From 05a49947ad898249606315cb08c6456cc46184a4 Mon Sep 17 00:00:00 2001
From: Philippe Ruiz <philippe.ruiz@inrae.fr>
Date: Mon, 10 Feb 2025 13:14:54 +0100
Subject: [PATCH 1/3] gtdbtk on bins extract archee outputs
---
modules/gtdbtk.nf | 5 +++--
modules/sum_up_bins_informations.nf | 21 +++++++++++++++------
subworkflows/08_binning.nf | 5 +++--
3 files changed, 21 insertions(+), 10 deletions(-)
diff --git a/modules/gtdbtk.nf b/modules/gtdbtk.nf
index 8ec0172..ffaeeb5 100644
--- a/modules/gtdbtk.nf
+++ b/modules/gtdbtk.nf
@@ -8,8 +8,9 @@ process GTDBTK {
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_bact
+ path "gtdbtk.ar53.summary.tsv*" , emit : gtdbtk_affiliations_predictions_arch
+ path "v_gtdbtk.txt" ,emit : v_gtdbtk
script:
"""
diff --git a/modules/sum_up_bins_informations.nf b/modules/sum_up_bins_informations.nf
index 042d2da..cc4a4ff 100644
--- a/modules/sum_up_bins_informations.nf
+++ b/modules/sum_up_bins_informations.nf
@@ -6,22 +6,31 @@ process GENOMES_ABUNDANCES_PER_SAMPLE {
path flagstats_files
val(bins_folder)
path genomes_informations
- path affiliations_predictions
+ path affiliations_predictions_arch
+ path affiliations_predictions_bact
path heatmap_header_mqc
path table_header_mqc
output:
- path "genomes_abundances.tsv" , emit: genomes_abundances
- tuple path("stats/genomes_abundances_mqc.tsv"), path("stats/genomes_checkm_mqc.json"), path("stats/bins_general_stats_mqc.tsv"), emit: report
+ path "genomes_abundances_arch.tsv" , emit: genomes_abundances_arch
+ path "genomes_abundances_bact.tsv" , emit: genomes_abundances_bact
+ tuple path("stats/genomes_abundances_mqc_arch.tsv"), path("stats/genomes_checkm_mqc_arch.json"), path("stats/bins_general_stats_mqc_arch.tsv"), emit: report_arch
+ tuple path("stats/genomes_abundances_mqc_bact.tsv"), path("stats/genomes_checkm_mqc_bact.json"), path("stats/bins_general_stats_mqc_bact.tsv"), emit: report_bact
script:
"""
mkdir -p stats
bins_per_sample_summarize.py --list_of_coverage_files ${coverage_files} \
- --list_of_flagstats_files ${flagstats_files} --affiliations_predictions ${affiliations_predictions} \
+ --list_of_flagstats_files ${flagstats_files} --affiliations_predictions ${affiliations_predictions_arch} \
--bins_folder ${bins_folder} --genomes_informations ${genomes_informations} \
- --output_file genomes_abundances.tsv --report_file stats/genomes_abundances_mqc.tsv \
- --checkm_file stats/genomes_checkm_mqc.json --table_file stats/bins_general_stats_mqc.tsv
+ --output_file genomes_abundances_arch.tsv --report_file stats/genomes_abundances_mqc_arch.tsv \
+ --checkm_file stats/genomes_checkm_mqc_arch.json --table_file stats/bins_general_stats_mqc_arch.tsv
+
+ bins_per_sample_summarize.py --list_of_coverage_files ${coverage_files} \
+ --list_of_flagstats_files ${flagstats_files} --affiliations_predictions ${affiliations_predictions_bact} \
+ --bins_folder ${bins_folder} --genomes_informations ${genomes_informations} \
+ --output_file genomes_abundances_bact.tsv --report_file stats/genomes_abundances_mqc_bact.tsv \
+ --checkm_file stats/genomes_checkm_mqc_bact.json --table_file stats/bins_general_stats_mqc_bact.tsv
cat ${table_header_mqc} > stats/tmp.txt && cat stats/bins_general_stats_mqc.tsv >> stats/tmp.txt \
&& mv stats/tmp.txt stats/bins_general_stats_mqc.tsv
diff --git a/subworkflows/08_binning.nf b/subworkflows/08_binning.nf
index 4573dc2..2ae4568 100644
--- a/subworkflows/08_binning.nf
+++ b/subworkflows/08_binning.nf
@@ -225,7 +225,8 @@ workflow STEP_08_BINNING {
GTDBTK(ch_bins_drep, gtdbtk_db, mash_db)
ch_gtdbtk_v = GTDBTK.out.v_gtdbtk
