUN \
     && rm -rf $CONDA_DIR/lib/python3.*/site-packages/pip \
     && find $CONDA_DIR -name '__pycache__' -type d -exec rm -rf '{}' '+'
 
+
 USER $WF_UID
 WORKDIR $HOME
 
+# Install JAFFA
+ADD subworkflows $HOME/subworkflows
+RUN /bin/sh -c $HOME/subworkflows/JAFFAL/install_jaffa.sh
+

README.md

@@ -1,4 +1,4 @@
-# wf-isoforms
+# wf-transcriptomes
 
 This repository contains a [nextflow](https://www.nextflow.io/) workflow
 for assembly and annotation of transcripts from Oxford Nanopore cDNA or direct RNA reads.
@@ -16,14 +16,17 @@ cDNA reads are initially preprocessed by [pychopper](https://github.com/epi2me-l
 for the identification of full-length reads, as well as trimming and orientation correction (This step is omitted for 
  direct RNA reads).
 
-### Reference-aided approach
+
+### Transcript assembly
+
+#### Reference-aided transcript assembly approach
 * Full length reads are mapped to a supplied reference genome using [minimap2](https://github.com/lh3/minimap2)
 * Transcripts are assembled by [stringtie](http://ccb.jhu.edu/software/stringtie) 
 in long read mode (with or without a guide reference annotation) to generate the GFF annotation.
 * The annotation generated by the pipeline is compared to the reference annotation. 
 using [gffcompare](http://ccb.jhu.edu/software/stringtie/gffcompare.shtml)
 
-### de novo-based approach (experimental!)
+#### de novo-based transcript assembly (experimental!)
 * Sequence clusters are generated using [isONclust2](https://github.com/nanoporetech/isONclust2)
   * If a reference genome is supplied, cluster quality metrics are determined by comparing    
   with clusters generated from a minimap2 alignment.
@@ -33,11 +36,17 @@ using [gffcompare](http://ccb.jhu.edu/software/stringtie/gffcompare.shtml)
 * Transcripts are assembled by stringtie as for the reference-based approach.
 * __Note__: This approach is currently not supported with direct RNA reads.
 
+### Fusion gene detection
+Fusion gene detection is performed using [JAFFA](https://github.com/Oshlack/JAFFA), with the JAFFAL extension for use 
+with ONT long reads. 
+
 ### Workflow inputs
 - Directory containing cDNA/direct RNA reads. Or a directory containing subdirectories each with reads from different samples
   (in fastq/fastq.gz format)
 - Reference genome in fasta format (required for reference-based assembly).
-- Optional reference annotation in GFF2/3 format.## Quickstart
+- Optional reference annotation in GFF2/3 format.
+- For fusion detection, JAFFAL reference files (see Quickstart) 
+## Quickstart
 
 The workflow uses [nextflow](https://www.nextflow.io/) to manage compute and 
 software resources, as such nextflow will need to be installed before attempting
@@ -54,31 +63,31 @@ It is not required to clone or download the git repository in order to run the w
 For more information on running EPI2ME Labs workflows [visit out website](https://labs.epi2me.io/wfindex).
 
 
-**Workflow options**
+### Workflow options
 
 To obtain the workflow, having installed `nextflow`, users can run:
 
 ```
-nextflow run epi2me-labs/wf-isoforms --help
+nextflow run epi2me-labs/wf-transcriptomes --help
 ```
 
 to see the options for the workflow.
 
+**Download demonstration data**
 
+A small test dataset is provided for the purposes of testing the workflow software. It consists of reads, reference,
+and annotations from human chromosome 20 only.
+It can be downloaded using:
+```shell
+wget -O test_data.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/wf-isoforms_test_data.tar.gz 
+tar -xzvf  test_data.tar.gz
+```
 
-**Example execution of a workflow for reference-based transcript assembly**
+**Example execution of a workflow for reference-based transcript assembly and fusion detection**
-
-This example uses a synthetic SIRV dataset, so we need to tell minimap2 about the non-canonical splice junctions with 
---minimap2_opts '-uf --splice-flank=no'
 ```
 OUTPUT=~/output;
-nextflow run wf-isoforms/ --fastq test_data/fastq  --ref_genome test_data/SIRV_150601a.fasta --ref_annotation test_data/SIRV_isofroms.gtf
+nexflow run epi2me-labs/wf-transcriptomes --fastq ERR6053095_chr20.fastq --ref_genome chr20/hg38_chr20.fa --ref_annotation chr20/gencode.v22.annotation.chr20.gtf \
---minimap2_opts '-uf --splice-flank=no' --out_dir outdir -w workspace_dir -profile conda -resume
+      --jaffal_refBase chr20/ --jaffal_genome hg38_chr20 --jaffal_annotation genCode22" --out_dir outdir -w workspace_dir -profile conda -resume
-```
-
-```
-# To evaluate the workflow on a larger Drosophila dataset
-./evaluation/run_evaluation_dmel.sh outdir
 ```
 
 **Example workflow for denovo transcript assembly**
@@ -91,7 +100,7 @@ A full list of options can be seen in nextflow_schema.json. Below are some commo
 
 - Threshold for including isoforms into interactive table `transcript_table_cov_thresh = 50`
 - Run the denovo pipeline `denovo = true` (default false)
-- To run the workflow with direct RNA reads `--direct_rna` (skips the pychopper step).
+- To run the workflow with direct RNA reads `--direct_rna` (this just skips the pychopper step).
 
 
 Pychopper and minimap2 can take options via `minimap2_opts` and `pychopper_opts`, for example:
@@ -102,12 +111,74 @@ Pychopper and minimap2 can take options via `minimap2_opts` and `pychopper_opts`
 - pychopper needs to know which cDNA synthesis kit used
   - SQK-PCS109: use `pychopper_opts = '-k PCS109'` (default)
   - SQK-PCS110: use `pychopper_opts = '-k PCS110'`
+  - SQK-PCS11:  use `pychopper_opts = '-k PCS111'`
 - pychopper can use one of two available backends for identifying primers in the raw reads
   - nhmmscan `pychopper opts = '-m phmm'` 
   - edlib `pychopper opts = '-m edlib'`
 
-__Note__: edlib is set by default in the config as it's quite a lot faster. However it may be less sensitive than nhmmscan. 
+__Note__: edlib is set by default in the config as it's quite a lot faster. However, it may be less sensitive than nhmmscan. 
 
