Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

LAST alignment statistics for MultiQC #5902

Merged
merged 12 commits into from
Jul 11, 2024
Merged

LAST alignment statistics for MultiQC #5902

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
203e719
last train modified to output multiqc
U13bs1125 Jul 2, 2024
22db3b1
Report alignment length and percent similarity, for MultiQC.
charles-plessy Jul 2, 2024
1156df2
Update snapshot file.
charles-plessy Jul 2, 2024
9a1f051
Merge branch 'lastrain_mult' into last-alignment-statistics
charles-plessy Jul 2, 2024
27f4312
Document the new channels
charles-plessy Jul 2, 2024
28750d9
Fix indentation
charles-plessy Jul 2, 2024
6a97674
Update test results.
charles-plessy Jul 2, 2024
0d28d46
Merge branch 'master' into last-alignment-statistics
charles-plessy Jul 2, 2024
b56e0cb
Give a longer suffix for better MultiQC search patterns.
charles-plessy Jul 3, 2024
5a85097
Merge branch 'last-alignment-statistics' of github.com:charles-plessy…
charles-plessy Jul 3, 2024
a4af769
Merge branch 'master' into last-alignment-statistics
charles-plessy Jul 3, 2024
1d54531
Merge branch 'master' into last-alignment-statistics
charles-plessy Jul 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 24 additions & 4 deletions modules/nf-core/last/lastal/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ process LAST_LASTAL {

output:
tuple val(meta), path("*.maf.gz"), emit: maf
tuple val(meta), path("*.tsv") , emit: multiqc
path "versions.yml" , emit: versions

when:
Expand All @@ -25,15 +26,33 @@ process LAST_LASTAL {
"""
INDEX_NAME=\$(basename \$(ls $index/*.des) .des)
set -o pipefail

function calculate_psl_metrics() {
awk 'BEGIN {
FS="\t"; # Set field separator as tab
totalMatches = 0;
totalAlignmentLength = 0;
print "Sample\tTotalAlignmentLength\tPercentSimilarity"; # Header for MultiQC
}
{
totalMatches += \$1 + \$3; # Sum matches and repMatches
totalAlignmentLength += \$1 + \$2 + \$3 + \$6 + \$8; # Sum matches, misMatches, repMatches, qBaseInsert, and tBaseInsert
}
END {
percentSimilarity = (totalAlignmentLength > 0) ? (totalMatches / totalAlignmentLength * 100) : 0;
print "$meta.id" "\t" totalAlignmentLength "\t" percentSimilarity; # Data in TSV format
}'
}

lastal \\
-P $task.cpus \\
$trained_params \\
$args \\
${index}/\$INDEX_NAME \\
$fastx \\
| gzip --no-name > ${prefix}.\$INDEX_NAME.maf.gz
# gzip needs --no-name otherwise it puts a timestamp in the file,
# which makes its checksum non-reproducible.
$fastx |
tee >(gzip --no-name > ${prefix}.maf.gz) |
maf-convert psl |
calculate_psl_metrics > ${prefix}.tsv

cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand All @@ -48,6 +67,7 @@ process LAST_LASTAL {
"""
INDEX_NAME=STUB
echo stub | gzip --no-name > ${prefix}.\$INDEX_NAME.maf.gz
touch ${prefix}.tsv

cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
4 changes: 4 additions & 0 deletions modules/nf-core/last/lastal/meta.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,10 @@ output:
type: file
description: Gzipped MAF (Multiple Alignment Format) file
pattern: "*.{maf.gz}"
- multiqc:
type: file
description: Alignment summary for MultiQC
pattern: "*.tsv"
authors:
- "@charles-plessy"
maintainers:
Expand Down
68 changes: 61 additions & 7 deletions modules/nf-core/last/lastal/tests/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,10 +8,19 @@
"id": "contigs",
"single_end": false
},
"contigs.genome.maf.gz:md5,902274b72657f62d270d284dc211aa7f"
"contigs.maf.gz:md5,902274b72657f62d270d284dc211aa7f"
]
],
"1": [
[
{
"id": "contigs",
"single_end": false
},
"contigs.tsv:md5,f028e69bd64e54080b9a03fd809cba74"
]
],
"2": [
"versions.yml:md5,e0a425d7cbca674252a1e4328b247ca2"
],
"maf": [
Expand All @@ -20,7 +29,16 @@
"id": "contigs",
"single_end": false
},
"contigs.genome.maf.gz:md5,902274b72657f62d270d284dc211aa7f"
"contigs.maf.gz:md5,902274b72657f62d270d284dc211aa7f"
]
],
"multiqc": [
[
{
"id": "contigs",
"single_end": false
},
"contigs.tsv:md5,f028e69bd64e54080b9a03fd809cba74"
]
],
"versions": [
Expand All @@ -32,7 +50,7 @@
"nf-test": "0.8.4",
"nextflow": "24.04.2"
},
"timestamp": "2024-06-06T23:11:59.764152"
"timestamp": "2024-07-02T17:57:48.589408"
},
"sarscov2 - contigs - genome - stub": {
"content": [
Expand All @@ -47,6 +65,15 @@
]
],
"1": [
[
{
"id": "contigs",
"single_end": false
},
"contigs.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"2": [
"versions.yml:md5,e0a425d7cbca674252a1e4328b247ca2"
],
"maf": [
Expand All @@ -58,6 +85,15 @@
"contigs.STUB.maf.gz:md5,f50b84b1db4b83ba62ec1deacc69c260"
]
],
"multiqc": [
[
{
"id": "contigs",
"single_end": false
},
"contigs.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"versions": [
"versions.yml:md5,e0a425d7cbca674252a1e4328b247ca2"
]
Expand All @@ -67,7 +103,7 @@
"nf-test": "0.8.4",
"nextflow": "24.04.2"
},
"timestamp": "2024-06-06T23:12:43.028075"
"timestamp": "2024-07-02T17:58:30.521811"
},
"sarscov2 - contigs - genome - withparams": {
"content": [
Expand All @@ -78,10 +114,19 @@
"id": "contigs",
"single_end": false
},
"contigs.genome.maf.gz:md5,8cb97b6daa34dbf9c723a2c4a984992d"
"contigs.maf.gz:md5,8cb97b6daa34dbf9c723a2c4a984992d"
]
],
"1": [
[
{
"id": "contigs",
"single_end": false
},
"contigs.tsv:md5,f315664aa18f1f6bad79486f9750f200"
]
],
"2": [
"versions.yml:md5,e0a425d7cbca674252a1e4328b247ca2"
],
"maf": [
Expand All @@ -90,7 +135,16 @@
"id": "contigs",
"single_end": false
},
"contigs.genome.maf.gz:md5,8cb97b6daa34dbf9c723a2c4a984992d"
"contigs.maf.gz:md5,8cb97b6daa34dbf9c723a2c4a984992d"
]
],
"multiqc": [
[
{
"id": "contigs",
"single_end": false
},
"contigs.tsv:md5,f315664aa18f1f6bad79486f9750f200"
]
],
"versions": [
Expand All @@ -102,6 +156,6 @@
"nf-test": "0.8.4",
"nextflow": "24.04.2"
},
"timestamp": "2024-06-06T23:12:21.536568"
"timestamp": "2024-07-02T17:58:09.677672"
}
}
26 changes: 25 additions & 1 deletion modules/nf-core/last/split/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ process LAST_SPLIT {

output:
tuple val(meta), path("*.maf.gz"), emit: maf
tuple val(meta), path("*.tsv") , emit: multiqc
path "versions.yml" , emit: versions

when:
Expand All @@ -23,7 +24,29 @@ process LAST_SPLIT {
if( "$maf" == "${prefix}.maf.gz" ) error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
"""
set -o pipefail
zcat < $maf | last-split $args | gzip --no-name > ${prefix}.maf.gz

function calculate_psl_metrics() {
awk 'BEGIN {
FS="\t"; # Set field separator as tab
totalMatches = 0;
totalAlignmentLength = 0;
print "Sample\tTotalAlignmentLength\tPercentSimilarity"; # Header for MultiQC
}
{
totalMatches += \$1 + \$3; # Sum matches and repMatches
totalAlignmentLength += \$1 + \$2 + \$3 + \$6 + \$8; # Sum matches, misMatches, repMatches, qBaseInsert, and tBaseInsert
}
END {
percentSimilarity = (totalAlignmentLength > 0) ? (totalMatches / totalAlignmentLength * 100) : 0;
print "$meta.id" "\t" totalAlignmentLength "\t" percentSimilarity; # Data in TSV format
}'
}

zcat < $maf |
last-split $args |
tee >(gzip --no-name > ${prefix}.maf.gz) |
maf-convert psl |
calculate_psl_metrics > ${prefix}.tsv

cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand All @@ -37,6 +60,7 @@ process LAST_SPLIT {
if( "$maf" == "${prefix}.maf.gz" ) error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
"""
echo stub | gzip --no-name > ${prefix}.maf.gz
touch ${prefix}.tsv

cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
4 changes: 4 additions & 0 deletions modules/nf-core/last/split/meta.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,10 @@ output:
type: file
description: Multiple Aligment Format (MAF) file, compressed with gzip
pattern: "*.{maf.gz}"
- multiqc:
type: file
description: Alignment summary for MultiQC
pattern: "*.tsv"
authors:
- "@aleksandrabliznina"
- "@charles-plessy"
Expand Down
36 changes: 34 additions & 2 deletions modules/nf-core/last/split/tests/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,14 @@
]
],
"1": [
[
{
"id": "sarscov.contigs.genome"
},
"sarscov.contigs.genome.tsv:md5,b625a3b37343e9e6a279b8625d4c2da8"
]
],
"2": [
"versions.yml:md5,9e429d0800988ae0bbe5000827d34ad1"
],
"maf": [
Expand All @@ -21,6 +29,14 @@
"sarscov.contigs.genome.maf.gz:md5,689cb18ff7098ff90eaf87017f590208"
]
],
"multiqc": [
[
{
"id": "sarscov.contigs.genome"
},
"sarscov.contigs.genome.tsv:md5,b625a3b37343e9e6a279b8625d4c2da8"
]
],
"versions": [
"versions.yml:md5,9e429d0800988ae0bbe5000827d34ad1"
]
Expand All @@ -30,7 +46,7 @@
"nf-test": "0.8.4",
"nextflow": "24.04.2"
},
"timestamp": "2024-06-06T17:49:24.045661"
"timestamp": "2024-07-02T11:45:00.535348"
},
"sarscov2 - contigs_genome - stub": {
"content": [
Expand All @@ -44,6 +60,14 @@
]
],
"1": [
[
{
"id": "sarscov.contigs.genome"
},
"sarscov.contigs.genome.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"2": [
"versions.yml:md5,9e429d0800988ae0bbe5000827d34ad1"
],
"maf": [
Expand All @@ -54,6 +78,14 @@
"sarscov.contigs.genome.maf.gz:md5,f50b84b1db4b83ba62ec1deacc69c260"
]
],
"multiqc": [
[
{
"id": "sarscov.contigs.genome"
},
"sarscov.contigs.genome.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"versions": [
"versions.yml:md5,9e429d0800988ae0bbe5000827d34ad1"
]
Expand All @@ -63,6 +95,6 @@
"nf-test": "0.8.4",
"nextflow": "24.04.2"
},
"timestamp": "2024-06-06T17:50:20.139442"
"timestamp": "2024-07-02T11:45:21.243325"
}
}
12 changes: 12 additions & 0 deletions modules/nf-core/last/train/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ process LAST_TRAIN {

output:
tuple val(meta), path("*.train"), emit: param_file
tuple val(meta), path("*.tsv") , emit: multiqc
path "versions.yml" , emit: versions

when:
Expand All @@ -31,6 +32,16 @@ process LAST_TRAIN {
$fastx \\
> ${prefix}.\$INDEX_NAME.train

echo "id\tsubstitution_percent_identity\tlast -t\tlast -a\tlast -A\tlast -b\tlast -B\tlast -S" > ${prefix}.train.tsv
printf "\$(basename ${prefix}.\$INDEX_NAME.train .target.train)\t" >> ${prefix}.train.tsv
grep 'substitution percent identity' ${prefix}.\$INDEX_NAME.train | tail -n 1 | awk '{print \$5}' | tr '\n' '\t' >> ${prefix}.train.tsv
grep 'last -t' ${prefix}.\$INDEX_NAME.train | tail -n 1 | awk '{print \$2}' | sed -e 's/-t//' | tr '\n' '\t' >> ${prefix}.train.tsv
grep 'last -a' ${prefix}.\$INDEX_NAME.train | tail -n 1 | awk '{print \$3}' | tr '\n' '\t' >> ${prefix}.train.tsv
grep 'last -A' ${prefix}.\$INDEX_NAME.train | tail -n 1 | awk '{print \$3}' | tr '\n' '\t' >> ${prefix}.train.tsv
grep 'last -b' ${prefix}.\$INDEX_NAME.train | tail -n 1 | awk '{print \$3}' | tr '\n' '\t' >> ${prefix}.train.tsv
grep 'last -B' ${prefix}.\$INDEX_NAME.train | tail -n 1 | awk '{print \$3}' | tr '\n' '\t' >> ${prefix}.train.tsv
grep 'last -S' ${prefix}.\$INDEX_NAME.train | tail -n 1 | awk '{print \$3}' >> ${prefix}.train.tsv

cat <<-END_VERSIONS > versions.yml
"${task.process}":
last: \$(lastdb --version | sed 's/lastdb //')
Expand All @@ -43,6 +54,7 @@ process LAST_TRAIN {
"""
INDEX_NAME=STUB
touch ${prefix}.\$INDEX_NAME.train
touch ${prefix}.train.tsv

cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
5 changes: 5 additions & 0 deletions modules/nf-core/last/train/meta.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,8 +42,13 @@ output:
type: file
description: Trained parameter file
pattern: "*.train"
- multiqc:
type: file
description: Alignment parameter summary for MultiQC
pattern: "*.tsv"
authors:
- "@aleksandrabliznina"
- "@charles-plessy"
- "@U13bs1125"
maintainers:
- "@charles-plessy"
Loading
Loading