Skip to content
Open
Original file line number Diff line number Diff line change
@@ -1,5 +1,25 @@
# Changelog

## [0.1.2] - 2026-09-21

### Automatic update
- `toolshed.g2.bx.psu.edu/repos/iuc/fastp/fastp/0.23.2+galaxy0` was updated to `toolshed.g2.bx.psu.edu/repos/iuc/fastp/fastp/1.3.7+galaxy0`
- `toolshed.g2.bx.psu.edu/repos/iuc/snpeff/snpEff_build_gb/4.3+T.galaxy4` was updated to `toolshed.g2.bx.psu.edu/repos/iuc/snpeff/snpEff_build_gb/5.4+galaxy0`
- `toolshed.g2.bx.psu.edu/repos/devteam/bwa/bwa_mem/0.7.17.2` was updated to `toolshed.g2.bx.psu.edu/repos/devteam/bwa/bwa_mem/0.7.19+galaxy1`
- `toolshed.g2.bx.psu.edu/repos/iuc/samtools_view/samtools_view/1.13+galaxy1` was updated to `toolshed.g2.bx.psu.edu/repos/iuc/samtools_view/samtools_view/1.22+galaxy2`
- `toolshed.g2.bx.psu.edu/repos/devteam/picard/picard_MarkDuplicates/2.18.2.2` was updated to `toolshed.g2.bx.psu.edu/repos/devteam/picard/picard_MarkDuplicates/3.1.1.0`
- `toolshed.g2.bx.psu.edu/repos/devteam/samtools_stats/samtools_stats/2.0.2+galaxy2` was updated to `toolshed.g2.bx.psu.edu/repos/devteam/samtools_stats/samtools_stats/2.0.9`
- `toolshed.g2.bx.psu.edu/repos/iuc/multiqc/multiqc/1.11+galaxy0` was updated to `toolshed.g2.bx.psu.edu/repos/iuc/multiqc/multiqc/1.35+galaxy4`
- `toolshed.g2.bx.psu.edu/repos/iuc/lofreq_indelqual/lofreq_indelqual/2.1.5+galaxy0` was updated to `toolshed.g2.bx.psu.edu/repos/iuc/lofreq_indelqual/lofreq_indelqual/2.1.5+galaxy1`
- `toolshed.g2.bx.psu.edu/repos/iuc/lofreq_call/lofreq_call/2.1.5+galaxy1` was updated to `toolshed.g2.bx.psu.edu/repos/iuc/lofreq_call/lofreq_call/2.1.5+galaxy3`
- `toolshed.g2.bx.psu.edu/repos/iuc/snpeff/snpEff/4.3+T.galaxy1` was updated to `toolshed.g2.bx.psu.edu/repos/iuc/snpeff/snpEff/5.4+galaxy0`

### Changed
- Reference sequence ids now keep their GenBank version (e.g. `KP849471.1` instead of `KP849471`). SnpEff 5.4 names chromosomes after the GenBank VERSION, so stripping the version left every variant unannotated (`ERROR_CHROMOSOME_NOT_FOUND`).

### Added
- Optional `Strip version from reference sequence ids` input (default: false). When set, the workflow also outputs `Fasta sequences for genbank file without version`, the reference FASTA with ids as in 0.1.1 (e.g. `KP849471`).