+### Fusion detection
+
+JAFFAL from the [JAFFA](https://github.com/Oshlack/JAFFA)
+package is used to identify potential fusion transcripts. To get this this working, there are a couple of things that need doing first.
+
+**Install JAFFA**
+
+to install JAFFA and it's dependencies run the folllowing:
+```shell
+cd wf-transcriptomes/
+./subworkflows/JAFFAL/install_jaffa.sh
+```
+
+**Prepare JAFFAL reference data**
+
+To use pre-processed reference files for the hg38 genome and GENCODE v22 annotation (as used in the JFFAAL paper),
+do:
+```shell
+mkdir jaffal_data_dir
+cd jaffal_data_dir/
+wf-transcriptomes/download_jaffal_references.sh
+````
+
+To use alternative genome and annotation files, they should be prepared as described
+[here](https://github.com/Oshlack/JAFFA/wiki/FAQandTroubleshooting#how-can-i-generate-the-reference-files-for-a-non-supported-genome)
+
+**Specifying the location of the JAFFA code and reference directories**
+
+`--jaffal_dir`
+This is the directory made by running install_jaffa.sh as shown above
+
+`--jaffal_refBase`
+The directory containing the reference data prepared for use with JAFFAL
+
+
+**JAFFAL annotation and genome files**
+
+The prepared JAFFAL reference files will look something like `hg38_chr20_genCode22.fa`. To enable JAFFAL to find these
+files `--jaffal_genome` should be set to `hg38_chr20` and `--jaffal_annotation` to `genCode22`
+
+
+__JAFFAL Notes__: 
+g++ must be installed. JAFFAL is not currently working on Mac M1 (osx-arm64 architecture). If there are no fusion transcripts
+detected, the workflow will terminate with an error at the JAFFAL stage. If this happens, 
+skip the JAFFAL stage by omitting ` --jaffal_refBase`
+
+
+## Workflow outputs
+* an HTML report document detailing the primary findings of the workflow.
+* for each sample:
+  * [gffcomapre](https://ccb.jhu.edu/software/stringtie/gffcompare.shtml) output directories
+  * read_aln_stats.tsv - alignment summary statistics
+  * transcriptome.fas - the assembled transcriptome
+  * merged_transcritptome.fas - annotated, assembled transcriptome
+  * [jaffal](https://github.com/Oshlack/JAFFA) ooutput directories
+  
+
+### Fusion detection outputs
+in `${out_dir}/jaffal_output_${sample_id}` you will find:
+* jaffa_results.csv - the csv results summary file 
+* jaffa_results.fasta - fusion transcritpt sequences
 ## Useful links
 
 * [nextflow](https://www.nextflow.io/)

bin/ping.py

@@ -53,7 +53,7 @@ def main():
             hostname=args.hostname,
             opsys=args.opsys
         ).send_workflow_ping(
-            workflow='wf-isoforms',
+            workflow='wf-transcriptomes',
             message=args.message,
             revision=args.revision,
             commit=args.commit,

bin/report.py

@@ -400,10 +400,10 @@ def gff_compare_plots(report, gffcompare_outdirs: Path, sample_ids):
         tracking = df_track.groupby("Overlaps").count().reset_index()
         tracking.Overlaps = tracking.Overlaps.map(names)
         tracking['Percent'] = tracking.Count * 100 / tracking.Count.sum()
-        tracking = tracking.sort_values("Overlaps")
+        tracking = tracking.sort_values("Count", ascending=False)
         track_bar = bars.simple_hbar(
-            tracking['Overlaps'].values.tolist(),
+            list(reversed(tracking['Overlaps'].values.tolist())),
-            tracking['Percent'].values.tolist(),
+            list(reversed(tracking['Percent'].values.tolist())),
             colors=Colors.cerulean, title=id_)
 
         tracking_dfs.append(tracking)
@@ -426,6 +426,7 @@ def gff_compare_plots(report, gffcompare_outdirs: Path, sample_ids):
         track_table = DataTable(
             columns=cols, source=ColumnDataSource(tracking),
             index_position=None, width=500)
+
         tabs.append(Panel(
             child=gridplot([track_bar, track_table], ncols=2), title=id_)
         )
@@ -602,7 +603,7 @@ def transcript_table(report, df_tmaps, covr_threshold):
 
     # drop some columns for the big table and do some filtering
     section.markdown('''
-    ### Query transcript table
+    ### Isoforms table
 
     Low coverage transcripts are removed to speed up the table viewing. <br>
     Coverage threshold can be set with the parameter
@@ -650,6 +651,8 @@ def transcript_table(report, df_tmaps, covr_threshold):
 
     df['parent gene iso num'] = df.apply(
         lambda x: gb.loc[(x.ref_gene_id, x.sample_id), 'num_isoforms'], axis=1)
+    # Uncalssified transcritps should not be lumped togetehr
+    df.loc[df.class_code == 'u', 'parent gene iso num'] = None
 
     df.sort_values('parent gene iso num', inplace=True, ascending=True)
 
@@ -795,6 +798,43 @@ def seq_stats_tabs(report, sample_ids, stats):
     section.plot(Tabs(tabs=tabs))
 
 
+def jaffal_table(report, sample_ids, result_csvs):
+    """Make a table of fusion transcripts identified by JAFFAL."""
+    cols = [
+        'sample_id', 'fusion genes', 'chrom1', 'chrom2', 'spanning reads',
+        'classification', 'known']
+    dfs = []
+    for csv, sid in zip(result_csvs, sample_ids):
+        df = pd.read_csv(csv)
+        df['sample_id'] = sid
+        sid_col = df.pop('sample_id')
+        df.insert(0, 'sample_id', sid_col)
+        dfs.append(df)
+
+    df = pd.concat(dfs)
+    df = df[cols]
+    df['chroms'] = df.chrom1.astype(str) + ':' + df.chrom2.astype(str)
+    df.rename(columns={
+        'spanning reads': 'nreads',
+        'fusion genes': 'genes'}, inplace=True)
+    df.drop(columns=['chrom1', 'chrom2'], inplace=True)
+    section = report.add_section()
+    section.markdown("""
+    ### JAFFAL fusion transcript summary
+
+    This table summarizes putative fusion transcripts identified
+    by [JAFFAL](https://github.com/Oshlack/JAFFA/).
+
+    * genes: the gene symbols of the fusion partners
+    * nreads: The number of reads supporting the fusion
+    * classification: JAFFAL's classification
+    * known: whether this fusion is in the given set of known gene fusions
+    * chroms: the respective, original chromosome location of the two partner
+    genes
+    """)
+    section.table(df)
+
+
 def main():
     """Run the entry point."""
     parser = argparse.ArgumentParser()
@@ -833,15 +873,17 @@ def main():
     parser.add_argument(
         "--cluster_qc_dirs", required=False, type=str, default=None, nargs='*',
         help="Directory with various cluster quality csvs")
+    parser.add_argument(
+        "--jaffal_csv", required=False, type=str, default=None,  nargs='*',
+        help="Path to JAFFAL results csv")
     parser.add_argument('--denovo', dest='denovo', action='store_true')
 
