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

Remove compressed flag from all mmseqs modules #7211

Merged
merged 14 commits into from
Jan 16, 2025
+446 −255
Merged

Remove compressed flag from all mmseqs modules #7211

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
b886a8b
Remove `compressed` flags from all mmmseqs modules
jasmezz Dec 12, 2024
2dc53e5
Update snapshots
SPPearce Dec 15, 2024
0ad5588
Merge branch 'master' into fix-mmseqs-compressed
SPPearce Dec 15, 2024
9038402
Merge branch 'master' into fix-mmseqs-compressed
jfy133 Jan 15, 2025
d639123
Fix language server and Yaml linting failures for all mmseqs modules
jfy133 Jan 15, 2025
7ee4099
Convert mmseqs/easysearch to nf-test
jfy133 Jan 15, 2025
cc8de7d
Fix linting for mmseqs/easysearch
jfy133 Jan 15, 2025
b8d627c
Co-authored with: @famosab Convert mmseqs/tsv2exprofiledb nf-test
jfy133 Jan 15, 2025
79d9f33
Try to fix linting errors
jfy133 Jan 15, 2025
95eb66b
rename variable db to database + snapshot output list and md5 few files
sateeshperi Jan 15, 2025
1e40c81
Merge branch 'master' into fix-mmseqs-compressed
jfy133 Jan 15, 2025
e2f33d3
Update modules/nf-core/mmseqs/tsv2exprofiledb/tests/nextflow.config
jfy133 Jan 15, 2025
ae4ab84
set mmseqs2 version mmseqs2:16.747c6
sateeshperi Jan 16, 2025
a4c71b2
Merge branch 'master' into fix-mmseqs-compressed
sateeshperi Jan 16, 2025
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
3 changes: 1 addition & 2 deletions modules/nf-core/mmseqs/cluster/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,8 +34,7 @@ process MMSEQS_CLUSTER {
${prefix}/${prefix} \\
tmp1 \\
$args \\
--threads ${task.cpus} \\
--compressed 1
--threads ${task.cpus}
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
6 changes: 3 additions & 3 deletions modules/nf-core/mmseqs/cluster/tests/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,15 +8,15 @@
"test_output_cluster.index"
],
[
"test_output_cluster.dbtype:md5,5c879eb8a8613fd4537b919e7d68d089",
"test_output_cluster.index:md5,ca7e1f0967222b06d7e05e47bcbe1e50"
"test_output_cluster.dbtype:md5,b9d9c6dbc098c97ae446f612efd8eafd",
"test_output_cluster.index:md5,9848b52b6df827d80a04f7c71c50056b"
],
"versions.yml:md5,4acad55952c6d1fb41ad7f5a44468aed"
],
"meta": {
"nf-test": "0.9.2",
"nextflow": "24.10.2"
},
"timestamp": "2024-12-05T10:44:45.713270981"
"timestamp": "2024-12-15T19:30:14.704271821"
}
}
3 changes: 1 addition & 2 deletions modules/nf-core/mmseqs/createdb/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,8 +33,7 @@ process MMSEQS_CREATEDB {
createdb \\
${sequence_name} \\
${prefix}/${prefix} \\
$args \\
--compressed 1
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
28 changes: 14 additions & 14 deletions modules/nf-core/mmseqs/createdb/tests/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,14 +8,14 @@
"single_end": false
},
[
"test:md5,7c3c2c5926cf8fa82e66b9628f680256",
"test.dbtype:md5,c8ed20c23ba91f4577f84c940c86c7db",
"test.index:md5,5b2fd8abd0ad3fee24738af7082e6a6e",
"test:md5,a2cda8768736a7a317a09d61556194bd",
"test.dbtype:md5,4352d88a78aa39750bf70cd6f27bcaa5",
"test.index:md5,4ba298b011e2472ce9f6b99fe6b6e3d5",
"test.lookup:md5,32f88756dbcb6aaf7b239b0d61730f1b",
"test.source:md5,9ada5b3ea6e1a7e16c4418eb98ae8d9d",
"test_h:md5,8c29f5ed94d83d7115e9c8a883ce358d",
"test_h.dbtype:md5,8895d3d8e9322aedbf45249dfb3ddb0a",
"test_h.index:md5,87c7c8c6d16018ebfaa6f408391a5ae2"
"test_h:md5,21c399702a071bdeecce09f9d1df4531",
"test_h.dbtype:md5,740bab4f9ec8808aedb68d6b1281aeb2",
"test_h.index:md5,d767fb43b37c0a644c676b00f9f93477"
]
]
],
Expand All @@ -27,7 +27,7 @@
"nf-test": "0.9.2",
"nextflow": "24.10.2"
},
"timestamp": "2024-12-05T10:35:27.322864475"
"timestamp": "2024-12-15T19:30:25.339409238"
},
"Should build an mmseqs db from a zipped amino acid sequence file": {
"content": [
Expand All @@ -37,14 +37,14 @@
"id": "test"
},
[
"test:md5,4b494965ed7ab67da8ca3f39523eb104",
"test.dbtype:md5,152afd7bf4dbe26f85032eee0269201a",
"test.index:md5,46f9d884e9a7f442fe1cd2ce339734e3",
"test:md5,1162504bc65aacf734abdcb0cdbe87de",
"test.dbtype:md5,f1d3ff8443297732862df21dc4e57262",
"test.index:md5,8cdcbc06c2b99fdb09f3d1735a76def9",
"test.lookup:md5,3e27cb93d9ee875ad42a6f32f5651bdc",
"test.source:md5,eaa64fc8a5f7ec1ee49b0dcbd1a72e9d",
"test_h:md5,6e798b81c70d191f78939c2dd6223a7f",
"test_h.dbtype:md5,8895d3d8e9322aedbf45249dfb3ddb0a",
"test_h.index:md5,d5ac49ff56df064b980fa0eb5da57673"
"test_h:md5,f258f8cc04f83c270a75e8b00a6d2d89",
"test_h.dbtype:md5,740bab4f9ec8808aedb68d6b1281aeb2",
"test_h.index:md5,844bf1950bcd37284fdc5d7117ee4241"
]
]
],
Expand All @@ -56,6 +56,6 @@
"nf-test": "0.9.2",
"nextflow": "24.10.2"
},
"timestamp": "2024-12-05T10:35:33.418552595"
"timestamp": "2024-12-15T19:30:34.93361715"
}
}
20 changes: 10 additions & 10 deletions modules/nf-core/mmseqs/createindex/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,16 +3,16 @@ process MMSEQS_CREATEINDEX {
label 'process_high'