## [0.1.1] - 2023-11-20

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
- hash_function: SHA-1
hash_value: 586d54741cb8b8f7d2e473827d3b25e5a235f9f7
Name for genome database: mpxv
Strip version from reference sequence ids: true
Paired Collection:
class: Collection
collection_type: list:paired
Expand All @@ -32,25 +33,108 @@
Fasta sequences for genbank file:
path: test-data/Fasta sequences for genbank file.fasta
compare: contains
Fasta sequences for genbank file without version:
asserts:
- has_line:
line: ">KP849471"
- not_has_text:
text: "KP849471.1"
- has_n_lines:
min: 2
SnpEff variants:
element_tests:
ERR3485802:
path: test-data/SnpEff variants.vcf
compare: diff
lines_diff: 6
asserts:
- has_line:
line: "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO"
- has_text:
text: '##SnpEffVersion='
# SnpEff must find the chromosome in the database built from the GenBank file
- not_has_text:
text: ERROR_CHROMOSOME_NOT_FOUND
# 92 variant records (90 PASS, 2 sb_fdr), 54 of them annotated, with the reference tool versions
- has_line_matching:
expression: 'KP849471(\.1)?\t.*'
n: 92
delta: 5
- has_line_matching:
expression: 'KP849471(\.1)?\t([^\t]+\t){5}PASS\t.*'
n: 90
delta: 5
- has_line_matching:
expression: 'KP849471(\.1)?\t([^\t]+\t){5}sb_fdr\t.*'
n: 2
delta: 2
- has_line_matching:
expression: 'KP849471(\.1)?\t.*;EFF=[A-Z_+]+\((HIGH|MODERATE|LOW|MODIFIER)\|.*'
n: 54
delta: 6
- has_line_matching:
expression: 'KP849471(\.1)?\t14383\t\.\tT\tC\t[0-9.]+\tPASS\t.*EFF=NON_SYNONYMOUS_CODING\(MODERATE\|MISSENSE\|Aaa/Gaa\|K393E\|.*'
- has_line_matching:
expression: 'KP849471(\.1)?\t30663\t\.\tC\tT\t[0-9.]+\tPASS\t.*EFF=SYNONYMOUS_CODING\(LOW\|SILENT\|acC/acT\|T101\|.*'
- has_line_matching:
expression: 'KP849471(\.1)?\t177387\t\.\tG\tT\t[0-9.]+\tPASS\t.*EFF=NON_SYNONYMOUS_CODING\(MODERATE\|MISSENSE\|Gac/Tac\|D627Y\|.*'
- has_line_matching:
expression: 'KP849471(\.1)?\t190964\t\.\tC\tT\t[0-9.]+\tPASS\t.*EFF=NON_SYNONYMOUS_CODING\(MODERATE\|MISSENSE\|gCa/gTa\|A4V\|.*'
- has_line_matching:
expression: 'KP849471(\.1)?\t190951\t\.\tG\tA\t[0-9.]+\tsb_fdr\t.*'
called_variants:
element_tests:
ERR3485802:
path: test-data/called_variants.vcf
compare: diff
lines_diff: 6
asserts:
- has_line:
line: "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO"
# 92 variant records (17 indels), all PASS before soft filtering
- has_line_matching:
expression: 'KP849471(\.1)?\t.*'
n: 92
delta: 5
- has_line_matching:
expression: 'KP849471(\.1)?\t.*;INDEL;.*'
n: 17
delta: 3
- has_line_matching:
expression: 'KP849471(\.1)?\t8226\t\.\tG\tA\t[0-9.]+\tPASS\tDP=5;AF=1(\.0+)?;SB=0;DP4=0,0,4,1'
- has_line_matching:
expression: 'KP849471(\.1)?\t93756\t\.\tTAAATGG\tT\t[0-9.]+\tPASS\t.*INDEL;.*'
- has_line_matching:
expression: 'KP849471(\.1)?\t190951\t\.\tG\tA\t[0-9.]+\tPASS\t.*'
mapped_reads_stats:
element_tests:
ERR3485802:
path: test-data/mapped_reads_stats.tabular
asserts:
- has_text:
text: This file was produced by samtools stats
- has_line_matching:
expression: 'SN\traw total sequences:\t4626(\t.*)?'
- has_line:
line: "SN\treads mapped:\t4626"
- has_line_matching:
expression: 'SN\treads properly paired:\t4626(\t.*)?'
- has_line_matching:
expression: 'SN\treads duplicated:\t0(\t.*)?'
# 150 with fastp 0.23.4, 151 with fastp 1.3.7
- has_line_matching:
expression: 'SN\taverage length:\t15[01]'
soft_filtered_variants:
element_tests:
ERR3485802:
path: test-data/soft_filtered_variants.vcf
compare: diff
lines_diff: 6
asserts:
- has_line:
line: "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO"
# 92 variant records (90 PASS, 2 sb_fdr)
- has_line_matching:
expression: 'KP849471(\.1)?\t.*'
n: 92
delta: 5
- has_line_matching:
expression: 'KP849471(\.1)?\t([^\t]+\t){5}sb_fdr\t.*'
n: 2
delta: 2
- has_line_matching:
expression: 'KP849471(\.1)?\t8226\t\.\tG\tA\t[0-9.]+\tPASS\tDP=5;AF=1(\.0+)?;SB=0;DP4=0,0,4,1'
- has_line_matching:
expression: 'KP849471(\.1)?\t153631\t\.\tG\tT\t[0-9.]+\tsb_fdr\t.*'
- has_line_matching:
expression: 'KP849471(\.1)?\t190951\t\.\tG\tA\t[0-9.]+\tsb_fdr\t.*'
Loading
Loading