schema updates

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -51,12 +51,11 @@ body:
   - type: dropdown
     id: profile
     attributes:
-      label: Workflow Execution - Execution Profile
+      label: Workflow Execution - CLI Execution Profile
       description: If you're using the CLI to run the workflow, what profile are you using?
       options:
         - Docker
         - Singularity
-        - Conda
     validations:
       required: false
   - type: input

.gitlab-ci.yml

@@ -9,6 +9,7 @@ variables:
                   --ref_genome chr20/hg38_chr20.fa --ref_annotation chr20/gencode.v22.annotation.chr20.gtf \
                   --jaffal_refBase chr20/ --jaffal_genome hg38_chr20 --jaffal_annotation genCode22"
               NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes
+              CI_FLAVOUR: "new"
 
 docker-run:
 
@@ -31,13 +32,13 @@ docker-run:
         - if: $MATRIX_NAME == "isoforms"
           variables:
               NF_BEFORE_SCRIPT: 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 \
+              NF_WORKFLOW_OPTS: "--fastq  ERR6053095_chr20.fastq --transcriptome-source reference-guided \
                   --ref_genome chr20/hg38_chr20.fa --ref_annotation chr20/gencode.v22.annotation.chr20.gtf"
               NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes
         - if: $MATRIX_NAME == "fusions"
           variables:
               NF_BEFORE_SCRIPT: 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 \
+              NF_WORKFLOW_OPTS: "--fastq  ERR6053095_chr20.fastq --transcriptome-source reference-guided \
                   --ref_genome chr20/hg38_chr20.fa --ref_annotation chr20/gencode.v22.annotation.chr20.gtf \
                   --jaffal_refBase chr20/ --jaffal_genome hg38_chr20 --jaffal_annotation genCode22"
               NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes
@@ -46,7 +47,7 @@ docker-run:
               NF_BEFORE_SCRIPT: wget -O differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf differential_expression.tar.gz
               NF_WORKFLOW_OPTS: "--fastq  differential_expression/differential_expression_fastq \
                   --de_analysis \
-                  --ref_genome differential_expression/hg38_chr20.fa \
+                  --ref_genome differential_expression/hg38_chr20.fa --transcriptome-source reference-guided \
                 --ref_annotation differential_expression/gencode.v22.annotation.chr20.gtf \
                 --direct_rna --minimap_index_opts \\-k15"
               NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes
@@ -54,6 +55,7 @@ docker-run:
           variables:
               NF_BEFORE_SCRIPT: wget -O differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf differential_expression.tar.gz
               NF_WORKFLOW_OPTS: "--fastq  differential_expression/differential_expression_fastq \
+                  --transcriptome-source precomputed \
                   --de_analysis \
                   --ref_genome differential_expression/hg38_chr20.fa \
                 --ref_annotation differential_expression/gencode.v22.annotation.chr20.gtf \

CHANGELOG.md

@@ -4,6 +4,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [unreleased]
+### Updated
+- `-profile conda` is no longer supported, users should use `-profile standard` (Docker) or `-profile singularity` instead
+- `nextflow run epi2me-labs/wf-transcriptomes --version` will now print the workflow version number and exit
+- Use parameter `--transcriptome-source` to define precalculated, reference-based or denovo
+
 ## [v0.1.6]
 ### Updated
 - Removed sanitize option

Dockerfile

@@ -1,24 +0,0 @@
-ARG BASEIMAGE=ontresearch/base-workflow-image:v0.2.0
-FROM $BASEIMAGE
-ARG ENVFILE=environment.yaml
-
-COPY $ENVFILE $HOME/environment.yaml
-RUN \
-    . $CONDA_DIR/etc/profile.d/micromamba.sh \
-    && micromamba activate \
-    && micromamba install -n base --file $HOME/environment.yaml \
-    && micromamba clean --all --yes \
-    && fix-permissions $CONDA_DIR \
-    && fix-permissions $HOME \
-    && rm -rf $CONDA_DIR/conda-meta \
-    && rm -rf $CONDA_DIR/include \
-    && 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

@@ -88,10 +88,9 @@ to run the workflow.
 