- ch_gtdbtk_affi = GTDBTK.out.gtdbtk_affiliations_predictions
+ ch_gtdbtk_affi_arch = GTDBTK.out.gtdbtk_affiliations_predictions_arch
+ ch_gtdbtk_affi_bact = GTDBTK.out.gtdbtk_affiliations_predictions_bact
/////////////////////////////
////GENOMES ABUNDANCES
@@ -254,7 +255,7 @@ workflow STEP_08_BINNING {
ch_collect_flagstats = GET_ALIGNMENT_METRICS.out.sam_flagstat.collect()
GENOMES_ABUNDANCES_PER_SAMPLE(ch_collect_coverages, ch_collect_flagstats,
- ch_bins_drep, ch_drep_stats , ch_gtdbtk_affi ,
+ ch_bins_drep, ch_drep_stats , ch_gtdbtk_affi_arch , ch_gtdbtk_affi_bact)
ch_heatmap_header_multiqc, ch_table_header_multiqc)
ch_bins_abundances_report = GENOMES_ABUNDANCES_PER_SAMPLE.out.report
--
GitLab
From 3a44fa42aa3dc34f65d65c787b1f8003352bce64 Mon Sep 17 00:00:00 2001
From: Philippe Ruiz <philippe.ruiz@inrae.fr>
Date: Tue, 11 Feb 2025 15:02:49 +0100
Subject: [PATCH 2/3] modify input and output for gtdbtk archee
---
modules/sum_up_bins_informations.nf | 40 ++++++++++++++++-------------
subworkflows/08_binning.nf | 5 ++--
2 files changed, 25 insertions(+), 20 deletions(-)
diff --git a/modules/sum_up_bins_informations.nf b/modules/sum_up_bins_informations.nf
index cc4a4ff..48f1bd1 100644
--- a/modules/sum_up_bins_informations.nf
+++ b/modules/sum_up_bins_informations.nf
@@ -4,7 +4,7 @@ process GENOMES_ABUNDANCES_PER_SAMPLE {
input:
path coverage_files
path flagstats_files
- val(bins_folder)
+ val bins_folder
path genomes_informations
path affiliations_predictions_arch
path affiliations_predictions_bact
@@ -20,23 +20,27 @@ process GENOMES_ABUNDANCES_PER_SAMPLE {
script:
"""
mkdir -p stats
- bins_per_sample_summarize.py --list_of_coverage_files ${coverage_files} \
- --list_of_flagstats_files ${flagstats_files} --affiliations_predictions ${affiliations_predictions_arch} \
- --bins_folder ${bins_folder} --genomes_informations ${genomes_informations} \
- --output_file genomes_abundances_arch.tsv --report_file stats/genomes_abundances_mqc_arch.tsv \
- --checkm_file stats/genomes_checkm_mqc_arch.json --table_file stats/bins_general_stats_mqc_arch.tsv
-
- bins_per_sample_summarize.py --list_of_coverage_files ${coverage_files} \
- --list_of_flagstats_files ${flagstats_files} --affiliations_predictions ${affiliations_predictions_bact} \
- --bins_folder ${bins_folder} --genomes_informations ${genomes_informations} \
- --output_file genomes_abundances_bact.tsv --report_file stats/genomes_abundances_mqc_bact.tsv \
- --checkm_file stats/genomes_checkm_mqc_bact.json --table_file stats/bins_general_stats_mqc_bact.tsv
-
- cat ${table_header_mqc} > stats/tmp.txt && cat stats/bins_general_stats_mqc.tsv >> stats/tmp.txt \
- && mv stats/tmp.txt stats/bins_general_stats_mqc.tsv
-
- cat ${heatmap_header_mqc} > stats/tmp.txt && cat stats/genomes_abundances_mqc.tsv >> stats/tmp.txt \
- && mv stats/tmp.txt stats/genomes_abundances_mqc.tsv
+
+ type=("bact" "arch")
+
+ for i in "\${type[@]}";
+ do
+ var_name="affiliations_predictions_\${i}"
+
+ bins_per_sample_summarize.py --list_of_coverage_files ${coverage_files} \\
+ --list_of_flagstats_files ${flagstats_files} --affiliations_predictions ${!var_name} \\
+ --bins_folder ${bins_folder} --genomes_informations ${genomes_informations} \\
+ --output_file genomes_abundances_\${i}.tsv --report_file stats/genomes_abundances_mqc_\${i}.tsv \\
+ --checkm_file stats/genomes_checkm_mqc_\${i}.json --table_file stats/bins_general_stats_mqc_\${i}.tsv
+
+ cat ${table_header_mqc} > stats/tmp_\${i}.txt && cat stats/bins_general_stats_mqc_\${i}.tsv >> stats/tmp_\${i}.txt \\
+ && mv stats/tmp_\${i}.txt stats/bins_general_stats_mqc_\${i}.tsv
+
