Merge pull request #1 from charles-plessy/minus-s-option

Minus s option

conf/modules.config

@@ -18,6 +18,14 @@ process {
         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
     ]
 
+    withName: 'LAST_LASTDB' {
+        // See https://gitlab.com/mcfrith/last/-/blob/main/doc/lastdb.rst for details
+        // -R01: uppercase all sequences and then lowercase simple repeats
+        // -c: soft-mask lowercase letters
+        // -S2: index both strands
+        ext.args = { "-R01 -c -u${params.seed} -S2" }
+    }
+
     withName: 'LAST_SPLIT_O2M' {
         ext.prefix = { "${meta.id}.o2m_aln" }
         ext.args = { "--reverse -m${params.last_split_mismap}" }
@@ -47,6 +55,11 @@ process {
         ext.args = { "--split-f=MAF+ ${params.lastal_args} ${params.lastal_extr_args}" }
     }
 
+    withName: 'LAST_LASTAL_M2M' {
+        ext.prefix = { "${meta.id}.m2o_aln" }
+        ext.args = { "${params.lastal_args} ${params.lastal_extr_args}" }
+    }
+
     withName: 'LAST_DOTPLOT_O2O' {
         ext.prefix = { "${meta.id}.o2o_plt" }
         ext.args = { "--rot2=h --sort2=3 --strands2=1 ${params.dotplot_options}" }

conf/test.config

@@ -24,6 +24,7 @@ params {
 
     // Target
     target = params.pipelines_testdata_base_path + 'modules/data/genomics/sarscov2/genome/genome.fasta'
+    lastal_args = '-C2'  // Remove -D1e9 because the virus genomes are so small.
 
     // Genome references
     genome = 'R64-1-1'

docs/usage.md

@@ -8,7 +8,13 @@
 
 You need at least two genomes, a _target_, which will be indexed, and one or more _queries_, which will be aligned to the _target_. Paths to the genome files for the _queries_ are passed with the _nf-core_ samplesheet `--input` system, and path to the genome file of the _target_ is passed with the `--target` parameter. Note that the computation is not symmetric: inverting _target_ and _query_ does not lead to strictly identical results.
 
-## Samplesheet input
+## Input
+
+### Target genome
+
+The target genome sequence is taken from a FASTA-formated file passed by the `--target` parameter. Its masking information (sequences in lower-case letters) is first discarded, and then simple repeats (like `cacacacacacacacac`) are converted to lower-case (`lastdb -R01`). The lowercased letters in the _target_ **and** in the _query_ will be excluded for initial matches (`lastdb -c`). Both strands of the genome are indexed (`lastdb -S2`).
+
+### Samplesheet for query genome(s)
 
 You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 2 columns, a header row and single or multiple sample rows (genome samples) as shown in the examples below.
 
@@ -96,10 +102,14 @@ An [example samplesheet](../assets/samplesheet.csv) has been provided with the p
 
 ## Fixed arguments (taken from the [LAST cookbook][] and the [LAST tuning][] manual)
 
-- The `lastdb` step soft-masks simple repeats by default, (`-c -R01`).It indexes both strands (`-S2`), which increases speed at the expense of memory usage.
-
 - The `last-train` commands runs with `--revsym` as the DNA strands play equivalent roles in the studied genomes.
 
+- The `lastdb` command takes all CPU cores available (`lastdb -P0`). Note that
+  when using more than one core, the output of `lastdb` may vary, causing the
+  order of tied positions to change. To prevent this to happen, you can pass a
+  nextflow parameter file to the pipeline that reduces the number of CPUs
+  allocated to `LAST_LASTDB` to 1.
+
 ## Running the pipeline
 
 The typical command for running the pipeline is as follows:

modules.json

@@ -17,37 +17,37 @@
                     },
                     "last/dotplot": {
                         "branch": "master",
-                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "git_sha": "3fa9017b55b9c26e1c327ca189d3942b55f4d496",
                         "installed_by": ["modules"]
                     },
                     "last/lastal": {
                         "branch": "master",
-                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "git_sha": "3fa9017b55b9c26e1c327ca189d3942b55f4d496",
                         "installed_by": ["modules"]
                     },
                     "last/lastdb": {
                         "branch": "master",
-                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "git_sha": "3fa9017b55b9c26e1c327ca189d3942b55f4d496",
                         "installed_by": ["modules"]
                     },
                     "last/mafswap": {
                         "branch": "master",
-                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "git_sha": "3fa9017b55b9c26e1c327ca189d3942b55f4d496",
                         "installed_by": ["modules"]
                     },
                     "last/split": {
                         "branch": "master",
-                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "git_sha": "3fa9017b55b9c26e1c327ca189d3942b55f4d496",
                         "installed_by": ["modules"]
                     },
                     "last/train": {
                         "branch": "master",
-                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "git_sha": "3fa9017b55b9c26e1c327ca189d3942b55f4d496",
                         "installed_by": ["modules"]
                     },
                     "multiqc": {
                         "branch": "master",
-                        "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a",
+                        "git_sha": "8f2062e7b4185590fb9f43c275381a31a6544fc0",
                         "installed_by": ["modules"]
                     }
                 }