 The workflow can currently be run using either
 [Docker](https://www.docker.com/products/docker-desktop),
-[Singularity](https://sylabs.io/singularity/) or
+[Singularity](https://sylabs.io/singularity/) to provide isolation of
-[conda](https://docs.conda.io/en/latest/miniconda.html) to provide isolation of
 the required software. Each method is automated out-of-the-box provided
-either docker, singularity or conda is installed.
+either docker or singularity is installed.
 
 It is not required to clone or download the git repository in order to run the workflow.
 For more information on running EPI2ME Labs workflows [visit out website](https://labs.epi2me.io/wfindex).
@@ -290,7 +289,6 @@ in `${out_dir}/jaffal_output_${sample_id}` you will find:
 * [nextflow](https://www.nextflow.io/)
 * [docker](https://www.docker.com/products/docker-desktop)
 * [Singularity](https://sylabs.io/singularity/)
-* [conda](https://docs.conda.io/en/latest/miniconda.html)
 * [racon](https://github.com/isovic/racon)
 * [spoa](https://github.com/rvaser/spoa)
 * [inONclust](https://github.com/ksahlin/isONclust)

bin/report.py

@@ -511,7 +511,7 @@ def pychopper_plots(report, pychop_report):
     ### Pychopper summary statisitcs
 
     The following plots summarize [pychopper] output
-    (https://github.com/nanoporetech/pychopper)
+    (https://github.com/epi2me-labs/pychopper)
 
     * **Pr.found**: Reads with primers found in correct orientation at
      both ends.
@@ -604,7 +604,7 @@ def transcript_table(report, df_tmaps, max_rows):
     """
     section = report.add_section()
 
-    # Should wße put data from each sample into it's own table or have it
+    # Should we put data from each sample into it's own table or have it
     # all in single table and sample_id column? Currently it's the latter
 
     # drop some columns for the big table and do some filtering
@@ -932,7 +932,9 @@ def main():
             [Path(x) for x in args.gffcompare_dir],
             sample_ids)
 
-        transcript_table(report, df_tmaps, args.isoform_table_nrows)
+        if df_tmaps is not None:
+            # Skip this section. This needs some work
+            transcript_table(report, df_tmaps, args.isoform_table_nrows)
 
     if args.cluster_qc_dirs is not None:
         cluster_quality(args.cluster_qc_dirs, report, sample_ids)

bin/run_isonclust2.py

@@ -53,19 +53,19 @@ def build_job_tree():
         for x in batches]
     levels = OrderedDict()
     levels[0] = []
-    for k, bf in sorted(zip(batch_ids, batches), key=lambda x: x[0]):
+    for id_, bf in sorted(zip(batch_ids, batches), key=lambda x: x[0]):
         n = Node(
-            k,
+            id_,
-            "clusters/isONcluster_{}.cer".format(k),
+            "clusters/isONcluster_{}.cer".format(id_),
             None,
             None,
             None,
             0)
         n.Done = True
-        job_tree[k] = n
+        job_tree[id_] = n
         levels[0].append(n)
     level = 0
-    max_id = levels[0][-1].k
+    max_id = levels[0][-1].Id
     while len(levels[level]) != 1:  # Final level will be link
         next_level = level + 1
         levels[next_level] = []
@@ -84,7 +84,7 @@ def build_job_tree():
             levels[next_level].append(new_node)
             job_tree[max_id] = new_node
         level = next_level
-    root = job_tree[len(job_tree) - 1].k
+    root = job_tree[len(job_tree) - 1].Id
     job_tree[root].RightSide = True
 
     return job_tree, levels
@@ -121,7 +121,7 @@ def main():
         sub.call(cmd, shell=True)
     sub.call((
         "ln -s `realpath clusters/isONcluster_{}.cer` "
-        "isONcluster_root.cer".format(n.Id)), shell=True)
+        "isONcluster_ROOT.cer".format(n.Id)), shell=True)
 
 
 if __name__ == '__main__':

docs/links.md

@@ -3,7 +3,6 @@
 * [nextflow](https://www.nextflow.io/)
 * [docker](https://www.docker.com/products/docker-desktop)
 * [Singularity](https://sylabs.io/singularity/)
-* [conda](https://docs.conda.io/en/latest/miniconda.html)
 * [racon](https://github.com/isovic/racon)
 * [spoa](https://github.com/rvaser/spoa)
 * [inONclust](https://github.com/ksahlin/isONclust)

docs/quickstart.md

@@ -6,10 +6,9 @@ to run the workflow.
 