conda "${moduleDir}/environment.yml"
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/mmseqs2:15.6f452--pl5321h6a68c12_0':
'biocontainers/mmseqs2:15.6f452--pl5321h6a68c12_0' }"
container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
? 'https://depot.galaxyproject.org/singularity/mmseqs2:15.6f452--pl5321h6a68c12_0'
: 'biocontainers/mmseqs2:15.6f452--pl5321h6a68c12_0'}"

input:
tuple val(meta), path(db)

output:
tuple val(meta), path(db) , emit: db_indexed
path "versions.yml" , emit: versions
tuple val(meta), path(db), emit: db_indexed
path "versions.yml", emit: versions

when:
task.ext.when == null || task.ext.when
Expand All @@ -23,15 +23,14 @@ process MMSEQS_CREATEINDEX {
def prefix = task.ext.prefix ?: "${meta.id}"

"""
DB_INPUT_PATH_NAME=\$(find -L "$db/" -maxdepth 1 -name "$args2" | sed 's/\\.[^.]*\$//' | sed -e 'N;s/^\\(.*\\).*\\n\\1.*\$/\\1\\n\\1/;D' )
DB_INPUT_PATH_NAME=\$(find -L "${db}/" -maxdepth 1 -name "${args2}" | sed 's/\\.[^.]*\$//' | sed -e 'N;s/^\\(.*\\).*\\n\\1.*\$/\\1\\n\\1/;D' )