     args = parser.parse_args()
-    print('denovo', args.denovo)
 
     sample_ids = args.sample_ids
 
     report = WFReport(
-        "Transcript isoform report", "wf-isoforms",
+        "Transcript isoform report", "wf-transcriptomes",
         revision=args.revision, commit=args.commit)
 
     # Add reads summary section
@@ -853,7 +895,9 @@ def main():
         section.markdown('''
           ### Read mapping summary
 
-          Output of [seqkit](https://bioinf.shenwei.me/seqkit/) bam -s''')
+          Summary of minimap2 mapping from
+          [seqkit](https://bioinf.shenwei.me/seqkit/)
+          `seqkit bam -s`''')
 
         section.table(df_aln_stats)
 
@@ -877,6 +921,9 @@ def main():
     if args.cluster_qc_dirs is not None:
         cluster_quality(args.cluster_qc_dirs, report, sample_ids)
 
+    if args.jaffal_csv is not None:
+        jaffal_table(report, sample_ids, args.jaffal_csv)
+
     # Arguments and software versions
     report.add_section(
         section=scomponents.version_table(args.versions))

docs/header.md

@@ -1,4 +1,4 @@
-# wf-isoforms
+# wf-transcriptomes
 
 This repository contains a [nextflow](https://www.nextflow.io/) workflow
 for assembly and annotation of transcripts from Oxford Nanopore cDNA or direct RNA reads.

docs/intro.md

@@ -8,14 +8,17 @@ cDNA reads are initially preprocessed by [pychopper](https://github.com/epi2me-l
 for the identification of full-length reads, as well as trimming and orientation correction (This step is omitted for 
  direct RNA reads).
 
-### Reference-aided approach
+
+### Transcript assembly
+
+#### Reference-aided transcript assembly approach
 * Full length reads are mapped to a supplied reference genome using [minimap2](https://github.com/lh3/minimap2)
 * Transcripts are assembled by [stringtie](http://ccb.jhu.edu/software/stringtie) 
 in long read mode (with or without a guide reference annotation) to generate the GFF annotation.
 * The annotation generated by the pipeline is compared to the reference annotation. 
 using [gffcompare](http://ccb.jhu.edu/software/stringtie/gffcompare.shtml)
 
-### de novo-based approach (experimental!)
+#### de novo-based transcript assembly (experimental!)
 * Sequence clusters are generated using [isONclust2](https://github.com/nanoporetech/isONclust2)
   * If a reference genome is supplied, cluster quality metrics are determined by comparing    
   with clusters generated from a minimap2 alignment.
@@ -25,8 +28,13 @@ using [gffcompare](http://ccb.jhu.edu/software/stringtie/gffcompare.shtml)
 * Transcripts are assembled by stringtie as for the reference-based approach.
 * __Note__: This approach is currently not supported with direct RNA reads.
 
+### Fusion gene detection
+Fusion gene detection is performed using [JAFFA](https://github.com/Oshlack/JAFFA), with the JAFFAL extension for use 
+with ONT long reads. 
+
 ### Workflow inputs
 - Directory containing cDNA/direct RNA reads. Or a directory containing subdirectories each with reads from different samples
   (in fastq/fastq.gz format)
 - Reference genome in fasta format (required for reference-based assembly).
 - Optional reference annotation in GFF2/3 format.
+- For fusion detection, JAFFAL reference files (see Quickstart) 

docs/quickstart.md

@@ -15,31 +15,31 @@ It is not required to clone or download the git repository in order to run the w
 For more information on running EPI2ME Labs workflows [visit out website](https://labs.epi2me.io/wfindex).
 
 
-**Workflow options**
+### Workflow options
 
 To obtain the workflow, having installed `nextflow`, users can run:
 
 ```
-nextflow run epi2me-labs/wf-isoforms --help
+nextflow run epi2me-labs/wf-transcriptomes --help
 ```
 
 to see the options for the workflow.
 
+**Download demonstration data**
 
+A small test dataset is provided for the purposes of testing the workflow software. It consists of reads, reference,
+and annotations from human chromosome 20 only.
+It can be downloaded using:
+```shell
+wget -O test_data.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/wf-isoforms_test_data.tar.gz 
+tar -xzvf  test_data.tar.gz
+```
 
-**Example execution of a workflow for reference-based transcript assembly**
+**Example execution of a workflow for reference-based transcript assembly and fusion detection**
-
-This example uses a synthetic SIRV dataset, so we need to tell minimap2 about the non-canonical splice junctions with 
---minimap2_opts '-uf --splice-flank=no'
 ```
 OUTPUT=~/output;
-nextflow run wf-isoforms/ --fastq test_data/fastq  --ref_genome test_data/SIRV_150601a.fasta --ref_annotation test_data/SIRV_isofroms.gtf
+nexflow run epi2me-labs/wf-transcriptomes --fastq ERR6053095_chr20.fastq --ref_genome chr20/hg38_chr20.fa --ref_annotation chr20/gencode.v22.annotation.chr20.gtf \
---minimap2_opts '-uf --splice-flank=no' --out_dir outdir -w workspace_dir -profile conda -resume
+      --jaffal_refBase chr20/ --jaffal_genome hg38_chr20 --jaffal_annotation genCode22" --out_dir outdir -w workspace_dir -profile conda -resume
-```
-
-```
-# To evaluate the workflow on a larger Drosophila dataset
-./evaluation/run_evaluation_dmel.sh outdir
 ```
 
 **Example workflow for denovo transcript assembly**
@@ -52,7 +52,7 @@ A full list of options can be seen in nextflow_schema.json. Below are some commo
 
 - Threshold for including isoforms into interactive table `transcript_table_cov_thresh = 50`
 - Run the denovo pipeline `denovo = true` (default false)
-- To run the workflow with direct RNA reads `--direct_rna` (skips the pychopper step).
+- To run the workflow with direct RNA reads `--direct_rna` (this just skips the pychopper step).
 