 The workflow can currently be run using either
 [Docker](https://www.docker.com/products/docker-desktop),
-[Singularity](https://sylabs.io/singularity/) or
+[Singularity](https://sylabs.io/singularity/) to provide isolation of
-[conda](https://docs.conda.io/en/latest/miniconda.html) to provide isolation of
 the required software. Each method is automated out-of-the-box provided
-either docker, singularity or conda is installed.
+either docker or singularity is installed.
 
 It is not required to clone or download the git repository in order to run the workflow.
 For more information on running EPI2ME Labs workflows [visit out website](https://labs.epi2me.io/wfindex).

environment.yaml

@@ -1,44 +0,0 @@
-name: epi2melabs-wf-transcriptomes
-channels:
-    - epi2melabs
-    - conda-forge
-    - bioconda
-    - defaults
-dependencies:
-    - python==3.8.*
-    - bokeh==2.4.3
-    - aplanat>=0.6.15
-    - epi2melabs
-    - minimap2==2.24
-    - samtools==1.14
-    - bedtools==2.30.0
-    - pychopper>=2.7.0
-    - pandas==1.3.5
-    - gffread==0.12.7
-    - gffcompare==0.11.2
-    - gffutils==0.10.1
-    - seqkit==2.2.0
-    - stringtie==2.1.1
-    - curl
-    - pysam==0.17.0
-    - racon==1.4.20
-    - spoa==3.4.0
-    - fastcat==0.4.10
-    - isonclust2==2.3
-    - parallel
-    - scikit-learn==1.0.2
-    - natsort
-# Fusion detection dependencies
-#    - bpipe=0.9.9.2
-    - java-jdk
-    - r-base
-    - gxx
-# Differential expression dependencies
-    - bioconductor-genomicfeatures
-    - bioconductor-drimseq
-    - bioconductor-edger
-    - bioconductor-dexseq
-    - bioconductor-stager
-    - r-dplyr
-    - r-tidyr
-    - salmon==1.9.0

lib/NfcoreSchema.groovy

@@ -70,7 +70,6 @@ class NfcoreSchema {
             'quiet',
             'syslog',
             'v',
-            'version',
 
             // Options for `nextflow run` command
             'ansi',

lib/NfcoreTemplate.groovy

@@ -66,6 +66,25 @@ class NfcoreTemplate {
         }
     }
 
+    //
+    // Generate version string
+    //
+    public static String version(workflow) {
+        String version_string = ""
+
+        if (workflow.manifest.version) {
+            def prefix_v = workflow.manifest.version[0] != 'v' ? 'v' : ''
+            version_string += "${prefix_v}${workflow.manifest.version}"
+        }
+
+        if (workflow.commitId) {
+            def git_shortsha = workflow.commitId.substring(0, 7)
+            version_string += "-g${git_shortsha}"
+        }
+
+        return version_string
+    }
+
     //
     // Construct and send completion email
     //
@@ -98,7 +117,7 @@ class NfcoreTemplate {
         misc_fields['Nextflow Compile Timestamp'] = workflow.nextflow.timestamp
 
         def email_fields = [:]
-        email_fields['version']           = workflow.manifest.version
+        email_fields['version']           = NfcoreTemplate.version(workflow)
         email_fields['runName']           = workflow.runName
         email_fields['success']           = workflow.success
         email_fields['dateComplete']      = workflow.complete
@@ -297,24 +316,23 @@ class NfcoreTemplate {
     //
     public static String dashedLine(monochrome_logs) {
         Map colors = logColours(monochrome_logs)
-        return "-${colors.dim}----------------------------------------------------${colors.reset}-"
+        return "${colors.dim}--------------------------------------------------------------------------------${colors.reset}"
     }
 
