Merge pull request #121 from tkchafin/db_params

Db params

Author: tkchafin

.github/workflows/ci.yml

@@ -35,19 +35,9 @@ jobs:
         with:
           version: "${{ matrix.NXF_VER }}"
 
-      - name: Download the NCBI taxdump database
-        run: |
-          mkdir ncbi_taxdump
-          curl -L https://ftp.ncbi.nih.gov/pub/taxonomy/new_taxdump/new_taxdump.tar.gz | tar -C ncbi_taxdump -xzf -
-
-      - name: Download the BUSCO lineage database
-        run: |
-          mkdir busco_database
-          curl -L https://tolit.cog.sanger.ac.uk/test-data/resources/busco/blobtoolkit.GCA_922984935.2.2023-08-03.lineages.tar.gz | tar -C busco_database -xzf -
-
       - name: Run pipeline with test data
         # You can customise CI pipeline run tests as required
         # For example: adding multiple test runs with different parameters
         # Remember that you can parallelise this by using strategy.matrix
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --taxdump $PWD/ncbi_taxdump --busco $PWD/busco_database --outdir ./results
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results

CHANGELOG.md

@@ -3,7 +3,7 @@
 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).
 
-## [[0.7.0](https://github.com/sanger-tol/blobtoolkit/releases/tag/0.7.0)] – Psyduck – [2024-10-02]
+## [[0.7.0](https://github.com/sanger-tol/blobtoolkit/releases/tag/0.7.0)] – Psyduck – [2024-11-20]
 
 The pipeline is now considered to be a complete and suitable replacement for the Snakemake version.
 
@@ -13,6 +13,7 @@ The pipeline is now considered to be a complete and suitable replacement for the
   to indicate in the samplesheet whether the reads are paired or single.
 - Updated the Blastn settings to allow 7 days runtime at most, since that
   covers 99.7% of the jobs.
+- Allow database inputs to be optionally compressed (`.tar.gz`)
 
 ### Software dependencies
 

assets/test/mMelMel3.1.buscogenes.dmnd

@@ -30,11 +30,11 @@ params {
     taxon     = "Meles meles"
 
     // Databases
-    taxdump = "/lustre/scratch123/tol/resources/taxonomy/latest/new_taxdump"
-    busco   = "/lustre/scratch123/tol/resources/nextflow/busco/blobtoolkit.GCA_922984935.2.2023-08-03"
-    blastp  = "${projectDir}/assets/test/mMelMel3.1.buscogenes.dmnd"
-    blastx  = "${projectDir}/assets/test/mMelMel3.1.buscoregions.dmnd"
-    blastn  = "${projectDir}/assets/test/nt_mMelMel3.1"
+    taxdump = "https://ftp.ncbi.nlm.nih.gov/pub/taxonomy/new_taxdump/new_taxdump.tar.gz"
+    busco   = "https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/resources/blobtoolkit.GCA_922984935.2.2023-08-03.tar.gz"
+    blastp  = "https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/resources/mMelMel3.1.buscogenes.dmnd.tar.gz"
+    blastx  = "https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/resources/mMelMel3.1.buscoregions.dmnd.tar.gz"
+    blastn  = "https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/resources/nt_mMelMel3.1.tar.gz"
 
     // Need to be set to avoid overfilling /tmp
     use_work_dir_as_temp = true

assets/test/mMelMel3.1.buscoregions.dmnd

@@ -25,11 +25,11 @@ params {
     taxon     = "Laetiporus sulphureus"
 
