From b9a2a03861028bc1733cff62937142e1857816ff Mon Sep 17 00:00:00 2001
From: Philippe Ruiz <philippe.ruiz@inrae.fr>
Date: Mon, 17 Feb 2025 13:38:00 +0100
Subject: [PATCH 1/8] start integration mash db in workflow
---
conf/functional_test.config | 3 ++-
docs/source/usage.md | 3 ++-
docs/source/use_case.md | 4 ++--
functional_tests/test_download.config | 3 ++-
main.nf | 8 +++++---
modules/gtdbtk.nf | 3 ++-
nextflow.config | 1 +
subworkflows/00_databases.nf | 4 ++++
subworkflows/08_binning.nf | 3 ++-
9 files changed, 22 insertions(+), 10 deletions(-)
diff --git a/conf/functional_test.config b/conf/functional_test.config
index 31d579c..e1a1fcf 100644
--- a/conf/functional_test.config
+++ b/conf/functional_test.config
@@ -26,5 +26,6 @@ params {
host_fasta = "/work/project/plateforme/metaG/functional_test/metagwgs-test-datasets/small/input/host/Homo_sapiens.GRCh38_chr21.fa"
input = "/work/project/plateforme/metaG/functional_test/metagwgs-test-datasets/small/input/samplesheet.csv"
type='SR'
- gtdbtk_bank="/work/project/plateforme/metaG/databases/GTDBtk_data/release207_v2"
+ gtdbtk_bank="/work/bank2/GTDB/GTDB/current/flat/release220/"
+ mash_bank="/work/project/plateforme/metaG/functional_test/FT_banks/mash/gtdb_ref_sketch.msh"
}
diff --git a/docs/source/usage.md b/docs/source/usage.md
index 5aae59f..52f275c 100644
--- a/docs/source/usage.md
+++ b/docs/source/usage.md
@@ -92,7 +92,7 @@ wget https://data.ace.uq.edu.au/public/gtdb/data/releases/latest/auxillary_files
tar xvzf gtdbtk_v2_data.tar.gz
```
-After that, you have to indicate the path to gtdb-tk file database with the flag --gtdbtk_bank .
+After that, you have to indicate the path to gtdb-tk file database with the flags --gtdbtk_bank and --mash_bank.
```{warning}
* if you use steps `S02_ASSEMBLY` or `S03_FILTERING` or `S04_STRUCTURAL_ANNOT` or `S05_ALIGNMENT` or `S06_FUNC_ANNOT` or
@@ -477,6 +477,7 @@ at the same time as the protein database used in 05_alignment step.
| Parameter | Description |
| ------------ | ----------- |
| `--gtdbtk_bank` | indicates path to the GTDBTK database (see [GTDBTk installing](https://ecogenomics.github.io/GTDBTk/installing/index.html)).<br /> Default: `""`.|
+| `--mash_bank` | indicates path to the Mash database (see [GTDBTk installing](https://ecogenomics.github.io/GTDBTk/installing/index.html)).<br /> Default: `""`.|
| `--checkm2_bank` | indicates path to the checkm2 database (`PATH/uniref100.KO.1.dmnd`).<br /> To download it, launch `singularity exec -B YOUR_ACTUAL_PATH PATH_TO/binning.sif checkm2 database --download --path YOUR_ACTUAL_PATH/checkm2DB`.<br /> Adapt -B parameter to your infrastructure if you are not in genobioinfo. This command will return 2 non-blocking errors, don't worry about them. <br /> Default: `""`.|
| `--metabat2_seed` | Set the seed for metabat2, for exact reproducibility of metabat2 (default: 0 (random seed)).<br /> Default: `0`.|
| `--min_completeness [nb]` | Minimum % of bins completeness for the bins to be kept after bin_refinement step.<br /> Default: `50`.|
diff --git a/docs/source/use_case.md b/docs/source/use_case.md
index 72e6b80..3b0f959 100644
--- a/docs/source/use_case.md
+++ b/docs/source/use_case.md
@@ -89,7 +89,7 @@ sample_3,test_data/ERR3201928_1.fastq.gz,test_data/ERR3201928_2.fastq.gz
4. We also need to have the diamond bank we want to use to align protein sequence of genes. Different diamond banks are available on genobioinfo cluster, here we will use NR: `/work/bank/diamonddb/nr.dmnd`. The path to this file will be used into our script.