-    //
+    // epi2me-labs logo
-    // nf-core logo
-    //
     public static String logo(workflow, monochrome_logs) {
-        Map colors = logColours(monochrome_logs)
+        Map colors = NfcoreTemplate.logColours(monochrome_logs)
+        String workflow_name = workflow.manifest.name.split("/")[1]
+        String workflow_version = version(workflow)
         String.format(
-            """\n
+            """
-            ${dashedLine(monochrome_logs)}
+            ${colors.igreen}||||||||||   ${colors.reset}${colors.dim}_____ ____ ___ ____  __  __ _____      _       _
-                                                    ${colors.green},--.${colors.black}/${colors.green},-.${colors.reset}
+            ${colors.igreen}||||||||||  ${colors.reset}${colors.dim}| ____|  _ \\_ _|___ \\|  \\/  | ____|    | | __ _| |__  ___
-            ${colors.blue}        ___     __   __   __   ___     ${colors.green}/,-._.--~\'${colors.reset}
+            ${colors.yellow}|||||       ${colors.reset}${colors.dim}|  _| | |_) | |  __) | |\\/| |  _| _____| |/ _` | '_ \\/ __|
-            ${colors.blue}  |\\ | |__  __ /  ` /  \\ |__) |__         ${colors.yellow}}  {${colors.reset}
+            ${colors.yellow}|||||       ${colors.reset}${colors.dim}| |___|  __/| | / __/| |  | | |__|_____| | (_| | |_) \\__ \\
-            ${colors.blue}  | \\| |       \\__, \\__/ |  \\ |___     ${colors.green}\\`-._,-`-,${colors.reset}
+            ${colors.iblue}||||||||||  ${colors.reset}${colors.dim}|_____|_|  |___|_____|_|  |_|_____|    |_|\\__,_|_.__/|___/
-                                                    ${colors.green}`._,._,\'${colors.reset}
+            ${colors.iblue}||||||||||  ${colors.reset}${colors.bold}${workflow_name} ${workflow_version}${colors.reset}
-            ${colors.purple}  ${workflow.manifest.name} v${workflow.manifest.version}${colors.reset}
+            ${NfcoreTemplate.dashedLine(monochrome_logs)}
-            ${dashedLine(monochrome_logs)}
             """.stripIndent()
         )
     }

lib/WorkflowMain.groovy

@@ -10,22 +10,28 @@ class WorkflowMain {
             "  https://doi.org/10.1038/s41587-020-0439-x\n\n"
     }
 
-    // Print help to screen
+    // Generate help string
     public static String help(workflow, params, log) {
         String line_sep = ' \\ \n\t'
-        def command_example = params.wf.example_cmd.join(line_sep)
+        String command_example = params.wf.example_cmd.join(line_sep)
-        def command = 'nextflow run ' + workflow.manifest.name + line_sep + command_example
+        String command = 'nextflow run ' + workflow.manifest.name + line_sep + command_example
-        def help_string = ''
+        String help_string = ''
+        help_string += NfcoreTemplate.logo(workflow, params.monochrome_logs)
         help_string += NfcoreSchema.paramsHelp(workflow, params, command)
         help_string += '\n' + citation(workflow) + '\n'
         return help_string
     }
 
-    // Print parameter summary log to screen
+    // Generate parameter summary log string
     public static String paramsSummaryLog(workflow, params, log) {
-        def summary_log = ''
+        String workflow_version = NfcoreTemplate.version(workflow)
+        String summary_log = ''
+        summary_log += NfcoreTemplate.logo(workflow, params.monochrome_logs)
         summary_log += NfcoreSchema.paramsSummaryLog(workflow, params)
         summary_log += '\n' + citation(workflow) + '\n'
+        summary_log += NfcoreTemplate.dashedLine(params.monochrome_logs)
+        summary_log += "\nThis is ${workflow.manifest.name} ${workflow_version}.\n"
+        summary_log += NfcoreTemplate.dashedLine(params.monochrome_logs)
         return summary_log
     }
 
