Adjusted fixes for AWS index handling

.github/workflows/ci.yml

@@ -64,7 +64,7 @@ jobs:
           nextflow run ${GITHUB_WORKSPACE} -profile test_tsv,docker --save_reference
       - name: REFERENCE Basic workflow, with supplied indices
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test_tsv,docker --bwa_index 'results/reference_genome/bwa_index/BWAIndex/Mammoth_MT_Krause.fasta' --fasta_index 'https://github.com/nf-core/test-datasets/blob/eager/reference/Mammoth/Mammoth_MT_Krause.fasta.fai' 
+          nextflow run ${GITHUB_WORKSPACE} -profile test_tsv,docker --bwa_index 'results/reference_genome/bwa_index/BWAIndex/' --fasta_index 'https://github.com/nf-core/test-datasets/blob/eager/reference/Mammoth/Mammoth_MT_Krause.fasta.fai' 
       - name: REFERENCE Run the basic pipeline with FastA reference with `fna` extension
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile test_tsv_fna,docker

assets/nf-core_eager_dummy.txt

@@ -0,0 +1 @@
+This is a dummy file for when we need a 'fake' file to satisfy all nextflow channel inputs being filled, even if we actually only use one.

assets/nf-core_eager_dummy2.txt

@@ -0,0 +1 @@
+This is a second dummy file for when we need a 'fake' file to satisfy all nextflow channel inputs being filled, even if we actually only use one.

conf/benchmarking_vikingfish.config

@@ -12,7 +12,7 @@ params {
    config_profile_description = "A 'fullsized' benchmarking profile for deepish sequencing aDNA data" 
 
    //Input data
-   input = 'https://raw.githubusercontent.com/jfy133/test-datasets/eager/testdata/Benchmarking/benchmarking_vikingfish.tsv'   
+   input = 'https://raw.githubusercontent.com/nf-core/test-datasets/eager/testdata/Benchmarking/benchmarking_vikingfish.tsv'   
    // Genome reference
    fasta = 'https://ftp.ncbi.nlm.nih.gov/genomes/refseq/vertebrate_other/Gadus_morhua/representative/GCF_902167405.1_gadMor3.0/GCF_902167405.1_gadMor3.0_genomic.fna.gz'
 

conf/benchmarking_vikingfish_single.config

@@ -0,0 +1,56 @@
+/*
+ * -------------------------------------------------
+ *  Nextflow config file for running tests
+ * -------------------------------------------------
+ * Defines bundled input files and everything required
+ * to run a fast and simple test. Use as follows:
+ * nextflow run nf-core/eager -profile test, docker (or singularity, or conda)
+ */
+
+params {
+   config_profile_name = 'nf-core/eager benchmarking - Viking Fish profile'
+   config_profile_description = "A 'fullsized' benchmarking profile for deepish sequencing aDNA data" 
+
+   //Input data
+   input = 'https://raw.githubusercontent.com/nf-core/test-datasets/eager/testdata/Benchmarking/benchmarking_vikingfish_single.tsv'   
+   // Genome reference
+   fasta = 'https://ftp.ncbi.nlm.nih.gov/genomes/refseq/vertebrate_other/Gadus_morhua/representative/GCF_902167405.1_gadMor3.0/GCF_902167405.1_gadMor3.0_genomic.fna.gz'
+
+   bwaalnn = 0.04
+   bwaalnl = 1024
+
+   run_bam_filtering = true
+   bam_discard_unmapped = true
+   bam_unmapped_type = 'discard'
+   bam_mapping_quality_threshold = 25
+
+   run_genotyping = true
+   genotyping_tool = 'hc'
+   genotyping_source = 'raw'
+   gatk_ploidy = 2
+
+}
+
+process {
+   withName:'adapter_removal'{
+      cpus = { check_max( 8, 'cpus' ) }
+      memory = { check_max( 16.GB * task.attempt, 'memory' ) }
+      time = { check_max( 2.h * task.attempt, 'time' ) }
+   }
+   withName:'bwa'{
+      cpus = { check_max( 8, 'cpus' ) }
+      memory = { check_max( 16.GB * task.attempt, 'memory' ) }
+      time = { check_max( 8.h * task.attempt, 'time' ) }
+   }
+   withName:'dedup'{
+      cpus = { check_max( 8, 'cpus' ) }
+      memory = { check_max( 16.GB * task.attempt, 'memory' ) }
+      time = { check_max( 4.h * task.attempt, 'time' ) }
+   }
+   withName:'genotyping_hc'{
+     cpus = { check_max( 8, 'cpus' ) }
+     memory = { check_max( 16.GB * task.attempt, 'memory' ) }
+     time = { check_max( 8.h * task.attempt, 'time' ) }
+   }
+
+}

docs/usage.md

@@ -362,7 +362,7 @@ Use this if you do not have pre-made reference FASTA indices for `bwa`, `samtool
 
 #### `--bwa_index`
 
-If you want to use pre-existing `bwa index` indices, please supply the path **and file** to the FASTA you also specified in `--fasta` (see above). EAGER2 will automagically detect the index files by searching for the FASTA filename with the corresponding `bwa` index file suffixes.
+If you want to use pre-existing `bwa index` indices, please supply the **directory** to the FASTA you also specified in `--fasta` (see above). EAGER2 will automagically detect the index files by searching for the FASTA filename with the corresponding `bwa` index file suffixes.
 
 For example:
 
@@ -371,7 +371,7 @@ nextflow run nf-core/eager \
 -profile test,docker \
 --input '*{R1,R2}*.fq.gz'
 --fasta 'results/reference_genome/bwa_index/BWAIndex/Mammoth_MT_Krause.fasta' \
---bwa_index 'results/reference_genome/bwa_index/BWAIndex/Mammoth_MT_Krause.fasta'
+--bwa_index 'results/reference_genome/bwa_index/BWAIndex/'
 ```
 
 > `bwa index` does not give you an option to supply alternative suffixes/names for these indices. Thus, the file names generated by this command _must not_ be changed, otherwise EAGER2 will not be able to find them.