-5. Finally, we want to download the gtdb-tk database in order to perform the taxonomic affiliations of the bins (see https://ecogenomics.github.io/GTDBTk/installing/index.html). The path to gtdb-tk database on genobioinfo is `usr/local/bioinfo/src/Miniconda/Miniconda3/envs/gtdbtk-v2.1.1_env/share/gtdbtk-2.1.1/db/`
+5. Finally, we want to download the gtdb-tk database in order to perform the taxonomic affiliations of the bins (see https://ecogenomics.github.io/GTDBTk/installing/index.html). The path to gtdb-tk database on genobioinfo is `usr/local/bioinfo/src/Miniconda/Miniconda3/envs/gtdbtk-v2.4.0_env/share/gtdbtk-2.4.0/db/`
6. In `Script_filtering_binning.sh` write:
@@ -108,7 +108,7 @@ nextflow run -profile genotoul main.nf --type SR --input "samplesheet.csv" \
--kaiju_db_dir "/bank/kaijudb/kaijudb_refseq_2020-05-25" \
--assembly metaspades \
--diamond_bank "/work/bank/diamonddb/nr.dmnd" \
---gtdbtk_bank "/work/project/plateforme/metaG/databases/GTDBtk_data/release207_v2/" \
+--gtdbtk_bank "/work/bank2/GTDB/GTDB/current/flat/release220/" \
-with-report -with-timeline -with-trace -with-dag -resume
```
diff --git a/functional_tests/test_download.config b/functional_tests/test_download.config
index a8b0cfd..3575b4d 100644
--- a/functional_tests/test_download.config
+++ b/functional_tests/test_download.config
@@ -19,7 +19,8 @@ params {
host_fasta = "/work/project/plateforme/metaG/functional_test/metagwgs-test-datasets/small/input/host/Homo_sapiens.GRCh38_chr21.fa"
host_index = ""
diamond_bank = "/work/project/plateforme/metaG/functional_test/FT_banks/refseq_bacteria_2021-05-20/refseq_bacteria_100000.dmnd"
- gtdbtk_bank="/work/project/plateforme/metaG/databases/GTDBtk_data/release207_v2"
+ gtdbtk_bank="/work/bank2/GTDB/GTDB/current/flat/release220/"
+ mash_bank="/work/project/plateforme/metaG/functional_test/FT_banks/mash/gtdb_ref_sketch.msh"
input = "/work/project/plateforme/metaG/functional_test/metagwgs-test-datasets/small/input/samplesheet.csv"
type='SR'
}
diff --git a/main.nf b/main.nf
index 92ac20f..9c1f7ab 100644
--- a/main.nf
+++ b/main.nf
@@ -93,6 +93,7 @@ include { MULTIQC } from './modules/multiqc'
SO8_BINNING options:
--skip_binning Skip this step
--gtdbtk_bank Path to the GTDBTK database
+ --mash_bank Path to the Mash database
--checkm2_bank Path to the CheckM2 database
--metabat2_seed Set the seed for metabat2, for exact reproducibility of metabat2 (default: 0 (random seed))
--binning_cross_alignment Mapping strategy to compute co-abundances for binning: .