@@ -37,6 +43,23 @@ class WorkflowMain {
             System.exit(0)
         }
 
+        // Print workflow version and exit on --version
+        if (params.version) {
+            String workflow_version = NfcoreTemplate.version(workflow)
+            log.info "${workflow.manifest.name} ${workflow_version}"
+            System.exit(0)
+        }
+
+        // Explode on conda
+        // conda.enabled seems to be backward compatible but wrap this
+        // in a generic catch just in case
+        try {
+            if (workflow.session.config.conda.enabled) {
+                log.error "Sorry, this workflow is not compatible with Conda, please use -profile standard (Docker) or -profile singularity."
+                System.exit(1)
+            }
+        } catch(Exception e) {}
+
         // Validate workflow parameters via the JSON schema
         if (params.validate_params) {
             NfcoreSchema.validateParameters(workflow, params, log)

main.nf

@@ -306,7 +306,6 @@ process makeReport {
     input:
         path versions
         path "params.json"
-        val denovo
         path "pychopper_report/*"
         path"jaffal_csv/*"
         val sample_ids
@@ -322,7 +321,7 @@ process makeReport {
         // Convert the sample_id arrayList.
         sids = new BlankSeparatedList(sample_ids)
         def report_name = "wf-transcriptomes-report.html"
-        def OPT_DENOVO = denovo ? "--denovo" : ''
+        def OPT_DENOVO = params.transcriptome_source == "denovo" ? "--denovo" : ''
     """
     if [ -f "de_report/OPTIONAL_FILE" ]; then
         dereport=""
@@ -432,15 +431,15 @@ workflow pipeline {
             full_len_reads = summariseConcatReads.out.input_reads
             pychopper_report = file("$projectDir/data/OPTIONAL_FILE")
         }
-        if (params.transcriptome_assembly){
+        if (params.transcriptome_source != "precomputed"){
         
-            if (params.denovo){
+            if (params.transcriptome_source == "denovo"){
-                println("Doing de novo assembly")
+                log.info("Doing de novo assembly")
                 assembly = denovo_assembly(full_len_reads, ref_genome)
 
             } else {
                 build_minimap_index(ref_genome)
-                println("Doing reference based transcript analysis")
+                log.info("Doing reference based transcript analysis")
                 assembly = reference_assembly(build_minimap_index.out.index, ref_genome, full_len_reads)
             }
             assembly_stats = assembly.stats.map{ it -> it[1]}.collect()
@@ -455,7 +454,7 @@ workflow pipeline {
 
             run_gffcompare(merge_gff_bundles.out.gff, ref_annotation)
 
-            if (params.denovo){
+            if (params.transcriptome_source == "denovo"){
                 // Use the per-sample, de novo-assembled CDS
                 seq_for_transcriptome_build = assembly.cds
             }else {
@@ -463,7 +462,7 @@ workflow pipeline {
                 // So map this reference to all sample_ids
                 seq_for_transcriptome_build = sample_ids.flatten().combine(Channel.fromPath(params.ref_genome))
             }
-            
+
             get_transcriptome(
                 merge_gff_bundles.out.gff
                 .join(run_gffcompare.out.gffcmp_dir)
@@ -517,7 +516,6 @@ workflow pipeline {
         makeReport(
             software_versions,
             workflow_params,
-            params.denovo,
             pychopper_report,
             jaffal_out,
             summariseConcatReads.out.summary.map{it->it[0]}.collect(),
@@ -541,19 +539,18 @@ workflow pipeline {
 
        }
     
-        if (!use_ref_ann && !params.denovo && params.transcriptome_assembly){
+        if (!use_ref_ann && params.transcriptome_source == "reference-guided"){
             results =  assembly.stats.concat(
                        get_transcriptome.out.transcriptome.flatMap(map_sample_ids_cls))
                       .map {it -> it[1]}
                       .concat(results)
 