 
 Pychopper and minimap2 can take options via `minimap2_opts` and `pychopper_opts`, for example:
@@ -63,9 +63,71 @@ Pychopper and minimap2 can take options via `minimap2_opts` and `pychopper_opts`
 - pychopper needs to know which cDNA synthesis kit used
   - SQK-PCS109: use `pychopper_opts = '-k PCS109'` (default)
   - SQK-PCS110: use `pychopper_opts = '-k PCS110'`
+  - SQK-PCS11:  use `pychopper_opts = '-k PCS111'`
 - pychopper can use one of two available backends for identifying primers in the raw reads
   - nhmmscan `pychopper opts = '-m phmm'` 
   - edlib `pychopper opts = '-m edlib'`
 
-__Note__: edlib is set by default in the config as it's quite a lot faster. However it may be less sensitive than nhmmscan. 
+__Note__: edlib is set by default in the config as it's quite a lot faster. However, it may be less sensitive than nhmmscan. 
 
+### Fusion detection
+
+JAFFAL from the [JAFFA](https://github.com/Oshlack/JAFFA)
+package is used to identify potential fusion transcripts. To get this this working, there are a couple of things that need doing first.
+
+**Install JAFFA**
+
+to install JAFFA and it's dependencies run the folllowing:
+```shell
+cd wf-transcriptomes/
+./subworkflows/JAFFAL/install_jaffa.sh
+```
+
+**Prepare JAFFAL reference data**
+
+To use pre-processed reference files for the hg38 genome and GENCODE v22 annotation (as used in the JFFAAL paper),
+do:
+```shell
+mkdir jaffal_data_dir
+cd jaffal_data_dir/
+wf-transcriptomes/download_jaffal_references.sh
+````
+
+To use alternative genome and annotation files, they should be prepared as described
+[here](https://github.com/Oshlack/JAFFA/wiki/FAQandTroubleshooting#how-can-i-generate-the-reference-files-for-a-non-supported-genome)
+
+**Specifying the location of the JAFFA code and reference directories**
+
+`--jaffal_dir`
+This is the directory made by running install_jaffa.sh as shown above
+
+`--jaffal_refBase`
+The directory containing the reference data prepared for use with JAFFAL
+
+
+**JAFFAL annotation and genome files**
+
+The prepared JAFFAL reference files will look something like `hg38_chr20_genCode22.fa`. To enable JAFFAL to find these
+files `--jaffal_genome` should be set to `hg38_chr20` and `--jaffal_annotation` to `genCode22`
+
+
+__JAFFAL Notes__: 
+g++ must be installed. JAFFAL is not currently working on Mac M1 (osx-arm64 architecture). If there are no fusion transcripts
+detected, the workflow will terminate with an error at the JAFFAL stage. If this happens, 
+skip the JAFFAL stage by omitting ` --jaffal_refBase`
+
+
+## Workflow outputs
+* an HTML report document detailing the primary findings of the workflow.
+* for each sample:
+  * [gffcomapre](https://ccb.jhu.edu/software/stringtie/gffcompare.shtml) output directories
+  * read_aln_stats.tsv - alignment summary statistics
+  * transcriptome.fas - the assembled transcriptome
+  * merged_transcritptome.fas - annotated, assembled transcriptome
+  * [jaffal](https://github.com/Oshlack/JAFFA) ooutput directories
+  
+
+### Fusion detection outputs
+in `${out_dir}/jaffal_output_${sample_id}` you will find:
+* jaffa_results.csv - the csv results summary file 
+* jaffa_results.fasta - fusion transcritpt sequences

download_jaffal_references.sh

@@ -0,0 +1,5 @@
+#!/bin/sh
+
+#Download the data. We should we move the data out of Figshare?
+wget -O JAFFA_REFERENCE_FILES_HG38_GENCODE22.V2.tar.gz https://figshare.com/ndownloader/files/25410494
+tar -zxvf JAFFA_REFERENCE_FILES_HG38_GENCODE22.V2.tar.gz

environment.yaml

@@ -1,8 +1,8 @@
-name: epi2melabs-wf-isoforms
+name: epi2melabs-wf-transcriptomes
 channels:
     - epi2melabs
-    - bioconda
     - conda-forge
+    - bioconda
     - defaults
 dependencies:
     - python==3.8.*
@@ -27,4 +27,8 @@ dependencies:
     - parallel
     - scikit-learn==1.0.2
     - natsort
-    - graphviz
+# Fusion detection dependencies
+#    - bpipe=0.9.9.2
+    - java-jdk
+    - r-base
+    - gxx