@@ -208,8 +209,8 @@ workflow {
exit 1, "You must specify --stop_at_structural_annot or specify a diamond bank with --diamond_bank"
}
- if ( !(params.stop_at_clean) && !(params.stop_at_assembly) && !(params.stop_at_filtering) && !(params.stop_at_structural_annot) && !(params.skip_binning ) && !(params.gtdbtk_bank || params.checkm2_bank) ) {
- exit 1, "You must specify --skip_binning or specify a GTDB-TK bank with --gtdbtk_bank and a checkm2 bank with --checkm2_bank"
+ if ( !(params.stop_at_clean) && !(params.stop_at_assembly) && !(params.stop_at_filtering) && !(params.stop_at_structural_annot) && !(params.skip_binning ) && !(params.gtdbtk_bank || params.mash_bank || params.checkm2_bank) ) {
+ exit 1, "You must specify --skip_binning or specify a GTDB-TK bank with --gtdbtk_bank, mash bank with --mash_bank and a checkm2 bank with --checkm2_bank"
}
if ( params.coassembly && params.binning_cross_alignment == 'group'){
@@ -300,6 +301,7 @@ workflow {
ch_taxonomy = DATABASES.out.taxonomy
ch_diamon_db = DATABASES.out.diamond
ch_gtbdtk_db = DATABASES.out.gtdbtk
+ ch_mash_db = DATABASES.out.mash
ch_checkm2_db = DATABASES.out.checkm2
ch_multiqc_config = Channel.empty()
@@ -450,7 +452,7 @@ workflow {
if ( !params.stop_at_clean && !params.stop_at_assembly && !params.stop_at_filtering && !params.stop_at_structural_annot && !params.skip_binning ) {
- S08_BINNING( ch_reads, ch_assembly, ch_bam, ch_gtbdtk_db, ch_checkm2_db, ch_quast, ch_circular)
+ S08_BINNING( ch_reads, ch_assembly, ch_bam, ch_gtbdtk_db, ch_mash_db, ch_checkm2_db, ch_quast, ch_circular)
ch_bins_abundances_report = S08_BINNING.out.bins_abundances_report
ch_bins_stats_report = S08_BINNING.out.bins_stats_report
diff --git a/modules/gtdbtk.nf b/modules/gtdbtk.nf
index ba9b86d..9eecfce 100644
--- a/modules/gtdbtk.nf
+++ b/modules/gtdbtk.nf
@@ -5,6 +5,7 @@ process GTDBTK {
input:
val(drep_bins_folder)
val(gtdbtk_db)
+ val(mash_db)
output:
path "gtdbtk.bac120.summary.tsv*" , emit : gtdbtk_affiliations_predictions
@@ -15,7 +16,7 @@ process GTDBTK {
export GTDBTK_DATA_PATH=$gtdbtk_db
- gtdbtk classify_wf --genome_dir $drep_bins_folder -x fa --out_dir ./ --skip_ani_screen --pplacer_cpus ${task.cpus} --cpus ${task.cpus}
+ gtdbtk classify_wf --genome_dir $drep_bins_folder -x fa --out_dir ./ --mash_db $mash_db --pplacer_cpus ${task.cpus} --cpus ${task.cpus}
echo \$(gtdbtk -h 2>&1) &> v_gtdbtk.txt
"""
}
\ No newline at end of file
diff --git a/nextflow.config b/nextflow.config
index c70ed22..59dff8c 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -16,6 +16,7 @@ params {
min_contigs_cpm = 1
diamond_bank = ""
gtdbtk_bank = ""
+ mash_bank = ""
checkm2_bank = ""
percentage_identity = 0.95
type = ""
diff --git a/subworkflows/00_databases.nf b/subworkflows/00_databases.nf
index 9c0ca02..f808092 100644
--- a/subworkflows/00_databases.nf
+++ b/subworkflows/00_databases.nf
@@ -82,10 +82,12 @@ workflow DATABASES {
}
ch_gtdbtk_db = Channel.empty()
+ ch_mash_db = Channel.empty()
ch_checkm2_db = Channel.empty()
if ( !(params.stop_at_clean) && !(params.stop_at_assembly) && !(params.stop_at_filtering) && !(params.stop_at_structural_annot) && !(params.skip_binning) ) {