         }
-        if (params.denovo){
+        if (params.transcriptome_source == "denovo"){
             results = assembly.cds.concat(
                        assembly.stats,
                       seq_for_transcriptome_build,
                       get_transcriptome.out.transcriptome.flatMap(map_sample_ids_cls),
-                      merge_gff_bundles.out.gff,
                       assembly.opt_qual_ch.flatMap {
                           it ->
                           l = []
@@ -596,10 +593,12 @@ workflow {
         error = "--fastq: File doesn't exist, check path."
     }
 
-    if (!params.denovo && !params.ref_genome){
+    if (params.transcriptome_source == "precomputed" && !params.ref_transcriptome){
-        error = "--ref_genome must be supplied unless doing de novo assembly (--denovo)"
+        error = "As transcriptome source parameter is precomputed you must include a ref_transcriptome parameter"
+    }
+    if (params.transcriptome_source == "reference-guided" && !params.ref_genome){
+        error = "As transcriptome source is reference guided you must include a ref_genome parameter"
     }
-
     if (params.ref_genome){
         ref_genome = file(params.ref_genome, type: "file")
         if (!ref_genome.exists()) {
@@ -609,7 +608,7 @@ workflow {
         ref_genome = file("$projectDir/data/OPTIONAL_FILE")
     }
 
-    if (params.denovo && params.ref_annotation) {
+    if (params.transcriptome_source == "denovo" && params.ref_annotation) {
         error = "Reference annotation with de denovo assembly is not supported"
     }
 
@@ -648,7 +647,7 @@ workflow {
         condition_sheet = file("$projectDir/data/OPTIONAL_FILE")
     }
     if (error){
-        println(error)
+        throw new Exception(error)
     }else{
         reads = fastq_ingress([
             "input":params.fastq,

nextflow.config

@@ -15,10 +15,11 @@ params {
     fastq = null
     ref_genome = null
     ref_annotation = null
-    transcriptome_assembly = true
+    transcriptome_source = "reference-guided"
     threads = 4
      // Thresholds for viewing isoforms in report table
     isoform_table_nrows = 5000
+    
 
     out_dir = "output"
     sample = null
@@ -26,8 +27,9 @@ params {
     wfversion = "v0.1.6"
     aws_image_prefix = null
     aws_queue = null
-    report_name = "report"
     process_label = "isoforms"
+    analyse_unclassified = false
+    version = false
 
     monochrome_logs = false
     validate_params = true
@@ -72,52 +74,9 @@ params {
     disable_ping = false
 
     //// Denovo-specific parameters
-    denovo = false
+    
-
+    isOnClust2_batch_size = -1
-    // Batch size in kilobases (if -1 then it is calculated based on the number of cores and bases):
+    isOnClust2_sort_options = "--batch-size -1 --kmer-size 11 --window-size 15 --min-shared 5 --min-qual 7.0 --mapped-threshold 0.65 --aligned-threshold 0.2 --min-fraction 0.8 --min-prob-no-hits 0.0 -M -1 -P 500 -g 50 -c 150 -F 2"
-    batch_size = -1
-
-    // Maximum sequences per input batch (-1 means no limit):
-    batch_max_seq = -1
-
-    // Clustering mode:
-    cls_mode = "sahlin"
-
-    // Kmer size:
-    kmer_size = 11
-
-    // Window size:
-    window_size = 15
-
-    // Minimum cluser size in the left batch:
-    min_left_cls = 2
-
-    // Consensus period (-1 means no consensus):
-    consensus_period = 500
-
-    // Minimum consensus sample size:
-    consensus_minimum = 50
-
-    // Maximum consensus sample size:
-    consensus_maximum = -150
-
-    // Minimum number of minimizers shared between read and cluster:
-    min_shared = 5
-
-    // Minimum average quality value:
-    min_qual = 7.0
-
-    // Minmum mapped fraction of read to be included in cluster:
-    mapped_threshold = 0.65
-
-    // Minimum aligned fraction of read to be included in cluster:
-    aligned_threshold = 0.2
-
-    // Minimum fraction of minimizers shared compared to best hit, in order to continue mapping:
-    min_fraction = 0.8
-
-    // 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
@@ -146,6 +105,8 @@ params {
           "--jaffal_genome hg38",
           "--jaffal_annotation genCode22"
       ]
+    agent = null
+    container_sha = "sha3d3c83523695550f398cbe095551b1192de5085a"
     }
 }
 