mmseqs \\
createindex \\
\${DB_INPUT_PATH_NAME} \\
tmp1 \\
$args \\
--threads ${task.cpus} \\
--compressed 1
${args} \\
--threads ${task.cpus}

cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand All @@ -40,8 +39,9 @@ process MMSEQS_CREATEINDEX {
"""

stub:
def args2 = task.ext.args2 ?: "*.dbtype"
"""
DB_INPUT_PATH_NAME=\$(find -L "$db/" -maxdepth 1 -name "$args2" | sed 's/\\.[^.]*\$//' | sed -e 'N;s/^\\(.*\\).*\\n\\1.*\$/\\1\\n\\1/;D' )
DB_INPUT_PATH_NAME=\$(find -L "${db}/" -maxdepth 1 -name "${args2}" | sed 's/\\.[^.]*\$//' | sed -e 'N;s/^\\(.*\\).*\\n\\1.*\$/\\1\\n\\1/;D' )

touch "\${DB_PATH_NAME}.idx"

Expand Down
3 changes: 1 addition & 2 deletions modules/nf-core/mmseqs/createtsv/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,8 +40,7 @@ process MMSEQS_CREATETSV {
\$DB_RESULT_PATH_NAME \\
${prefix}.tsv \\
$args \\
--threads ${task.cpus} \\
--compressed 1
--threads ${task.cpus}

cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
1 change: 0 additions & 1 deletion modules/nf-core/mmseqs/databases/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,6 @@ process MMSEQS_DATABASES {
${prefix}/database \\
tmp/ \\
--threads ${task.cpus} \\
--compressed 1 \\
${args}
cat <<-END_VERSIONS > versions.yml
Expand Down
25 changes: 13 additions & 12 deletions modules/nf-core/mmseqs/easysearch/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,20 +1,19 @@

process MMSEQS_EASYSEARCH {
tag "$meta.id"
tag "${meta.id}"
label 'process_high'

conda "${moduleDir}/environment.yml"
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/mmseqs2:15.6f452--pl5321h6a68c12_0':
'biocontainers/mmseqs2:15.6f452--pl5321h6a68c12_0' }"
container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
? 'https://depot.galaxyproject.org/singularity/mmseqs2:15.6f452--pl5321h6a68c12_0'
: 'biocontainers/mmseqs2:15.6f452--pl5321h6a68c12_0'}"

input:
tuple val(meta) , path(fasta)
tuple val(meta), path(fasta)
tuple val(meta2), path(db_target)

output:
tuple val(meta), path("${prefix}.tsv"), emit: tsv
path "versions.yml" , emit: versions
path "versions.yml", emit: versions

when:
task.ext.when == null || task.ext.when
Expand All @@ -27,17 +26,16 @@ process MMSEQS_EASYSEARCH {
mkdir -p ${prefix}

# Extract files with specified args based suffix | remove suffix | isolate longest common substring of files
DB_TARGET_PATH_NAME=\$(find -L "$db_target/" -maxdepth 1 -name "$args2" | sed 's/\\.[^.]*\$//' | sed -e 'N;s/^\\(.*\\).*\\n\\1.*\$/\\1\\n\\1/;D' )
DB_TARGET_PATH_NAME=\$(find -L "${db_target}/" -maxdepth 1 -name "${args2}" | sed 's/\\.[^.]*\$//' | sed -e 'N;s/^\\(.*\\).*\\n\\1.*\$/\\1\\n\\1/;D' )

mmseqs \\
easy-search \\
$fasta \\
${fasta} \\
\$DB_TARGET_PATH_NAME \\
${prefix}.tsv \\
tmp1 \\
$args \\
--threads ${task.cpus} \\
--compressed 1
${args} \\
--threads ${task.cpus}


cat <<-END_VERSIONS > versions.yml
Expand All @@ -47,6 +45,9 @@ process MMSEQS_EASYSEARCH {
"""

stub:
def args = task.ext.args ?: ''
def args2 = task.ext.args2 ?: "*.dbtype"
prefix = task.ext.prefix ?: "${meta.id}"
"""
touch ${prefix}.tsv

