update bouncy-basenji branch

CHANGELOG.md

@@ -3,10 +3,17 @@
 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).
 
+## v1.2dev - Bouncy Basenji [unreleased]
+
+### `Added`
+
+- [#417](https://github.com/nf-core/taxprofiler/pull/417) - Added reference-free metagenome estimation with Nonpareil (added by @jfy133)
+
 ## v1.1.6dev - [unreleased]
 
 ### `Added`
 
+- [#417](https://github.com/nf-core/taxprofiler/pull/417) - Added reference-free metagenome estimation with Nonpareil (added by @jfy133)
 - [#454](https://github.com/nf-core/taxprofiler/pull/454) Updated to nf-core pipeline template v2.13.1 (added by @LilyAnderssonLee & @sofstam)
 - [#461](https://github.com/nf-core/taxprofiler/pull/461) Turned on 'strict' Nextflow evaluation runs (added by @jfy133)
 - [#461](https://github.com/nf-core/taxprofiler/pull/461) Optimised database compression so each compressed input database is untarred once, and shared amongst each run with different parameters (added by @jfy133)

CITATIONS.md

@@ -30,6 +30,10 @@
 
   > Schubert, M., Lindgreen, S., & Orlando, L. (2016). AdapterRemoval v2: rapid adapter trimming, identification, and read merging. BMC Research Notes, 9, 88. https://doi.org/10.1186/s13104-016-1900-2
 
+- [Nonpareil](https://doi.org/10.1128/mSystems.00039-18)
+
+  - Rodriguez-R, L. M., Gunturu, S., Tiedje, J. M., Cole, J. R., & Konstantinidis, K. T. (2018). Nonpareil 3: Fast Estimation of Metagenomic Coverage and Sequence Diversity. mSystems, 3(3). https://doi.org/10.1128/mSystems.00039-18
+
 - [Porechop](https://github.com/rrwick/Porechop)
 
   > Wick, R. R., Judd, L. M., Gorrie, C. L., & Holt, K. E. (2017). Completing bacterial genome assemblies with multiplex MinION sequencing. Microbial Genomics, 3(10), e000132. https://doi.org/10.1099/mgen.0.000132

README.md

@@ -33,7 +33,7 @@
    - Low complexity and quality filtering (short-read: [bbduk](https://jgi.doe.gov/data-and-tools/software-tools/bbtools/), [PRINSEQ++](https://github.com/Adrian-Cantu/PRINSEQ-plus-plus); long-read: [Filtlong](https://github.com/rrwick/Filtlong))
    - Host-read removal (short-read: [BowTie2](http://bowtie-bio.sourceforge.net/bowtie2/); long-read: [Minimap2](https://github.com/lh3/minimap2))
    - Run merging
-3. Supports statistics for host-read removal ([Samtools](http://www.htslib.org/))
+3. Supports statistics metagenome coverage estimation ([Nonpareil](https://nonpareil.readthedocs.io/en/latest/)) and for host-read removal ([Samtools](http://www.htslib.org/))
 4. Performs taxonomic classification and/or profiling using one or more of:
    - [Kraken2](https://ccb.jhu.edu/software/kraken2/)
    - [MetaPhlAn](https://huttenhower.sph.harvard.edu/metaphlan/)

assets/multiqc_config.yml

@@ -10,6 +10,44 @@ report_section_order:
     order: -1001
   "nf-core-taxprofiler-summary":
     order: -1002
+  general_stats":
+    order: 1000
+  fastqc:
+    order: 900
+  fastqc-1:
+    order: 800
+  fastp:
+    order: 700
+  adapterRemoval:
+    order: 600
+  nonpareil_all_samples:
+    order: 500
+  porechop:
+    order: 400
+  bbduk:
+    order: 300
+  prinseqplusplus:
+    order: 200
+  filtlong:
+    order: 100
+  bowtie2:
+    order: 90
+  samtools:
+    order: 80
+  kraken:
+    order: 70
+  bracken:
+    order: 60
+  centrifuge:
+    order: 50
+  malt:
+    order: 40
+  diamond:
+    order: 30
+  kaiju:
+    order: 20
+  motus:
+    order: 10
 