ch_gtdbtk_db = Channel.fromPath(params.gtdbtk_bank).first()
+ ch_mash_db = Channel.fromPath(params.mash_bank).first()
ch_checkm2_db = Channel.fromPath(params.checkm2_bank).first()
}
@@ -97,6 +99,7 @@ workflow DATABASES {
ch_taxdump.ifEmpty([]),
ch_diamond.ifEmpty([]),
ch_gtdbtk_db.ifEmpty([]),
+ ch_mash_db.ifEmpty([])
ch_checkm2_db.ifEmpty([])
)
@@ -108,6 +111,7 @@ workflow DATABASES {
taxonomy = ch_taxonomy.first()
diamond = ch_diamond
gtdbtk = ch_gtdbtk_db
+ mash = ch_mash_db
checkm2 = ch_checkm2_db
}
diff --git a/subworkflows/08_binning.nf b/subworkflows/08_binning.nf
index 1346139..4573dc2 100644
--- a/subworkflows/08_binning.nf
+++ b/subworkflows/08_binning.nf
@@ -15,6 +15,7 @@ workflow STEP_08_BINNING {
assembly
bam
gtdbtk_db
+ mash_db
checkm2_db
quast
circular
@@ -222,7 +223,7 @@ workflow STEP_08_BINNING {
///// TAXONOMIC AFFILIATION BIN
///////////////////////////////
- GTDBTK(ch_bins_drep, gtdbtk_db)
+ GTDBTK(ch_bins_drep, gtdbtk_db, mash_db)
ch_gtdbtk_v = GTDBTK.out.v_gtdbtk
ch_gtdbtk_affi = GTDBTK.out.gtdbtk_affiliations_predictions
--
GitLab
From 19612c6363976d8a725c2cd5cf3401b8719f91fa Mon Sep 17 00:00:00 2001
From: Philippe Ruiz <philippe.ruiz@inrae.fr>
Date: Mon, 17 Feb 2025 15:18:13 +0100
Subject: [PATCH 2/8] gtdbtk run with mash db in a specific folder
---
main.nf | 3 ++-
modules/get_db_versions.nf | 6 ++++++
subworkflows/00_databases.nf | 2 +-
3 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/main.nf b/main.nf
index 9c1f7ab..96ccb76 100644
--- a/main.nf
+++ b/main.nf
@@ -291,7 +291,8 @@ workflow {
ch_taxonomy = Channel.empty()
ch_diamon_db = Channel.empty()
ch_gtbdtk_db = Channel.empty()
- ch_gtbdtk_db = Channel.empty()
+ ch_mash_db = Channel.empty()
+ ch_checkm2_db = Channel.empty()
DATABASES ()
ch_host_fasta = DATABASES.out.host_fasta
diff --git a/modules/get_db_versions.nf b/modules/get_db_versions.nf
index b64e41b..407d3aa 100644
--- a/modules/get_db_versions.nf
+++ b/modules/get_db_versions.nf
@@ -10,6 +10,7 @@ process GET_DB_VERSIONS {
path taxdump
path diamond
path gtdbtk
+ path mash
path checkm2
@@ -49,6 +50,11 @@ process GET_DB_VERSIONS {
echo "GTDBTK ${gtdbtk}" > gtdbtk_db.txt
fi
+ if [[ "${mash}" != "" ]]
+ then
+ echo "MASH ${mash}" > mash_db.txt
+ fi
+
if [[ "${checkm2}" != "" ]]
then
echo "Checkm2 ${checkm2}" > checkm2_db.txt
diff --git a/subworkflows/00_databases.nf b/subworkflows/00_databases.nf
index f808092..92ac645 100644
--- a/subworkflows/00_databases.nf
+++ b/subworkflows/00_databases.nf
@@ -99,7 +99,7 @@ workflow DATABASES {
ch_taxdump.ifEmpty([]),
ch_diamond.ifEmpty([]),
ch_gtdbtk_db.ifEmpty([]),
- ch_mash_db.ifEmpty([])
+ ch_mash_db.ifEmpty([]),
ch_checkm2_db.ifEmpty([])
)
--
GitLab
From ac7a2c16e3af29dca3e6658f452d44798042170b Mon Sep 17 00:00:00 2001
From: Philippe Ruiz <philippe.ruiz@inrae.fr>
Date: Mon, 17 Feb 2025 15:58:46 +0100
Subject: [PATCH 3/8] update documentation for gtdbtk + mash
---
docs/source/output.md | 2 +-
docs/source/usage.md | 6 +++---
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/docs/source/output.md b/docs/source/output.md
index e9ca730..9c75622 100644
--- a/docs/source/output.md
+++ b/docs/source/output.md