evaluation/run_evaluation_dmel.sh

@@ -1,59 +0,0 @@
-#!/usr/bin/env bash
-
-# Usage: ./run_evaluation_dmel.sh pathto/outputdir
-
-# See the isONcorrect paper https://www.nature.com/articles/s41467-020-20340-8 where this dataset is described
-
-
-if [[ "$#" -lt 1 ]]; then
-    echo "usage: run_evaluation_dmel.sh <outdir> [nextflow.config]"
-    exit 1
-fi
-
-if [[ "$#" -eq 1 ]]; then
-    config=''
-fi
-
-if [[ "$#" -eq 2 ]]; then
-  config="-c $2";
-fi
-
-OUTDIR=$1;
-
-FASTQ_URL="http://ftp.sra.ebi.ac.uk/vol1/fastq/ERR358/005/ERR3588905/ERR3588905_1.fastq.gz"
-REF_URL="http://ftp.ensembl.org/pub/release-99/fasta/drosophila_melanogaster/dna/Drosophila_melanogaster.BDGP6.28.dna.toplevel.fa.gz"
-GFF_URL="http://ftp.ensembl.org/pub/release-99/gff3/drosophila_melanogaster/Drosophila_melanogaster.BDGP6.28.99.gff3.gz"
-
-DATA_DIR="$OUTDIR/data"
-READS_DIR="$DATA_DIR/reads"
-FASTQ="$READS_DIR/ERR3588905_1.fastq.gz"
-REF="$DATA_DIR/Drosophila_melanogaster.BDGP6.28.dna.toplevel.fa"
-GFF="$DATA_DIR/Drosophila_melanogaster.BDGP6.28.99.gff3"
-
-mkdir -p $READS_DIR
-
-if [ ! -f $REF ];
-then (echo "downloading reference genome"; cd $DATA_DIR; curl -L -C - -O $REF_URL); gzip -d ${REF}.gz
-fi
-
-if [ ! -f $GFF ];
-then
-	(echo "downloading reference annotation"; cd $DATA_DIR; curl -L -C - -O $GFF_URL); gzip -d ${GFF}.gz
-fi
-
-if [ ! -f $FASTQ ];
-then (echo "downloading reads"; cd $READS_DIR; curl -L -C - -O $FASTQ_URL); gzip -d ${FASTQ}.gz
-fi
-
-
-OUT_REF="$OUTDIR/ref"
-OUT_DENOVO="$OUTDIR/denovo"
-
-
-nextflow run ../ --fastq $READS_DIR  $config \
---ref_genome $REF --ref_annotation $GFF -profile local --out_dir $OUT_REF --minimap2_opts '-uf --splice-flank=no' \
--w $OUT_REF/workspace -resume;
-
-echo "Doing de novo evaluation"
-nextflow run ../ --fastq $READS_DIR  $config --denovo -profile local --out_dir $OUT_DENOVO \
--w $OUT_DENOVO/workspace -resume;

main.nf

@@ -12,8 +12,9 @@ nextflow.enable.dsl = 2
 
 include { fastq_ingress } from './lib/fastqingress'
 include { start_ping; end_ping } from './lib/ping'
-include { reference_assembly } from './reference_assembly'
+include { reference_assembly } from './subworkflows/reference_assembly'
-include { denovo_assembly } from './denovo_assembly'
+include { denovo_assembly } from './subworkflows/denovo_assembly'
+include { gene_fusions } from './subworkflows/JAFFAL/gene_fusions'
 
 
 process summariseConcatReads {
@@ -83,11 +84,11 @@ process preprocess_reads {
     input:
         tuple val(sample_id), path(input_reads)
     output:
-         tuple val(sample_id), path("${sample_id}_full_length_reads.fq"), emit: full_len_reads
+         tuple val(sample_id), path("${sample_id}_full_length_reads.fastq"), emit: full_len_reads
          path '*.tsv',  emit: report
     script:
         """
-        pychopper -t ${params.threads} ${params.pychopper_opts} ${input_reads} ${sample_id}_full_length_reads.fq
+        pychopper -t ${params.threads} ${params.pychopper_opts} ${input_reads} ${sample_id}_full_length_reads.fastq
         mv pychopper.tsv ${sample_id}_pychopper.tsv
         generate_pychopper_stats.py --data ${sample_id}_pychopper.tsv --output .
 
@@ -285,13 +286,14 @@ process makeReport {
               path(seq_summaries),
               path(aln_stats),
               path(gffcmp_dir),
-              path(gff_annotation)
+              path(gff_annotation),
+              path(jaffal_csv)
     output:
-        path("wf-isoforms-*.html"), emit: report
+        path("wf-transcriptomes-*.html"), emit: report
     script:
         // Convert the sample_id arrayList.
         sids = new BlankSeparatedList(sample_ids)
-        def report_name = "wf-isoforms-report.html"
+        def report_name = "wf-transcriptomes-report.html"
         def OPT_ALN = denovo ?  '' : "--alignment_stats ${aln_stats}"
         def OPT_DENOVO = denovo ? "--denovo" : ''
         def OPT_PC_REPORT = pychopper_report.name.startsWith('OPTIONAL_FILE') ? '' : "--pychop_report ${pychopper_report}"
@@ -306,6 +308,7 @@ process makeReport {
     --gffcompare_dir $gffcmp_dir \
     --gff_annotation $gff_annotation \
     --transcript_table_cov_thresh $params.transcript_table_cov_thresh \
+    --jaffal_csv $jaffal_csv
     $OPT_DENOVO
     """
 }
@@ -332,6 +335,9 @@ workflow pipeline {
         reads
         ref_genome
         ref_annotation
+        jaffal_refBase
+        jaffal_genome
+        jaffal_annotation
     main:
         map_sample_ids_cls = {it ->
         /* Harmonize tuples
@@ -400,6 +406,10 @@ workflow pipeline {
             seq_for_transcriptome_build = sample_ids.flatten().combine(Channel.fromPath(params.ref_genome))
         }
 
+        if (jaffal_refBase){
+            gene_fusions(full_len_reads, jaffal_refBase, jaffal_genome, jaffal_annotation)
+        }
+
         makeReport(
             software_versions,
             workflow_params,
@@ -409,6 +419,7 @@ workflow pipeline {
             .join(m.stats)
             .join(run_gffcompare.out.gffcmp_dir)
             .join(merge_gff_bundles.out.gff)
+            .join(gene_fusions.out.results_csv)
             .toList().transpose().toList())
 
         report = makeReport.out.report
@@ -452,6 +463,11 @@ workflow pipeline {
                       .map {it -> it[1]}
                       .concat(makeReport.out.report)
         }
+        if (params.jaffal_refBase){
+            results = results
+                .concat(gene_fusions.out.results
+                .map {it -> it[1]})
+        }
 
     emit:
         results
@@ -466,42 +482,49 @@ workflow {
 
     fastq = file(params.fastq, type: "file")
 
+    error = null
+
     if (!fastq.exists()) {
-        println("--fastq: File doesn't exist, check path.")
+        error = "--fastq: File doesn't exist, check path."
-        exit 1
     }
 
     if (!params.denovo && !params.ref_genome){
-        println("--ref_genome must be supplied unless doing de novo assembly (--denovo)")
+        error = "--ref_genome must be supplied unless doing de novo assembly (--denovo)"
-        exit 1
     }
 