     // Databases
-    taxdump = "/lustre/scratch123/tol/resources/taxonomy/latest/new_taxdump"
+    taxdump = "https://ftp.ncbi.nlm.nih.gov/pub/taxonomy/new_taxdump/new_taxdump.tar.gz"
     busco   = "/lustre/scratch123/tol/resources/busco/latest"
-    blastp  = "${projectDir}/assets/test_full/gfLaeSulp1.1.buscogenes.dmnd"
-    blastx  = "${projectDir}/assets/test_full/gfLaeSulp1.1.buscoregions.dmnd"
-    blastn  = "${projectDir}/assets/test_full/nt_gfLaeSulp1.1"
+    blastp  = "https://tolit.cog.sanger.ac.uk/test-data/Laetiporus_sulphureus/resources/gfLaeSulp1.1.buscogenes.dmnd.tar.gz"
+    blastx  = "https://tolit.cog.sanger.ac.uk/test-data/Laetiporus_sulphureus/resources/gfLaeSulp1.1.buscoregions.dmnd.tar.gz"
+    blastn  = "https://tolit.cog.sanger.ac.uk/test-data/Laetiporus_sulphureus/resources/nt_gfLaeSulp1.1.tar.gz"
 
     // Need to be set to avoid overfilling /tmp
     use_work_dir_as_temp = true

assets/test/nt_mMelMel3.1/nt_mMelMel3.1.ndb

@@ -31,11 +31,11 @@ params {
     taxon     = "Meles meles"
 
     // Databases
-    taxdump = "/lustre/scratch123/tol/resources/taxonomy/latest/new_taxdump"
-    busco   = "/lustre/scratch123/tol/resources/nextflow/busco/blobtoolkit.GCA_922984935.2.2023-08-03"
-    blastp  = "${projectDir}/assets/test/mMelMel3.1.buscogenes.dmnd"
-    blastx  = "${projectDir}/assets/test/mMelMel3.1.buscoregions.dmnd"
-    blastn  = "${projectDir}/assets/test/nt_mMelMel3.1/"
+    taxdump = "https://ftp.ncbi.nlm.nih.gov/pub/taxonomy/new_taxdump/new_taxdump.tar.gz"
+    busco   = "https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/resources/blobtoolkit.GCA_922984935.2.2023-08-03.tar.gz"
+    blastp  = "https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/resources/mMelMel3.1.buscogenes.dmnd.tar.gz"
+    blastx  = "https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/resources/mMelMel3.1.buscoregions.dmnd.tar.gz"
+    blastn  = "https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/resources/nt_mMelMel3.1.tar.gz"
 
     // Need to be set to avoid overfilling /tmp
     use_work_dir_as_temp = true

assets/test/nt_mMelMel3.1/nt_mMelMel3.1.nhr

@@ -78,15 +78,20 @@ The BlobToolKit pipeline can be run in many different ways. The default way requ
 
 It is a good idea to put a date suffix for each database location so you know at a glance whether you are using the latest version. We are using the `YYYY_MM` format as we do not expect the databases to be updated more frequently than once a month. However, feel free to use `DATE=YYYY_MM_DD` or a different format if you prefer.
 
+Note that all input databases may be optionally passed directly to the pipeline compressed as `.tar.gz`, and the pipeline will handle decompression.
+The instructions below show how to build each input database in _two_ forms: decompressed _and_ compressed. You may not need to do both. Select the one that is most appropriate for how you want to use the pipeline.
+
 #### 1. NCBI taxdump database
 
 Create the database directory, retrieve and decompress the NCBI taxonomy:
 
 ```bash
 DATE=2024_10
 TAXDUMP=/path/to/databases/taxdump_${DATE}
+TAXDUMP_TAR=/path/to/databases/taxdump_${DATE}.tar.gz
 mkdir -p "$TAXDUMP"
-curl -L ftp://ftp.ncbi.nih.gov/pub/taxonomy/new_taxdump/new_taxdump.tar.gz | tar -xzf - -C "$TAXDUMP"
+curl -L ftp://ftp.ncbi.nih.gov/pub/taxonomy/new_taxdump/new_taxdump.tar.gz -o $TAXDUMP_TAR
+tar -xzf $TAXDUMP_TAR -C "$TAXDUMP"
 ```
 