@@ -267,7 +267,7 @@ If you want to make further analysis about intra-population genetic diversity (m
| File | Description |
| ----------------------- | --------------------------------------- |
-| `gtdbtk.bac120.summary.tsv` | Taxonomic classifications provided by GTDB-Tk. One line = one bin id (1st column, `user_genome`), <br /> its taxonomical classification based on the closest reference genome from the GTDB-Tk database (2nd column, `classification`), <br /> the accession number of the closest reference genome (3rd column, `fastani_reference`). <br /> Please see GTDB-Tk documentation [here](https://ecogenomics.github.io/GTDBTk/files/summary.tsv.html) for information on additional columns. |
+| `gtdbtk.bac120.summary.tsv` | Taxonomic classifications provided by GTDB-Tk. One line = one bin id (1st column, `user_genome`), <br /> its taxonomical classification based on the closest reference genome from the GTDB-Tk database (2nd column, `classification`), <br /> the accession number of the closest reference genome (3rd column, `closest_genome_reference`). <br /> Please see GTDB-Tk documentation [here](https://ecogenomics.github.io/GTDBTk/files/summary.tsv.html) for information on additional columns. |
#### 4. 08_4_mapping_on_final_bins
diff --git a/docs/source/usage.md b/docs/source/usage.md
index 52f275c..03dae44 100644
--- a/docs/source/usage.md
+++ b/docs/source/usage.md
@@ -87,9 +87,9 @@ In addition to the general mandatory files, if you wish to launch certain steps
* Step `S08_BINNING`, To perform the taxonomic affiliations of the bins, you must download the gtdb-tk database as follows (see [GTDBTk](https://ecogenomics.github.io/GTDBTk/installing/index.html)) :
```bash
-wget https://data.gtdb.ecogenomic.org/releases/latest/auxillary_files/gtdbtk_v2_data.tar.gz
-wget https://data.ace.uq.edu.au/public/gtdb/data/releases/latest/auxillary_files/gtdbtk_v2_data.tar.gz (or, mirror)
-tar xvzf gtdbtk_v2_data.tar.gz
+wget https://data.ace.uq.edu.au/public/gtdb/data/releases/latest/auxillary_files/gtdbtk_package/full_package/gtdbtk_data.tar.gz
+wget https://data.gtdb.ecogenomic.org/releases/latest/auxillary_files/gtdbtk_package/full_package/gtdbtk_data.tar.gz ( mirror for Australia)
+tar xvzf gtdbtk_data.tar.gz
```
After that, you have to indicate the path to gtdb-tk file database with the flags --gtdbtk_bank and --mash_bank.
--
GitLab
From 6d9138b52862c3b04e575e18b71c786117662524 Mon Sep 17 00:00:00 2001
From: Philippe Ruiz <philippe.ruiz@inrae.fr>
Date: Tue, 18 Feb 2025 10:49:10 +0100
Subject: [PATCH 4/8] use gtdbk240 with mash db only if it already exist and
pointed in the config path
---
main.nf | 4 ++--
modules/gtdbtk.nf | 18 +++++++++---------
subworkflows/00_databases.nf | 18 +++++++++++++++++-
3 files changed, 28 insertions(+), 12 deletions(-)
diff --git a/main.nf b/main.nf
index 96ccb76..f902901 100644
--- a/main.nf
+++ b/main.nf
@@ -93,7 +93,7 @@ include { MULTIQC } from './modules/multiqc'
SO8_BINNING options:
--skip_binning Skip this step
--gtdbtk_bank Path to the GTDBTK database
- --mash_bank Path to the Mash database
+ --mash_bank Path to the Mash database. If the database doesn't exist, it will be created in this path.