 export_plots: true
 
@@ -22,6 +60,7 @@ run_modules:
   - fastqc
   - adapterRemoval
   - fastp
+  - custom_content
   - bbduk
   - prinseqplusplus
   - porechop
@@ -34,7 +73,6 @@ run_modules:
   - diamond
   - malt
   - motus
-  - custom_content
 
 sp:
   diamond:
@@ -43,6 +81,13 @@ sp:
     fn_re: ".*(fastqc|falco)_data.txt$"
   fastqc/zip:
     fn: "*_fastqc.zip"
+  nonpareil_all_samples_mqc:
+    fn: "nonpareil_all_samples_mqc.png"
+
+custom_data:
+  nonpareil_all_samples:
+    section_name: "Nonpareil"
+    description: "Nonpareil uses the redundancy of the reads in metagenomic datasets to estimate the average coverage and predict the amount of sequences that will be required to achieve “nearly complete coverage”. Plots here are not interactive - being exported directly from the tool. If you have difficulty reading the plot, please see the individual PNG files in the results directory. DOI: https://doi.org/10.1128/mSystems.00039-18"
 
 top_modules:
   - "fastqc":
@@ -59,13 +104,8 @@ top_modules:
       path_filters_exclude:
         - "*raw*"
       extra: "If used in this run, Falco is a drop-in replacement for FastQC producing the same output, written by Guilherme de Sena Brandine and Andrew D. Smith."
-  - "fastp"
-  - "adapterRemoval"
   - "porechop":
       extra: "ℹ️: if you get the error message 'Error - was not able to plot data.' this means that porechop did not detect any adapters and therefore no statistics generated."
-  - "bbduk"
-  - "prinseqplusplus"
-  - "filtlong"
   - "bowtie2":
       name: "bowtie2"
   - "samtools":
@@ -94,12 +134,11 @@ top_modules:
         - "*.centrifuge.txt"
   - "malt":
       name: "MALT"
-  - "diamond"
   - "kaiju":
       name: "Kaiju"
-  - "motus"
 
-#It is not possible to set placement for custom kraken and centrifuge columns.
+# It is not possible to set placement for custom kraken
+# and centrifuge columns.
 
 table_columns_placement:
   FastQC / Falco (pre-Trimming):

conf/modules.config

@@ -198,6 +198,34 @@ process {
         ]
     }
 
+    // Redundancy estimation with nonpareil
+    withName: NONPAREIL_NONPAREIL {
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/nonpareil/" },
+            mode: params.publish_dir_mode,
+            pattern: '*.np{a,c,l,o}'
+        ]
+    }
+
+    withName: 'NONPAREIL_CURVE' {
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/nonpareil/" },
+            mode: params.publish_dir_mode,
+            pattern: '*.png'
+        ]
+    }
+
+    withName: 'NONPAREIL_SET' {
+        ext.prefix = { "nonpareil_all_samples_mqc" }
+        publishDir = [
+            path: { "${params.outdir}/nonpareil/" },
+            mode: params.publish_dir_mode,
+            pattern: '*.png'
+        ]
+    }
+
     // AdapterRemoval separate output merging
     withName: CAT_FASTQ {
         ext.prefix = { "${meta.id}_${meta.run_accession}" }

conf/test.config

@@ -20,6 +20,7 @@ params {
     max_time   = '6.h'
 
     // Input data
+<<<<<<< HEAD
     input                                 = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv'
     databases                             = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database_v1.2.csv'
     perform_shortread_qc                  = true
@@ -48,6 +49,37 @@ params {
     kraken2_save_reads                    = true
     centrifuge_save_reads                 = true
     run_profile_standardisation           = true
+=======
+    input                                  = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv'
+    databases                              = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database_v1.1.csv'
+    perform_shortread_qc                   = true
+    perform_longread_qc                    = true
+    shortread_qc_mergepairs                = true
+    perform_shortread_redundancyestimation = true
+    perform_shortread_complexityfilter     = true
+    perform_shortread_hostremoval          = true
+    perform_longread_hostremoval           = true
+    perform_runmerging                     = true
+    hostremoval_reference                  = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta'
+    run_kaiju                              = true
+    run_kraken2                            = true
+    run_bracken                            = true
+    run_malt                               = false
+    run_metaphlan                          = true
+    run_centrifuge                         = true
+    run_diamond                            = true
+    run_krakenuniq                         = true
+    run_motus                              = false
+    run_ganon                              = true
+    run_krona                              = true
+    run_kmcp                               = true
+    kmcp_mode                              = 0
+    krona_taxonomy_directory               = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/sarscov2/metagenome/krona_taxonomy.tab'
+    malt_save_reads                        = true
+    kraken2_save_reads                     = true
+    centrifuge_save_reads                  = true
+    run_profile_standardisation            = true
+>>>>>>> bouncy-basenji
 }
 