+ cat ${heatmap_header_mqc} > stats/tmp_\${i}.txt && cat stats/genomes_abundances_mqc_\${i}.tsv >> stats/tmp_\${i}.txt \\
+ && mv stats/tmp_\${i}.txt stats/genomes_abundances_mqc_\${i}.tsv
+
+ done
+
"""
}
diff --git a/subworkflows/08_binning.nf b/subworkflows/08_binning.nf
index 2ae4568..6bcc673 100644
--- a/subworkflows/08_binning.nf
+++ b/subworkflows/08_binning.nf
@@ -171,7 +171,8 @@ workflow STEP_08_BINNING {
ch_bins_drep = Channel.empty()
ch_bam_bins = Channel.empty()
ch_reads_fna = Channel.empty()
- ch_gtdbtk_affi = Channel.empty()
+ ch_gtdbtk_affi_arch = Channel.empty()
+ ch_gtdbtk_affi_bact = Channel.empty()
ch_drep_stats = Channel.empty()
ch_bins_assembly = ch_bins_set.multiple.join(ch_assembly)
@@ -255,7 +256,7 @@ workflow STEP_08_BINNING {
ch_collect_flagstats = GET_ALIGNMENT_METRICS.out.sam_flagstat.collect()
GENOMES_ABUNDANCES_PER_SAMPLE(ch_collect_coverages, ch_collect_flagstats,
- ch_bins_drep, ch_drep_stats , ch_gtdbtk_affi_arch , ch_gtdbtk_affi_bact)
+ ch_bins_drep, ch_drep_stats , ch_gtdbtk_affi_arch , ch_gtdbtk_affi_bact,
ch_heatmap_header_multiqc, ch_table_header_multiqc)
ch_bins_abundances_report = GENOMES_ABUNDANCES_PER_SAMPLE.out.report
--
GitLab
From 0424d5d5d42f674d7e9b282b38fe9ada1f84f583 Mon Sep 17 00:00:00 2001
From: Philippe Ruiz <philippe.ruiz@inrae.fr>
Date: Mon, 3 Mar 2025 15:12:05 +0100
Subject: [PATCH 3/3] gtdbtk allways give in output bacteria and archaea
summary
---
docs/source/output.md | 3 ++-
modules/gtdbtk.nf | 9 +++++++++
modules/sum_up_bins_informations.nf | 8 ++++++--
3 files changed, 17 insertions(+), 3 deletions(-)
diff --git a/docs/source/output.md b/docs/source/output.md
index 9c75622..fc4ee22 100644
--- a/docs/source/output.md
+++ b/docs/source/output.md
@@ -267,7 +267,8 @@ 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, `closest_genome_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 of bacteria 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. |
+| `gtdbtk.ar53.summary.tsv` | Taxonomic classifications of archae 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/modules/gtdbtk.nf b/modules/gtdbtk.nf
index ffaeeb5..f820a00 100644
--- a/modules/gtdbtk.nf
+++ b/modules/gtdbtk.nf
@@ -19,5 +19,14 @@ process GTDBTK {
gtdbtk classify_wf --genome_dir $bins_drep -x fa --out_dir ./ --mash_db $mash_db --pplacer_cpus ${task.cpus} --cpus ${task.cpus}
echo \$(gtdbtk -h 2>&1) &> v_gtdbtk.txt
+
+ if [ ! -f ./gtdbtk.bac120.summary.tsv ]; then
+ touch ./gtdbtk.bac120.summary.tsv
+ fi
+
+ if [ ! -f ./gtdbtk.ar53.summary.tsv ]; then
+ touch ./gtdbtk.ar53.summary.tsv
+ fi
+
"""
}
\ No newline at end of file
diff --git a/modules/sum_up_bins_informations.nf b/modules/sum_up_bins_informations.nf
index 48f1bd1..e649b82 100644
--- a/modules/sum_up_bins_informations.nf
+++ b/modules/sum_up_bins_informations.nf
@@ -25,10 +25,14 @@ process GENOMES_ABUNDANCES_PER_SAMPLE {
for i in "\${type[@]}";
do
- var_name="affiliations_predictions_\${i}"
+ if [ "\$i" == "bact" ]; then
+ var_name=${affiliations_predictions_bact}
+ else
+ var_name=${affiliations_predictions_arch}
+ fi
bins_per_sample_summarize.py --list_of_coverage_files ${coverage_files} \\
- --list_of_flagstats_files ${flagstats_files} --affiliations_predictions ${!var_name} \\
+ --list_of_flagstats_files ${flagstats_files} --affiliations_predictions \$var_name \\
--bins_folder ${bins_folder} --genomes_informations ${genomes_informations} \\
--output_file genomes_abundances_\${i}.tsv --report_file stats/genomes_abundances_mqc_\${i}.tsv \\
--checkm_file stats/genomes_checkm_mqc_\${i}.json --table_file stats/bins_general_stats_mqc_\${i}.tsv
--
GitLab