--checkm2_bank Path to the CheckM2 database
--metabat2_seed Set the seed for metabat2, for exact reproducibility of metabat2 (default: 0 (random seed))
--binning_cross_alignment Mapping strategy to compute co-abundances for binning: .
@@ -294,7 +294,7 @@ workflow {
ch_mash_db = Channel.empty()
ch_checkm2_db = Channel.empty()
- DATABASES ()
+ DATABASES()
ch_host_fasta = DATABASES.out.host_fasta
ch_host_index = DATABASES.out.host_index
ch_kaiju_db = DATABASES.out.kaiju_db
diff --git a/modules/gtdbtk.nf b/modules/gtdbtk.nf
index 9eecfce..8ec0172 100644
--- a/modules/gtdbtk.nf
+++ b/modules/gtdbtk.nf
@@ -1,22 +1,22 @@
process GTDBTK {
- publishDir "${params.outdir}/08_binning/08_3_gtdbtk", mode: 'copy'
- label 'BINNING'
+ publishDir "${params.outdir}/08_binning/08_3_gtdbtk", mode: 'copy'
+ label 'BINNING'
input:
- val(drep_bins_folder)
- val(gtdbtk_db)
- val(mash_db)
+ path bins_drep
+ val gtdbtk_db
+ val mash_db
output:
- path "gtdbtk.bac120.summary.tsv*" , emit : gtdbtk_affiliations_predictions
- path "v_gtdbtk.txt" ,emit : v_gtdbtk
+ path "gtdbtk.bac120.summary.tsv*", emit: gtdbtk_affiliations_predictions
+ path "v_gtdbtk.txt", emit: v_gtdbtk
script:
"""
-
+ echo "hello"
export GTDBTK_DATA_PATH=$gtdbtk_db
- gtdbtk classify_wf --genome_dir $drep_bins_folder -x fa --out_dir ./ --mash_db $mash_db --pplacer_cpus ${task.cpus} --cpus ${task.cpus}
+ gtdbtk classify_wf --genome_dir $bins_drep -x fa --out_dir ./ --mash_db $mash_db --pplacer_cpus ${task.cpus} --cpus ${task.cpus}
echo \$(gtdbtk -h 2>&1) &> v_gtdbtk.txt
"""
}
\ No newline at end of file
diff --git a/subworkflows/00_databases.nf b/subworkflows/00_databases.nf
index 92ac645..a39ca92 100644
--- a/subworkflows/00_databases.nf
+++ b/subworkflows/00_databases.nf
@@ -86,8 +86,12 @@ workflow DATABASES {
ch_checkm2_db = Channel.empty()
if ( !(params.stop_at_clean) && !(params.stop_at_assembly) && !(params.stop_at_filtering) && !(params.stop_at_structural_annot) && !(params.skip_binning) ) {
+ if ( params.mash_bank && file(params.mash_bank).exists() ) {
+ ch_mash_db = Channel.fromPath(params.mash_bank).first()
+ } else {
+ MASH_DB()
+ }
ch_gtdbtk_db = Channel.fromPath(params.gtdbtk_bank).first()
- ch_mash_db = Channel.fromPath(params.mash_bank).first()
ch_checkm2_db = Channel.fromPath(params.checkm2_bank).first()
}
@@ -163,3 +167,15 @@ process EGGNOG_MAPPER_DB {
"""
}
+process MASH_DB {
+ publishDir "${params.databases}/mash_db"
+ label 'BINNING'
+
+ output:
+ path "mash_db", emit: mash_annot_db
+
+ script:
+ """
+ mkdir mash_db
+ """
+}
\ No newline at end of file
--
GitLab
From 8ffac784e391d802e6f80b5b7829946039ca0dba Mon Sep 17 00:00:00 2001
From: Philippe Ruiz <philippe.ruiz@inrae.fr>
Date: Wed, 19 Feb 2025 10:53:01 +0100
Subject: [PATCH 5/8] specify release of gtdb tk database in doc
---
docs/source/usage.md | 4 ++++
docs/source/use_case.md | 3 ++-
2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/docs/source/usage.md b/docs/source/usage.md
index 03dae44..4f972f5 100644
--- a/docs/source/usage.md
+++ b/docs/source/usage.md
@@ -94,6 +94,10 @@ tar xvzf gtdbtk_data.tar.gz
After that, you have to indicate the path to gtdb-tk file database with the flags --gtdbtk_bank and --mash_bank.