 #### 2. NCBI nucleotide BLAST database
@@ -96,6 +101,7 @@ Create the database directory and move into the directory:
 ```bash
 DATE=2024_10
 NT=/path/to/databases/nt_${DATE}
+NT_TAR=/path/to/databases/nt_${DATE}.tar.gz
 mkdir -p $NT
 cd $NT
 ```
@@ -113,6 +119,11 @@ done
 wget "https://ftp.ncbi.nlm.nih.gov/blast/db/v5/taxdb.tar.gz" &&
 tar xf taxdb.tar.gz -C $NT &&
 rm taxdb.tar.gz
+
+# Compress and cleanup
+cd ..
+tar -cvzf $NT_TAR $NT
+rm -r $NT
 ```
 
 #### 3. UniProt reference proteomes database
@@ -126,6 +137,7 @@ Create the database directory and move into the directory:
 ```bash
 DATE=2024_10
 UNIPROT=/path/to/databases/uniprot_${DATE}
+UNIPROT_TAR=/path/to/databases/uniprot_${DATE}.tar.gz
 mkdir -p $UNIPROT
 cd $UNIPROT
 ```
@@ -152,6 +164,12 @@ diamond makedb -p 16 --in reference_proteomes.fasta.gz --taxonmap reference_prot
 # clean up
 mv extract/{README,STATS} .
 rm -r extract
+rm -r $TAXDUMP
+
+# Compress final database and cleanup
+cd ..
+tar -cvzf $UNIPROT_TAR $UNIPROT
+rm -r $UNIPROT
 ```
 
 #### 4. BUSCO databases
@@ -161,6 +179,7 @@ Create the database directory and move into the directory:
 ```bash
 DATE=2024_10
 BUSCO=/path/to/databases/busco_${DATE}
+BUSCO_TAR=/path/to/databases/busco_${DATE}.tar.gz
 mkdir -p $BUSCO
 cd $BUSCO
 ```
@@ -181,6 +200,13 @@ If you have [GNU parallel](https://www.gnu.org/software/parallel/) installed, yo
 find v5/data -name "*.tar.gz" | parallel "cd {//}; tar -xzf {/}"
 ```
 
+Finally re-compress and cleanup the files:
+
+```bash
+tar -cvzf $BUSCO_TAR $BUSCO
+rm -r $BUSCO
+```
+
 ## Changes from Snakemake to Nextflow
 
 ### Commands

assets/test/nt_mMelMel3.1/nt_mMelMel3.1.nin

@@ -87,6 +87,11 @@
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/seqtk/subseq/seqtk-subseq.diff"
                     },
+                    "untar": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "windowmasker/mkcounts": {
                         "branch": "master",
                         "git_sha": "32cac29d4a92220965dace68a1fb0bb2e3547cac",

assets/test/nt_mMelMel3.1/nt_mMelMel3.1.nog

@@ -10,13 +10,11 @@ process GENERATE_CONFIG {
     val taxon_query
     val busco_lin
     path lineage_tax_ids
-    tuple val(meta2), path(blastn)
     val reads
-    // The following are passed as "val" because we just want to know the full paths. No staging necessary
-    val blastp_path
-    val blastx_path
-    val blastn_path
-    val taxdump_path
+    tuple val(meta2), path(blastp)
+    tuple val(meta3), path(blastx)
+    tuple val(meta4), path(blastn)
+    tuple val(meta5), path(taxdump)
 
     output:
     tuple val(meta), path("*.yaml")          , emit: yaml
@@ -43,10 +41,10 @@ process GENERATE_CONFIG {
         $accession_params \\
         --nt $blastn \\
         $input_reads \\
-        --blastp ${blastp_path} \\
-        --blastx ${blastx_path} \\
-        --blastn ${blastn_path} \\
-        --taxdump ${taxdump_path} \\
+        --blastp ${blastp} \\
+        --blastx ${blastx} \\
+        --blastn ${blastn} \\
+        --taxdump ${taxdump} \\
         --output_prefix ${prefix}
 
     cat <<-END_VERSIONS > versions.yml