-
     if (params.ref_genome){
         ref_genome = file(params.ref_genome, type: "file")
         if (!ref_genome.exists()) {
-            println("--ref_genome: File doesn't exist, check path.")
+            error = "--ref_genome: File doesn't exist, check path."
-            exit 1
         }
     }else {
         ref_genome = file("$projectDir/data/OPTIONAL_FILE")
     }
 
     if (params.denovo && params.ref_annotation) {
-        println("Reference annotation with de denovo assembly is not supported")
+        error = "Reference annotation with de denovo assembly is not supported"
-        exit 1
     }
 
     if (params.ref_annotation){
         ref_annotation = file(params.ref_annotation, type: "file")
         if (!ref_annotation.exists()) {
-            println("--annotation: File doesn't exist, check path.")
+            error = "--annotation: File doesn't exist, check path."
-            exit 1
         }
     }else{
         ref_annotation = file("$projectDir/data/OPTIONAL_FILE")
     }
+     if (params.jaffal_refBase){
+        jaffal_refBase = file(params.jaffal_refBase, type: "dir")
+        if (!jaffal_refBase.exists()) {
+            error = "--jaffa_refBase: Directory doesn't exist, check path."
+        }
+     }else{
+        jaffal_refBase = null
+     }
 
+    if (error){
+        println(error)
+    }else{
         reads = fastq_ingress([
             "input":params.fastq,
             "sample":params.sample,
@@ -509,9 +532,10 @@ workflow {
             "sanitize": params.sanitize_fastq,
             "output":params.out_dir])
 
-    pipeline(reads, ref_genome, ref_annotation)
+        pipeline(reads, ref_genome, ref_annotation, jaffal_refBase, params.jaffal_genome, params.jaffal_annotation)
 
         output(pipeline.out.results)
 
         end_ping(pipeline.out.telemetry)
+    }
 }

nextflow.config

@@ -119,21 +119,30 @@ params {
     // Minimum probability for i consecutive minimizers to be different between read and representative:
     min_prob_no_hits = 0.1
 
+    ////// Fusion detection parameters
+    jaffal_refBase = null
+    jaffal_genome = "hg38"
+    jaffal_annotation = "genCode22"
+    // The default location of the JAFFA src directory when running in EPI2ME-Labs environment
+    // This needs overriding if running elsewhere
+    jaffal_dir = "/home/epi2melabs/JAFFA"
+
     wf {
       example_cmd = [
           "--fastq test_data/fastq",
           "--ref_genome test_data/SIRV_150601a.fasta",
-          "--ref_annotation test_data/SIRV_isofroms.gtf"
+          "--ref_annotation test_data/SIRV_isofroms.gtf",
+          "--jaffal_refBase chr20/",
+          "--jaffal_genome hg38",
+          "--jaffal_annotation genCode22"
       ]
     }
-
-
 }
 
 manifest {
-    name            = 'epi2me-labs/wf-isoforms'
+    name            = 'epi2me-labs/wf-transcriptomes'
     author          = 'Oxford Nanopore Technologies'
-    homePage        = 'https://github.com/epi2me-labs/wf-isoforms'
+    homePage        = 'https://github.com/epi2me-labs/wf-transcriptomes'
     description     = 'RNA/cDNA isoform analysis workflow'
     mainScript      = 'main.nf'
     nextflowVersion = '>=20.10.0'
@@ -151,7 +160,7 @@ executor {
 // other profiles may override.
 process {
     withLabel:isoforms {
-        container = "ontresearch/wf-isoforms:${params.wfversion}"
+        container = "ontresearch/wf-transcriptomes:${params.wfversion}"
     }
     shell = ['/bin/bash', '-euo', 'pipefail']
 }
@@ -201,7 +210,7 @@ profiles {
             queue = "${params.aws_queue}"
             memory = '8G'
             withLabel:isoforms {
-                container = "${params.aws_image_prefix}-wf-isoforms:${params.wfversion}"
+                container = "${params.aws_image_prefix}-wf-transcriptomes:${params.wfversion}"
             }
             shell = ['/bin/bash', '-euo', 'pipefail']
         }