+```{note}
+metagWGS v2.4.devel use GTDB-Tk v2.4.0 and require the gtdb databank r220.
+```
+
```{warning}
* if you use steps `S02_ASSEMBLY` or `S03_FILTERING` or `S04_STRUCTURAL_ANNOT` or `S05_ALIGNMENT` or `S06_FUNC_ANNOT` or
`S07_TAXO_AFFI` without skipping `S01_CLEAN_QC` or host reads filtering, you need to use the mandatory files of step `S01_CLEAN_QC`.
diff --git a/docs/source/use_case.md b/docs/source/use_case.md
index 3b0f959..3df94bd 100644
--- a/docs/source/use_case.md
+++ b/docs/source/use_case.md
@@ -89,7 +89,8 @@ sample_3,test_data/ERR3201928_1.fastq.gz,test_data/ERR3201928_2.fastq.gz
4. We also need to have the diamond bank we want to use to align protein sequence of genes. Different diamond banks are available on genobioinfo cluster, here we will use NR: `/work/bank/diamonddb/nr.dmnd`. The path to this file will be used into our script.
-5. Finally, we want to download the gtdb-tk database in order to perform the taxonomic affiliations of the bins (see https://ecogenomics.github.io/GTDBTk/installing/index.html). The path to gtdb-tk database on genobioinfo is `usr/local/bioinfo/src/Miniconda/Miniconda3/envs/gtdbtk-v2.4.0_env/share/gtdbtk-2.4.0/db/`
+
+5. Finally, we want to download the gtdb-tk database (r220) in order to perform the taxonomic affiliations of the bins (see https://ecogenomics.github.io/GTDBTk/installing/index.html). The path to gtdb-tk database on genobioinfo is `usr/local/bioinfo/src/Miniconda/Miniconda3/envs/gtdbtk-v2.4.0_env/share/gtdbtk-2.4.0/db/`
6. In `Script_filtering_binning.sh` write:
--
GitLab
From c49a0444b54959f097fb20eea9f997073d75e9ff Mon Sep 17 00:00:00 2001
From: Philippe Ruiz <philippe.ruiz@inrae.fr>
Date: Wed, 19 Feb 2025 17:00:29 +0100
Subject: [PATCH 6/8] run gtdbtk with mash db
---
modules/get_db_versions.nf | 8 ++++----
subworkflows/00_databases.nf | 20 ++------------------
2 files changed, 6 insertions(+), 22 deletions(-)
diff --git a/modules/get_db_versions.nf b/modules/get_db_versions.nf
index 407d3aa..4c51979 100644
--- a/modules/get_db_versions.nf
+++ b/modules/get_db_versions.nf
@@ -50,10 +50,10 @@ process GET_DB_VERSIONS {
echo "GTDBTK ${gtdbtk}" > gtdbtk_db.txt
fi
- if [[ "${mash}" != "" ]]
- then
- echo "MASH ${mash}" > mash_db.txt
- fi
+ #if [[ "${mash}" != "" ]]
+ #then
+ # echo "MASH ${mash}" > mash_db.txt
+ #fi
if [[ "${checkm2}" != "" ]]
then
diff --git a/subworkflows/00_databases.nf b/subworkflows/00_databases.nf
index a39ca92..fb0cc56 100644
--- a/subworkflows/00_databases.nf
+++ b/subworkflows/00_databases.nf
@@ -86,14 +86,11 @@ workflow DATABASES {
