New changes towards Enchantr 0.0.5

.github/workflows/ci.yml

@@ -79,7 +79,7 @@ jobs:
         NXF_VER:
           - "21.10.3"
           - "latest-everything"
-        profile: ["test_immcantation_devel"]
+        profile: ["test_assembled_immcantation_devel", "test_raw_immcantation_devel"]
       fail-fast: false
     steps:
       - name: Check out pipeline code

CHANGELOG.md

@@ -3,6 +3,18 @@
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
+## [3.0dev] -
+
+### `Added`
+
+- Added compulsory AIRR fields in input samplesheet.
+
+### `Fixed`
+
+### `Dependencies`
+
+### `Deprecated`
+
 ## [2.3.0] - 2022-09-22 "Expelliarmus"
 
 ### `Added`

bin/check_samplesheet.py

@@ -61,6 +61,10 @@ def check_samplesheet(file_in):
             "species",
             "pcr_target_locus",
             "single_cell",
+            "sex",
+            "tissue",
+            "biomaterial_provider",
+            "age"
         ]
         header = [x.strip('"') for x in fin.readline().strip().split("\t")]
         for col in REQUIRED_COLUMNS:

conf/modules.config

@@ -286,7 +286,7 @@ process {
 
     withName: ADD_META_TO_TAB {
         publishDir = [
-            path: { "${params.outdir}/vdj_annotation/06-annotat-metadata/${meta.id}" },
+            path: { "${params.outdir}/vdj_annotation/06-annotate-metadata/${meta.id}" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
@@ -352,13 +352,26 @@ process {
         ]
     }
 
-    withName: DEFINE_CLONES {
+    withName: DEFINE_CLONES_COMPUTE {
         publishDir = [
             path: { "${params.outdir}/clonal_analysis/define_clones" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
-        ext.args = ['outname':'', 'model':'hierarchical', 'method':'nt', 'linkage':'single', 'outputby':'sample_id']
+        ext.args = ['outname':'', 'model':'hierarchical',
+                    'method':'nt', 'linkage':'single',
+                    'outputby':'sample_id', 'min_n':30]
+    }
+
+    withName: DEFINE_CLONES_REPORT {
+        publishDir = [
+            path: { "${params.outdir}/clonal_analysis/define_clones" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+        ext.args = ['outname':'', 'model':'hierarchical',
+                    'method':'nt', 'linkage':'single',
+                    'outputby':'sample_id', 'min_n':30]
     }
 
     withName: DOWSER_LINEAGES {

conf/test.config

@@ -20,7 +20,7 @@ params {
     max_time   = '6.h'
 
     // Input data
-    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/Metadata_test.tsv'
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/Metadata_test_airr.tsv'
     cprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/C_primers.fasta'
     vprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/V_primers.fasta'
     imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
@@ -35,3 +35,11 @@ params {
     umi_start = 6
     umi_position = 'R1'
 }
+
+process{
+    withName:"DEFINE_CLONES*"{
+        ext.args = ['outname':'', 'model':'hierarchical',
+                    'method':'nt', 'linkage':'single',
+                    'outputby':'sample_id', 'min_n':10]
+    }
+}

conf/test_immcantation_devel.config → conf/test_assembled_immcantation_devel.config

@@ -4,7 +4,7 @@
  * -------------------------------------------------
  * Defines bundled input files and everything required
  * to run a fast and simple test. Use as follows:
- *   nextflow run nf-core/airrflow -profile test,<docker/singularity>
+ *   nextflow run nf-core/airrflow -profile test_assembled_immcantation_devel,<docker/singularity>
  */
 
 params {
@@ -19,8 +19,8 @@ params {
     // Input data
     mode = 'assembled'
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-reveal/test_reveal_metadata.tsv'
-    imgtdb_base = '/usr/local/share/germlines/imgt'
-    igblast_base = '/usr/local/share/igblast'
+    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
     igphyml = '/usr/local/share/igphyml/src/igphyml'
 
     reassign = true

conf/test_fetchimgt.config

@@ -20,7 +20,7 @@ params {
     max_time   = '6.h'
 
     // Input data
-    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/Metadata_test.tsv'
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/Metadata_test_airr.tsv'
     cprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/C_primers.fasta'
     vprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/V_primers.fasta'
 