nextflow_schema.json

@@ -1,9 +1,9 @@
 {
     "$schema": "http://json-schema.org/draft-07/schema",
     "$id": "https://raw.githubusercontent.com/./master/nextflow_schema.json",
-    "title": "epi2me-labs/wf-isoforms",
+    "title": "epi2me-labs/wf-transcriptomes",
     "description": "Isoform detection and characterisation.",
-    "url": "https://github.com/epi2me-labs/wf-isoforms",
+    "url": "https://github.com/epi2me-labs/wf-transcriptomes",
     "type": "object",
     "definitions": {
         "basic_input_output_options": {
@@ -14,13 +14,13 @@
             "properties": {
                 "out_dir": {
                     "type": "string",
-                    "default": "output",
                     "format": "directory-path",
+                    "default": "output",
                     "description": "Directory for output of all user-facing files."
                 },
                 "fastq": {
                     "type": "string",
-                    "format": "path",
+                    "format": "file-path",
                     "demo_data": "${projectDir}/test_data/fastq",
                     "description": "A fastq file or directory containing fastq input files or directories of input files.",
                     "help_text": "If directories named \\\"barcode*\\\" are found under the `--fastq` directory the data is assumed to be multiplex and each barcode directory will be processed independently. If `.fastq(.gz)` files are found under the `--fastq` directory the sample is assumed to not be multiplexed. In this second case `--samples` should be a simple name rather than a CSV file."
@@ -99,7 +99,7 @@
         "reference_wf_options": {
             "title": "Options for reference-based workflow",
             "type": "object",
-            "description": "Parameters that are used solely for the referenc-guided workflow",
+            "description": "Parameters that are used solely for the reference-guided workflow",
             "properties": {
                 "plot_gffcmp_stats": {
                     "type": "boolean",
@@ -219,6 +219,34 @@
                 }
             }
         },
+        "fusion_detection_options": {
+            "title": "Gene fusion detection options",
+            "type": "object",
+            "description": "Parameters for gene fusion detection",
+            "properties": {
+                "jaffal_refBase": {
+                    "type": "string",
+                    "format": "path",
+                    "description": "JAFFAl reference genome directory"
+                },
+                "jaffal_genome": {
+                    "type": "string",
+                    "description": "Genome reference prefix. e.g. hg38",
+                    "default": "hg38"
+                },
+                "jaffal_annotation": {
+                    "type": "string",
+                    "description": "Annotation prefix",
+                    "default": "genCode22"
+                },
+                "jaffal_dir": {
+                    "type": "string",
+                    "format": "path",
+                    "description": "Path to JAFFAL git code directory. Defaults is epi2me-labs container location",
+                    "default": "/home/epi2melabs/JAFFA"
+                }
+            }
+        },
         "meta_data": {
             "title": "Meta Data",
             "type": "object",
@@ -266,6 +294,9 @@
         {
             "$ref": "#/definitions/denovo_wf_options"
         },
+        {
+            "$ref": "#/definitions/fusion_detection_options"
+        },
         {
             "$ref": "#/definitions/meta_data"
         },
@@ -299,7 +330,7 @@
         }
     },
     "docs": {
-        "intro": "## Introduction\n\nThis workflow identifies RNA isoforms using either cDNA or direct RNA (dRNA) \nOxford Nanopore reads.\n\n### Preprocesing\ncDNA reads are initially preprocessed by [pychopper](https://github.com/epi2me-labs/pychopper) \nfor the identification of full-length reads, as well as trimming and orientation correction (This step is omitted for \n direct RNA reads).\n\n### Reference-aided approach\n* Full length reads are mapped to a supplied reference genome using [minimap2](https://github.com/lh3/minimap2)\n* Transcripts are assembled by [stringtie](http://ccb.jhu.edu/software/stringtie) \nin long read mode (with or without a guide reference annotation) to generate the GFF annotation.\n* The annotation generated by the pipeline is compared to the reference annotation. \nusing [gffcompare](http://ccb.jhu.edu/software/stringtie/gffcompare.shtml)\n\n### de novo-based approach (experimental!)\n* Sequence clusters are generated using [isONclust2](https://github.com/nanoporetech/isONclust2)\n  * If a reference genome is supplied, cluster quality metrics are determined by comparing    \n  with clusters generated from a minimap2 alignment.\n* A consensus sequence for each cluster is generated using [spoa](https://github.com/rvaser/spoa)\n* Three rounds of polishing using racon and minimap2 to give a final polished CDS for each gene.\n* Full-length reads are then mapped to these polished CDS.\n* Transcripts are assembled by stringtie as for the reference-based approach.\n* __Note__: This approach is currently not supported with direct RNA reads.\n\n### Workflow inputs\n- Directory containing cDNA/direct RNA reads. Or a directory containing subdirectories each with reads from different samples\n  (in fastq/fastq.gz format)\n- Reference genome in fasta format (required for reference-based assembly).\n- Optional reference annotation in GFF2/3 format.",
+        "intro": "## Introduction\n\nThis workflow identifies RNA isoforms using either cDNA or direct RNA (dRNA) \nOxford Nanopore reads.\n\n### Preprocesing\ncDNA reads are initially preprocessed by [pychopper](https://github.com/epi2me-labs/pychopper) \nfor the identification of full-length reads, as well as trimming and orientation correction (This step is omitted for \n direct RNA reads).\n\n\n### Transcript assembly\n\n#### Reference-aided transcript assembly approach\n* Full length reads are mapped to a supplied reference genome using [minimap2](https://github.com/lh3/minimap2)\n* Transcripts are assembled by [stringtie](http://ccb.jhu.edu/software/stringtie) \nin long read mode (with or without a guide reference annotation) to generate the GFF annotation.\n* The annotation generated by the pipeline is compared to the reference annotation. \nusing [gffcompare](http://ccb.jhu.edu/software/stringtie/gffcompare.shtml)\n\n#### de novo-based transcript assembly (experimental!)\n* Sequence clusters are generated using [isONclust2](https://github.com/nanoporetech/isONclust2)\n  * If a reference genome is supplied, cluster quality metrics are determined by comparing    \n  with clusters generated from a minimap2 alignment.\n* A consensus sequence for each cluster is generated using [spoa](https://github.com/rvaser/spoa)\n* Three rounds of polishing using racon and minimap2 to give a final polished CDS for each gene.\n* Full-length reads are then mapped to these polished CDS.\n* Transcripts are assembled by stringtie as for the reference-based approach.\n* __Note__: This approach is currently not supported with direct RNA reads.\n\n### Fusion gene detection\nFusion gene detection is performed using [JAFFA](https://github.com/Oshlack/JAFFA), with the JAFFAL extension for use \nwith ONT long reads. \n\n### Workflow inputs\n- Directory containing cDNA/direct RNA reads. Or a directory containing subdirectories each with reads from different samples\n  (in fastq/fastq.gz format)\n- Reference genome in fasta format (required for reference-based assembly).\n- Optional reference annotation in GFF2/3 format.\n- For fusion detection, JAFFAL reference files (see Quickstart) \n",
         "links": "## Useful links\n\n* [nextflow](https://www.nextflow.io/)\n* [docker](https://www.docker.com/products/docker-desktop)\n* [Singularity](https://sylabs.io/singularity/)\n* [conda](https://docs.conda.io/en/latest/miniconda.html)\n* [racon](https://github.com/isovic/racon)\n* [spoa](https://github.com/rvaser/spoa)\n* [inONclust](https://github.com/ksahlin/isONclust)\n* [isONclust2](https://github.com/nanoporetech/isONclust2)"
     }
 }

subworkflows/JAFFAL/build_jaffal_ref.sh

@@ -0,0 +1,2 @@
+#!/bin/sh
+

subworkflows/JAFFAL/gene_fusions.nf

@@ -0,0 +1,40 @@
+
+process jaffal{
+    label "isoforms"
+    input:
+        tuple val(sample_id), path(fastq)
+        path refBase
+        val genome
+        val annotation
+    output:
+        tuple val(sample_id), path("jaffal_output_$sample_id"), emit: results
+        tuple val(sample_id), path("jaffal_output_$sample_id/*jaffa_results.csv"), emit: results_csv
+    script:
+    """
+    JAFFAOUT=jaffal_output_$sample_id
+    $params.jaffal_dir/tools/bin/bpipe run \
+        -n $params.threads \
+        -p jaffa_output="\$JAFFAOUT/" \
+        -p refBase=$refBase \
+        -p genome=$genome \
+        -p annotation=$annotation \
+        -p fastqInputFormat="*.fastq" \
+        $params.jaffal_dir/JAFFAL.groovy \
+        $fastq
+    mv "\$JAFFAOUT/jaffa_results.csv" "\$JAFFAOUT/${sample_id}_jaffa_results.csv"
+    """
+}
+
+// workflow module
+workflow gene_fusions {
+    take:
+        fastq
+        refBase
+        genome
+        annotation
+    main:
+        jaffal(fastq, refBase, genome, annotation)
+    emit:
+        results_csv = jaffal.out.results_csv
+        results = jaffal.out.results
+}