 process {
@@ -61,4 +93,7 @@ process {
     withName: MEGAN_RMA2INFO_KRONA {
         maxForks = 1
     }
+    withName: NONPAREIL_NONPAREIL {
+        ext.args = { "-k 5" }
+    }
 }

conf/test_adapterremoval.config

@@ -20,6 +20,7 @@ params {
     max_time   = '6.h'
 
     // Input data
+<<<<<<< HEAD
     input                                 = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv'
     databases                             = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database_v1.2.csv'
     perform_shortread_qc                  = true
@@ -42,11 +43,39 @@ params {
     run_ganon                             = false
     run_kmcp                              = false
     kmcp_mode                             = 0
+=======
+    input                                  = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv'
+    databases                              = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database_v1.1.csv'
+    perform_shortread_qc                   = true
+    perform_longread_qc                    = true
+    shortread_qc_tool                      = 'adapterremoval'
+    perform_shortread_redundancyestimation = true
+    perform_shortread_complexityfilter     = true
+    perform_shortread_hostremoval          = true
+    perform_longread_hostremoval           = true
+    perform_runmerging                     = true
+    hostremoval_reference                  = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta'
+    run_kaiju                              = true
+    run_kraken2                            = true
+    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
+>>>>>>> bouncy-basenji
 }
 
 process {
     withName: MALT_RUN {
         maxForks = 1
         ext.args = { "-m ${params.malt_mode} -J-Xmx12G" }
     }
+    withName: NONPAREIL_NONPAREIL {
+        ext.args = { "-k 5" }
+    }
 }

conf/test_bbduk.config

@@ -49,4 +49,7 @@ process {
         maxForks = 1
         ext.args = { "-m ${params.malt_mode} -J-Xmx12G" }
     }
+    withName: NONPAREIL_NONPAREIL {
+        ext.args = { "-k 5" }
+    }
 }

conf/test_falco.config

@@ -49,4 +49,7 @@ process {
         maxForks = 1
         ext.args = { "-m ${params.malt_mode} -J-Xmx12G" }
     }
+    withName: NONPAREIL_NONPAREIL {
+        ext.args = { "-k 5" }
+    }
 }

conf/test_fastp.config

@@ -20,6 +20,7 @@ params {
     max_time   = '6.h'
 
     // Input data
+<<<<<<< HEAD
     input                                 = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv'
     databases                             = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database_v1.2.csv'
     perform_shortread_qc                  = true
@@ -43,11 +44,40 @@ params {
     run_ganon                             = false
     run_kmcp                              = false
     kmcp_mode                             = 0
+=======
+    input                                  = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv'
+    databases                              = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database_v1.1.csv'
+    perform_shortread_qc                   = true
+    perform_longread_qc                    = true
+    shortread_qc_tool                      = 'fastp'
+    perform_shortread_redundancyestimation = true
+    perform_shortread_complexityfilter     = true
+    shortread_complexityfilter_tool        = 'fastp'
+    perform_shortread_hostremoval          = true
+    perform_longread_hostremoval           = true
+    perform_runmerging                     = true
+    hostremoval_reference                  = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta'
+    run_kaiju                              = true
+    run_kraken2                            = true
+    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
+>>>>>>> bouncy-basenji
 }
 
 process {
     withName: MALT_RUN {
         maxForks = 1
         ext.args = { "-m ${params.malt_mode} -J-Xmx12G" }
     }
+    withName: NONPAREIL_NONPAREIL {
+        ext.args = { "-k 5" }
+    }
 }