Expand Down
1 change: 0 additions & 1 deletion modules/nf-core/mmseqs/easysearch/meta.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,3 @@
# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json
name: "mmseqs_easysearch"
description: Searches for the sequences of a fasta file in a database using MMseqs2
keywords:
Expand Down
68 changes: 68 additions & 0 deletions modules/nf-core/mmseqs/easysearch/tests/main.nf.test
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,68 @@
nextflow_process {

name "Test Process MMSEQS_EASYSEARCH"
script "../main.nf"
process "MMSEQS_EASYSEARCH"
config './nextflow.config'

tag "modules"
tag "modules_nfcore"
tag "mmseqs"
tag "mmseqs/easysearch"
tag "mmseqs/createdb"

setup {

run("MMSEQS_CREATEDB") {
script "../../createdb/main.nf"
process {
"""
input[0] = [ [id: 'test_query', single_end: true], file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fasta/contigs.fasta', checkIfExists: true) ]
"""
}
}
}

test("sarscov2 - illumina - contigs - fasta") {

when {
process {
"""
input[0] = [ [id: 'test_scaffolds', single_end: true], file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fasta/scaffolds.fasta', checkIfExists: true) ]
input[1] = MMSEQS_CREATEDB.out.db
"""
}
}

then {
assertAll(
{ assert process.success },
{ assert snapshot(process.out).match() }
)
}

}

test("sarscov2 - illumina - contigs - fasta - stub") {

options "-stub"

when {
process {
"""
input[0] = [ [id: 'test_scaffolds', single_end: true], file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fasta/scaffolds.fasta', checkIfExists: true) ]
input[1] = MMSEQS_CREATEDB.out.db
"""
}
}

then {
assertAll(
{ assert process.success },
{ assert snapshot(process.out).match() }
)
}

}

}
72 changes: 72 additions & 0 deletions modules/nf-core/mmseqs/easysearch/tests/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,72 @@
{
"sarscov2 - illumina - contigs - fasta": {
"content": [
{
"0": [
[
{
"id": "test_scaffolds",
"single_end": true
},
"test_scaffolds.tsv:md5,98a6e138ad41ed04366808799fd6a4b8"
]
],
"1": [
"versions.yml:md5,6e4d1e0d47fdc34c4ef32ad7b030cf70"
],
"tsv": [
[
{
"id": "test_scaffolds",
"single_end": true
},
"test_scaffolds.tsv:md5,98a6e138ad41ed04366808799fd6a4b8"
]
],
"versions": [
"versions.yml:md5,6e4d1e0d47fdc34c4ef32ad7b030cf70"
]
}
],
"meta": {
"nf-test": "0.9.0",
"nextflow": "24.10.2"
},
"timestamp": "2025-01-15T10:08:31.865068417"
},
"sarscov2 - illumina - contigs - fasta - stub": {
"content": [
{
"0": [
[
{
"id": "test_scaffolds",
"single_end": true
},
"test_scaffolds.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"1": [
"versions.yml:md5,bef949a977594a12d605c2d30198ab27"
],
"tsv": [
[
{
"id": "test_scaffolds",
"single_end": true
},
"test_scaffolds.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"versions": [
"versions.yml:md5,bef949a977594a12d605c2d30198ab27"
]
}
],
"meta": {
"nf-test": "0.9.0",
"nextflow": "24.10.2"
},
"timestamp": "2025-01-15T10:09:30.132833597"
}
}
5 changes: 5 additions & 0 deletions modules/nf-core/mmseqs/easysearch/tests/nextflow.config
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
process {
withName: MMSEQS_EASYSEARCH {
ext.args = '--remove-tmp-files 1 --search-type 2'
}
}
3 changes: 1 addition & 2 deletions modules/nf-core/mmseqs/linclust/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,8 +34,7 @@ process MMSEQS_LINCLUST {
${prefix}/${prefix} \\
tmp1 \\
$args \\
--threads ${task.cpus} \\
--compressed 1
--threads ${task.cpus}
cat <<-END_VERSIONS > versions.yml
"${task.process}":
Expand Down
Loading
Loading