Sourmash profiler [DO NOT MERGE YET]

conf/test_sourmash.config

@@ -0,0 +1,63 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    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/taxprofiler -profile test,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+//
+// Separate test for sourmash
+//
+
+params {
+    config_profile_name        = 'Test profile'
+    config_profile_description = 'Minimal test to check sourmash 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://github.com/nf-core/test-datasets/raw/taxprofiler/samplesheet.csv'
+    databases                             = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database_v1.1.csv'
+    perform_shortread_qc                  = false
+    perform_longread_qc                   = false
+    perform_shortread_complexityfilter    = false
+    perform_shortread_hostremoval         = false
+    perform_longread_hostremoval          = false
+    perform_runmerging                    = false
+    hostremoval_reference                 = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta'
+    run_kaiju                             = false
+    run_kraken2                           = false
+    run_bracken                           = false
+    run_malt                              = false
+    run_metaphlan                         = false
+    run_centrifuge                        = false
+    run_diamond                           = false
+    run_krakenuniq                        = false
+    run_motus                             = false
+    run_ganon                             = false
+    run_kmcp                              = false
+    kmcp_mode                             = 0
+    run_sourmash                          = true
+}
+
+
+process {
+    withName: SOURMASH_SKETCH {
+        ext.args = "dna --param-string 'k=31,scaled=10,noabund'"
+    }
+
+    withName: SOURMASH_GATHER {
+        ext.args = "--threshold-bp 0"
+    }
+
+}
+
+

lib/WorkflowTaxprofiler.groovy

@@ -102,6 +102,7 @@ class WorkflowTaxprofiler {
                 params.run_motus      ? "mOTUs (Ruscheweyh et al. 2022)," : "",
                 params.run_ganon      ? "ganon (Piro et al. 2020)" : "",
                 params.run_kmcp       ? "KMCP (Shen et al. 2023)" : "",
+                params.run_sourmash   ? "sourmash (Brown & Irber 2016)" : "",
                 "."
             ].join(' ').trim()
 
@@ -174,6 +175,7 @@ class WorkflowTaxprofiler {
                 params.run_motus      ? "<li>Ruscheweyh, H.-J., Milanese, A., Paoli, L., Karcher, N., Clayssen, Q., Keller, M. I., Wirbel, J., Bork, P., Mende, D. R., Zeller, G., & Sunagawa, S. (2022). Cultivation-independent genomes greatly expand taxonomic-profiling capabilities of mOTUs across various environments. Microbiome, 10(1), 212. <a href=\"https://doi.org/10.1186/s40168-022-01410-z\">10.1186/s40168-022-01410-z</a></li>" : "",
                 params.run_ganon      ? "<li>Piro, V. C., Dadi, T. H., Seiler, E., Reinert, K., & Renard, B. Y. (2020). Ganon: Precise metagenomics classification against large and up-to-date sets of reference sequences. Bioinformatics (Oxford, England), 36(Suppl_1), i12–i20. <a href=\"https://doi.org/10.1093/bioinformatics/btaa458\">10.1093/bioinformatics/btaa458</a></li>" : "",
                 params.run_kmcp       ? "<li>Shen, W., Xiang, H., Huang, T., Tang, H., Peng, M., Cai, D., Hu, P., & Ren, H. (2023). KMCP: accurate metagenomic profiling of both prokaryotic and viral populations by pseudo-mapping. Bioinformatics (Oxford, England), 39(1). <a href=\"https://doi.org/10.1093/bioinformatics/btac845\">10.1093/bioinformatics/btac845</a></li>" : "",
+                params.run_sourmash   ? "<li>Brown, T., & Irber, L. (2016).  sourmash: a library for MinHash sketching of DNA. Journal of Open Source Software, 1(5). <a href=\"https://doi.org/10.21105/joss.00027\">10.21105/joss.00027</a></li>" : "",
             ].join(' ').trim()
 
             def text_visualisation = [

modules.json

@@ -232,6 +232,21 @@
                         "git_sha": "3ffae3598260a99e8db3207dead9f73f87f90d1f",
                         "installed_by": ["modules"]
                     },
+                    "sourmash/gather": {
+                        "branch": "master",
+                        "git_sha": "33f66e0b2612df417ba94e89ce4c3770258d674b",
+                        "installed_by": ["modules"]
+                    },
+                    "sourmash/sketch": {
+                        "branch": "master",
+                        "git_sha": "33f66e0b2612df417ba94e89ce4c3770258d674b",
+                        "installed_by": ["modules"]
+                    },
+                    "sourmash/taxannotate": {
+                        "branch": "master",
+                        "git_sha": "33f66e0b2612df417ba94e89ce4c3770258d674b",
+                        "installed_by": ["modules"]
+                    },
                     "taxpasta/merge": {
                         "branch": "master",
                         "git_sha": "48019785051ba491e82dce910273c2eca61bd5b7",