Build branch main with version main (cf97972)

Build pipeline: viash-hub.htrnaseq.main-6f8s8

Source commit: cf9797232d

Source message: WIP: add component to parse STAR logs (#7)

* WIP: add component to parse STAR logs

* Add tests and logging
This commit is contained in:
CI
2024-09-17 09:02:15 +00:00
parent bde35f120c
commit b8abf8c490
37 changed files with 6473 additions and 40 deletions

View File

@@ -0,0 +1,214 @@
name: "combine_star_logs"
namespace: "stats"
version: "main"
argument_groups:
- name: "Arguments"
arguments:
- type: "string"
name: "--barcodes"
description: "Barcodes responding to the respective log files.\n"
info: null
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--star_logs"
description: "Paths to the STAR log files (most frequently called Log.final.out)\n"
info: null
example:
- "Log.final.out"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--gene_summary_logs"
description: "Paths to the Summary.csv files from the STAR Solo output. Can be\
\ found in\nthe 'Solo.out/Gene' folder relative to the root of the STAR output\
\ directory. \n"
info: null
example:
- "Summary.txt"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--reads_per_gene_logs"
description: "Paths to the 'ReadsPerGene.out.tab' files as output by STAR.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--output"
description: "Tab-delimited file describing for each barcode (as the rows), the\
\ metrics (as columns)\ngathered from the different input files. \n"
info: null
default:
- "starLogs.txt"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "python_script"
path: "script.py"
is_executable: true
- type: "file"
path: "nextflow_labels.config"
dest: "nextflow_labels.config"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
license: "MIT"
links:
repository: "https://github.com/viash-hub/htrnaseq"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
script:
- "includeConfig(\"nextflow_labels.config\")"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "python:3.12-slim"
target_registry: "images.viash-hub.com"
target_tag: "main"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "pandas"
upgrade: true
test_setup:
- type: "python"
user: false
packages:
- "viashpy"
upgrade: true
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/stats/combine_star_logs/config.vsh.yaml"
runner: "nextflow"
engine: "docker|native"
output: "target/nextflow/stats/combine_star_logs"
executable: "target/nextflow/stats/combine_star_logs/main.nf"
viash_version: "0.9.0-RC7"
git_commit: "cf9797232db1306bfd5696287928cababe317d99"
git_remote: "https://x-access-token:ghs_KjB7pWu8DQM3iFulLu7RI06qnt5K8S1A0eaE@github.com/viash-hub/htrnaseq"
package_config:
name: "htrnaseq"
version: "main"
description: "High-throughput pipeline [WIP]\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].config.script\
\ := 'includeConfig(\"nextflow_labels.config\")'\n.resources += {path: '/src/config/labels.config',\
\ dest: 'nextflow_labels.config'}\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'main'"
keywords:
- "bioinformatics"
- "sequence"
- "high-throughput"
- "mapping"
- "counting"
- "pipeline"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/htrnaseq"
issue_tracker: "https://github.com/viash-hub/htrnaseq/issues"