ch_checkm2_db = Channel.empty()
if ( !(params.stop_at_clean) && !(params.stop_at_assembly) && !(params.stop_at_filtering) && !(params.stop_at_structural_annot) && !(params.skip_binning) ) {
- if ( params.mash_bank && file(params.mash_bank).exists() ) {
- ch_mash_db = Channel.fromPath(params.mash_bank).first()
- } else {
- MASH_DB()
- }
ch_gtdbtk_db = Channel.fromPath(params.gtdbtk_bank).first()
+ ch_mash_db = Channel.value(file(params.mash_bank)).first()
ch_checkm2_db = Channel.fromPath(params.checkm2_bank).first()
}
+
GET_DB_VERSIONS(
ch_host_fasta.ifEmpty([]),
@@ -166,16 +163,3 @@ process EGGNOG_MAPPER_DB {
download_eggnog_data.py -f -y --data_dir db_eggnog_mapper
"""
}
-
-process MASH_DB {
- publishDir "${params.databases}/mash_db"
- label 'BINNING'
-
- output:
- path "mash_db", emit: mash_annot_db
-
- script:
- """
- mkdir mash_db
- """
-}
\ No newline at end of file
--
GitLab
From a1f485b1c15644ee9a99b9dac1f4e568aaba76b2 Mon Sep 17 00:00:00 2001
From: Philippe Ruiz <philippe.ruiz@inrae.fr>
Date: Tue, 25 Feb 2025 16:47:17 +0100
Subject: [PATCH 7/8] modif explaination of mash bank param
---
main.nf | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/main.nf b/main.nf
index f902901..de8cdda 100644
--- a/main.nf
+++ b/main.nf
@@ -93,7 +93,7 @@ include { MULTIQC } from './modules/multiqc'
SO8_BINNING options:
--skip_binning Skip this step
--gtdbtk_bank Path to the GTDBTK database
- --mash_bank Path to the Mash database. If the database doesn't exist, it will be created in this path.
+ --mash_bank Path to the Mash database. If the database doesn't exist, it will be created in the working directory.
--checkm2_bank Path to the CheckM2 database
--metabat2_seed Set the seed for metabat2, for exact reproducibility of metabat2 (default: 0 (random seed))
--binning_cross_alignment Mapping strategy to compute co-abundances for binning: .
--
GitLab
From f7f598c9022086f41addfa3f7cbe8d16bddeb460 Mon Sep 17 00:00:00 2001
From: Philippe Ruiz <philippe.ruiz@inrae.fr>
Date: Tue, 25 Feb 2025 16:49:07 +0100
Subject: [PATCH 8/8] mash db version is not referenced in db_versions.txt
---
modules/get_db_versions.nf | 5 -----
1 file changed, 5 deletions(-)
diff --git a/modules/get_db_versions.nf b/modules/get_db_versions.nf
index 4c51979..1f59ce5 100644
--- a/modules/get_db_versions.nf
+++ b/modules/get_db_versions.nf
@@ -50,11 +50,6 @@ process GET_DB_VERSIONS {
echo "GTDBTK ${gtdbtk}" > gtdbtk_db.txt
fi
- #if [[ "${mash}" != "" ]]
- #then
- # echo "MASH ${mash}" > mash_db.txt
- #fi
-
if [[ "${checkm2}" != "" ]]
then
echo "Checkm2 ${checkm2}" > checkm2_db.txt
--
GitLab