@@ -153,10 +114,10 @@ manifest {
     name            = 'epi2me-labs/wf-transcriptomes'
     author          = 'Oxford Nanopore Technologies'
     homePage        = 'https://github.com/epi2me-labs/wf-transcriptomes'
-    description     = 'RNA/cDNA isoform analysis workflow'
+    description     = 'Transcriptome analysis workflow including gene fusions and differential expression'
     mainScript      = 'main.nf'
     nextflowVersion = '>=20.10.0'
-    //version       = 'v0.0.1'
+    version         = 'v0.1.6'
 }
 
 executor {
@@ -166,11 +127,15 @@ executor {
     }
 }
 
+epi2melabs {
+  tags = "isoforms, transcriptomics, denovo"
+}
+
 // used by default for "standard" (docker) and singularity profiles,
 // other profiles may override.
 process {
     withLabel:isoforms {
-        container = "ontresearch/wf-transcriptomes:${params.wfversion}"
+        container = "ontresearch/wf-transcriptomes:${params.wf.container_sha}"
     }
     shell = ['/bin/bash', '-euo', 'pipefail']
 }
@@ -197,21 +162,9 @@ profiles {
     }
 
 
-    // profile using conda environments
     conda {
-    docker.enabled = false
+        conda.enabled = true
-    process {
-        withLabel:isoforms {
-            conda = "${projectDir}/environment.yaml"
-        }
-        shell = ['/bin/bash', '-euo', 'pipefail']
     }
-    conda {
-        enabled = true // required for 22.08
-        cacheDir = ""
-        useMamba = true
-    }
-}
 
     // Using AWS batch.
     // May need to set aws.region and aws.batch.cliPath
@@ -221,7 +174,7 @@ profiles {
             queue = "${params.aws_queue}"
             memory = '8G'
             withLabel:isoforms {
-                container = "${params.aws_image_prefix}-wf-transcriptomes:${params.wfversion}"
+                container = "${params.aws_image_prefix}-wf-transcriptomes:${params.wf.container_sha}-root"
             }
             shell = ['/bin/bash', '-euo', 'pipefail']
         }

subworkflows/denovo_assembly.nf

@@ -170,7 +170,7 @@ process make_batches {
     minimum_batch_size = 2000
     """
     b=0
-    if [ ${params.batch_size} -lt \$b ];
+    if [ ${params.isOnClust2_batch_size} -lt \$b ];
     then
         nr_bases=\$(seqkit stats -T $fastq|cut -f 5| sed '2q;d')
         let batch_size=\$nr_bases/1000/$maxcpus
@@ -179,19 +179,13 @@ process make_batches {
                 batch_size=$minimum_batch_size
         fi
     else
-        batch_size=${params.batch_size}
+        batch_size=${params.isOnClust2_batch_size}
     fi
 
     echo "Batch size:\$batch_size";
     echo "Num bases: \$nr_bases";
 
-    init_cls_options="--batch-size \$batch_size --kmer-size ${params.kmer_size} --window-size ${params.window_size} \
+    mkdir -p sorted; isONclust2 sort $params.isOnClust2_sort_options -v -o sorted $fastq;
-        --min-shared ${params.min_shared} --min-qual ${params.min_qual} \
-        --mapped-threshold ${params.mapped_threshold} --aligned-threshold ${params.aligned_threshold} \
-        --min-fraction ${params.min_fraction} --min-prob-no-hits ${params.min_prob_no_hits} \
-        -M ${params.batch_max_seq} -P ${params.consensus_period} -g ${params.consensus_minimum} \
-        -c ${params.consensus_maximum} -F ${params.min_left_cls} "
-    mkdir -p sorted; isONclust2 sort \$init_cls_options -v -o sorted $fastq;
     """
 
 }