@@ -33,3 +33,12 @@ params {
     umi_start = 6
     umi_position = 'R1'
 }
+
+process{
+    withName:"DEFINE_CLONES*"{
+        ext.args = ['outname':'', 'model':'hierarchical',
+                    'method':'nt', 'linkage':'single',
+                    'outputby':'sample_id', 'min_n':10]
+    }
+}
+

conf/test_full.config

@@ -15,7 +15,7 @@ params {
     config_profile_description = 'Full test dataset to check pipeline function'
 
     // Input data
-    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/metadata_pcr_umi_airr.tsv'
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/metadata_pcr_umi_airr_300.tsv'
     cprimers = 's3://nf-core-awsmegatests/airrflow/input_data/pcr_umi/cprimers.fasta'
     vprimers = 's3://nf-core-awsmegatests/airrflow/input_data/pcr_umi/vprimers.fasta'
     imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'

conf/test_no_umi.config

@@ -27,7 +27,7 @@ params {
     umi_length = 0
 
     // Input data
-    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-no-umi/Metadata_test-no-umi.tsv'
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-no-umi/Metadata_test-no-umi_airr.tsv'
     cprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-no-umi/Greiff2014_CPrimers.fasta'
     vprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-no-umi/Greiff2014_VPrimers.fasta'
     imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
@@ -39,6 +39,11 @@ process {
     // When not using UMIs, set the coord parameter based on source (e.g., sra or illumina)
     withName: PRESTO_ASSEMBLEPAIRS_SANS_UMI {
             ext.args = '--rc tail --coord sra --maxerror 0.3'
-        }
-
+    }
+    withName:"DEFINE_CLONES*"{
+        ext.args = ['outname':'', 'model':'hierarchical',
+                    'method':'nt', 'linkage':'single',
+                    'outputby':'sample_id', 'min_n':10]
+    }
 }
+

conf/test_nocluster.config

@@ -20,7 +20,7 @@ params {
     max_time   = '6.h'
 
     // Input data
-    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/Metadata_test.tsv'
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/Metadata_test_airr.tsv'
     cprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/C_primers.fasta'
     vprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/V_primers.fasta'
     imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
@@ -36,3 +36,11 @@ params {
     umi_position = 'R1'
     cluster_sets = false
 }
+
+process{
+    withName:"DEFINE_CLONES*"{
+        ext.args = ['outname':'', 'model':'hierarchical',
+                    'method':'nt', 'linkage':'single',
+                    'outputby':'sample_id', 'min_n':10]
+    }
+}

conf/test_raw_immcantation_devel.config

@@ -0,0 +1,54 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/airrflow -profile test_raw_immcantation_devel,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Test profile'
+    config_profile_description = 'Minimal test dataset to check pipeline function'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '6.GB'
+    max_time   = '6.h'
+
+    // Input data
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/Metadata_test_airr.tsv'
+    cprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/C_primers.fasta'
+    vprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/V_primers.fasta'
+
+    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    igphyml = '/usr/local/share/igphyml/src/igphyml'
+
+    mode = 'fastq'
+
+    library_generation_method = 'specific_pcr_umi'
+    cprimer_position = 'R1'
+    index_file = true
+    umi_length = 8
+    umi_start = 6
+    umi_position = 'R1'
+}
+
+process{
+    withLabel:immcantation{
+        container = 'immcantation/suite:devel'
+    }
+    withName:"DEFINE_CLONES*"{
+        ext.args = ['outname':'', 'model':'hierarchical',
+                    'method':'nt', 'linkage':'single',
+                    'outputby':'sample_id', 'min_n':10]
+    }
+}
+
+env {
+   PYTHONNOUSERSITE = 0
+}

conf/test_tcr.config

@@ -29,10 +29,18 @@ params {
 
 
     // Input data
-    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-tcr/TCR_metadata.tsv'
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-tcr/TCR_metadata_airr.tsv'
     cprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-tcr/cprimers.fasta'
     race_linker = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-tcr/linker.fasta'
     imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
     igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
 
 }
+
+process{
+    withName:"DEFINE_CLONES*"{
+        ext.args = ['outname':'', 'model':'hierarchical',
+                    'method':'nt', 'linkage':'single',
+                    'outputby':'sample_id', 'min_n':10]
+    }
+}