subworkflows/JAFFAL/install_jaffa.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+set -e
+
+git clone https://github.com/Oshlack/JAFFA.git &&
+cd JAFFA
+git checkout 24b1c3b
+
+cp ../subworkflows/JAFFAL/install_linux64.sh .
+./install_linux64.sh
+
+# JAFFA uses tools.groovy to locate binaries. We modify it as we only need a small subset or they are already
+# included in our env
+
+# Tools to be compiled from src/
+bin=$(realpath tools/bin)
+echo "//Tools built locally" >> tools.groovy
+declare -a tools=("reformat" "extract_seq_from_fasta" "make_simple_read_table" "process_transcriptome_align_table" "make_3_gene_fusion_table")
+for b in "${tools[@]}"; do
+  echo "$b=\"$bin/$b\"" >> tools.groovy
+done
+echo "minimap2=\"minimap2\"" >> tools.groovy

subworkflows/JAFFAL/install_linux64.sh

@@ -0,0 +1,111 @@
+#!/bin/bash
+
+# 21/06/22: This script has been modified to install only those applications needed for epi2melabs/wf-transcriptomes
+
+## This script will install the tools required for the JAFFA pipeline.
+## It will fetched each tool from the web and placed into the tools/ subdirectory.
+## Paths to all installed tools can be found in the file tools.groovy at the
+## end of execution of this script. These paths can be changed if a different
+## version of software is required. Note that R must be installed manually
+##
+## Last Modified: Sep. 2021 by Nadia Davidson
+
+mkdir -p tools/bin 
+cd tools 
+
+#a list of which programs need to be installed
+commands="bpipe reformat extract_seq_from_fasta make_simple_read_table process_transcriptome_align_table make_3_gene_fusion_table dedupe"
+
+#installation methods
+function bpipe_install {
+   wget -O bpipe-0.9.9.2.tar.gz https://github.com/ssadedin/bpipe/releases/download/0.9.9.2/bpipe-0.9.9.2.tar.gz
+   tar -zxvf bpipe-0.9.9.2.tar.gz ; rm bpipe-0.9.9.2.tar.gz
+   ln -s $PWD/bpipe-0.9.9.2/bin/* $PWD/bin/
+}
+
+function make_3_gene_fusion_table_install {
+    g++ -std=c++11 -O3 -o bin/make_3_gene_fusion_table ../src/make_3_gene_fusion_table.c++
+}
+
+function extract_seq_from_fasta_install {
+    g++ -std=c++11 -O3 -o bin/extract_seq_from_fasta ../src/extract_seq_from_fasta.c++
+}
+
+function make_simple_read_table_install {
+    g++ -std=c++11 -O3 -o bin/make_simple_read_table ../src/make_simple_read_table.c++
+}
+
+function process_transcriptome_align_table_install {
+    g++ -std=c++11 -O3 -o bin/process_transcriptome_align_table ../src/process_transcriptome_align_table.c++
+}
+
+function make_count_table_install {
+    g++ -O3 -o bin/make_count_table ../src/make_count_table.c++
+}
+
+function dedupe_install {
+    wget --no-check-certificate https://sourceforge.net/projects/bbmap/files/BBMap_36.59.tar.gz
+    tar -zxvf BBMap_36.59.tar.gz
+    rm BBMap_36.59.tar.gz
+    for script in `ls $PWD/bbmap/*.sh` ; do
+	s=`basename $script`
+	s_pre=`echo $s | sed 's/.sh//g'`
+	echo "$PWD/bbmap/$s \$@" > $PWD/bin/$s_pre
+	chmod +x $PWD/bin/$s_pre
+    done
+}
+
+#function bypass_genomic_alignment_install {
+#    g++ -std=c++11 -O3 -o bin/bypass_genomic_alignment ../src/bypass_genomic_alignment.c++
+#}
+
+#Check if the version of gcc is >= 4.9
+gcc_version=`gcc -dumpversion`
+gcc_check=`echo -e "$gcc_version\n4.9" | sort -n | tail -n1`
+if [[ $gcc_chek = "4.9" ]] 
+then 
+   echo "Your version of gcc is $gcc_version."
+   echo "gcc must be >= 4.9 to install JAFFA. Exiting..."
+   exit 1
+fi
+
+echo "gcc check passed"
+
+echo "// Path to tools used by the JAFFA pipeline" > ../tools.groovy
+
+for c in $commands ; do 
+    c_path=`which $PWD/bin/$c 2>/dev/null`
+    if [ -z $c_path ] ; then 
+	echo "$c not found, fetching it"
+	${c}_install
+	c_path=`which $PWD/bin/$c 2>/dev/null`
+    fi
+    echo "$c=\"$c_path\"" >> ../tools.groovy
+done
+
+#finally check that R is install
+R_path=`which R 2>/dev/null`
+if [ -z $R_path ] ; then
+    echo "R not found!"
+    echo "Please go to http://www.r-project.org/ and follow the installation instructions."
+    echo "Note that the IRanges R package must be installed."
+fi
+echo "R=\"$R_path\"" >> ../tools.groovy
+
+#loop through commands to check they are all installed
+echo "Checking that all required tools were installed:"
+Final_message="All commands installed successfully!"
+for c in $commands ; do
+    c_path=`which $PWD/bin/$c 2>/dev/null`
+    if [ -z $c_path ] ; then
+	echo -n "WARNING: $c could not be found!!!! " 
+	echo "You will need to download and install $c manually, then add its path to tools.groovy"
+	Final_message="WARNING: One or more command did not install successfully. See warning messages above. \
+                       You will need to correct this before running JAFFA."
+    else 
+        echo "$c looks like it has been installed"
+    fi
+done
+echo "**********************************************************"
+echo $Final_message
+

subworkflows/JAFFAL/tools.groovy

@@ -0,0 +1,10 @@
+// Path to tools used by the JAFFA pipeline
+
+// Conda-installable tools
+bpipe="bpipe"
+//trimmomatic="trimmomatic"
+R="/usr/bin/R"
+minimap2="minimap2"
+dedupe="dedupe"
+
+