Skip to content

Commit 4530155

Browse files
d4straubd4straub
authored
Merge pull request #1028 from d4straub/remove-support-for-legacy-datasheet
Remove support for legacy sample sheet and adjust multiregion sheet
2 parents 0ea1c1f + 94c0c51 commit 4530155

58 files changed

Lines changed: 101 additions & 170 deletions

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎CHANGELOG.md‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -32,6 +32,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
3232
| --RV_primer | --primer_rev | |
3333
| --classifier | --qiime_classifier | |
3434

35+
- [#1028](https://github.com/nf-core/ampliseq/pull/1028) - Multi-region sample sheet via `--multiregion` had its header changed from `FW_primer` and `RV_primer` to `primer_fwd` and `primer_rev`, respectively. (by @d4straub)
36+
3537
### `Fixed`
3638

3739
- [#1019](https://github.com/nf-core/ampliseq/pull/1019) - Improve channel assignment & improve some version reporting (by @d4straub)
@@ -41,6 +43,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
4143

4244
### `Removed`
4345

46+
- [#1028](https://github.com/nf-core/ampliseq/pull/1028) - Removed support for the legacy sample sheet to simplify parsing (by @d4straub)
47+
4448
## nf-core/ampliseq version 2.18.0 - 2026-06-18
4549

4650
### `Added`

assets/samplesheet_standardized.tsv renamed to assets/samplesheet.tsv

File renamed without changes.

‎assets/samplesheet_legacy.tsv‎

Lines changed: 0 additions & 4 deletions
This file was deleted.

‎assets/schema_input.json‎

Lines changed: 3 additions & 64 deletions
Original file line numberDiff line numberDiff line change
@@ -7,31 +7,12 @@
77
"items": {
88
"type": "object",
99
"properties": {
10-
"sampleID": {
10+
"sample": {
1111
"type": "string",
1212
"pattern": "^[a-zA-Z][a-zA-Z0-9_]+$",
1313
"errorMessage": "Unique sample ID must be provided: Must start with a letter, and can only contain letters, numbers or underscores; Regex: '^[a-zA-Z][a-zA-Z0-9_]+$'",
1414
"meta": ["sample"]
1515
},
16-
"forwardReads": {
17-
"type": "string",
18-
"format": "file-path",
19-
"exists": true,
20-
"pattern": "^([\\S\\s]*\\/)?[^\\s\\/]+\\.f(ast)?q\\.gz$",
21-
"errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
22-
},
23-
"reverseReads": {
24-
"type": "string",
25-
"format": "file-path",
26-
"exists": true,
27-
"pattern": "^([\\S\\s]*\\/)?[^\\s\\/]+\\.f(ast)?q\\.gz$",
28-
"errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
29-
},
30-
"sample": {
31-
"type": "string",
32-
"pattern": "^[a-zA-Z][a-zA-Z0-9_]+$",
33-
"errorMessage": "Unique sample ID must be provided: Must start with a letter, and can only contain letters, numbers or underscores; Regex: '^[a-zA-Z][a-zA-Z0-9_]+$'"
34-
},
3516
"fastq_1": {
3617
"type": "string",
3718
"format": "file-path",
@@ -65,49 +46,7 @@
6546
"meta": ["quant_reading"]
6647
}
6748
},
68-
"oneOf": [
69-
{
70-
"required": ["sampleID", "forwardReads"],
71-
"not": {
72-
"anyOf": [
73-
{
74-
"required": ["sample"]
75-
},
76-
{
77-
"required": ["fastq_1"]
78-
},
79-
{
80-
"required": ["fastq_2"]
81-
}
82-
]
83-
},
84-
"errorMessage": "When using legacy format (sampleID/forwardReads), do not use standardized fields (sample/fastq_1/fastq_2)"
85-
},
86-
{
87-
"required": ["sample", "fastq_1"],
88-
"not": {
89-
"anyOf": [
90-
{
91-
"required": ["sampleID"]
92-
},
93-
{
94-
"required": ["forwardReads"]
95-
},
96-
{
97-
"required": ["reverseReads"]
98-
}
99-
]
100-
},
101-
"errorMessage": "When using standardized format (sample/fastq_1), do not use legacy fields (sampleID/forwardReads/reverseReads)"
102-
}
103-
]
49+
"required": ["sample", "fastq_1"]
10450
},
105-
"allOf": [
106-
{
107-
"uniqueEntries": ["sample"]
108-
},
109-
{
110-
"uniqueEntries": ["sampleID"]
111-
}
112-
]
51+
"uniqueEntries": ["sample"]
11352
}

‎assets/schema_multiregion.json‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -18,20 +18,20 @@
1818
"errorMessage": "Length of region must be an integer",
1919
"meta": ["region_length"]
2020
},
21-
"FW_primer": {
21+
"primer_fwd": {
2222
"type": "string",
2323
"pattern": "^[ATUGCYRSWKMBDHVN]*$",
24-
"errorMessage": "FW_primer must be provided and may contain only uppercase nucleotide IUPAC code [ATUGCYRSWKMBDHVN]",
24+
"errorMessage": "primer_fwd must be provided and may contain only uppercase nucleotide IUPAC code [ATUGCYRSWKMBDHVN]",
2525
"meta": ["primer_fwd"]
2626
},
27-
"RV_primer": {
27+
"primer_rev": {
2828
"type": "string",
2929
"pattern": "^[ATUGCYRSWKMBDHVN]*$",
30-
"errorMessage": "RV_primer must be provided and may contain only uppercase nucleotide IUPAC code [ATUGCYRSWKMBDHVN]",
30+
"errorMessage": "primer_rev must be provided and may contain only uppercase nucleotide IUPAC code [ATUGCYRSWKMBDHVN]",
3131
"meta": ["primer_rev"]
3232
}
3333
},
34-
"required": ["region", "region_length", "FW_primer", "RV_primer"]
34+
"required": ["region", "region_length", "primer_fwd", "primer_rev"]
3535
},
3636
"uniqueEntries": ["region"]
3737
}

‎conf/test.config‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@ params {
2525
// Input data
2626
primer_fwd = "GTGYCAGCMGCCGCGGTAA"
2727
primer_rev = "GGACTACNVGGGTWTCTAAT"
28-
input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_standardized.tsv"
28+
input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_v3.tsv"
2929
metadata = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Metadata.tsv"
3030
dada_ref_taxonomy = "gtdb=R07-RS207"
3131
cut_dada_ref_taxonomy = true

‎conf/test_doubleprimers.config‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@ params {
2626
primer_fwd = "NNNNCCTAHGGGRBGCAGCAG"
2727
primer_rev = "GACTACHVGGGTATCTAATCC"
2828
double_primer = true
29-
input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_double_primer.tsv"
29+
input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_double_primer_v3.tsv"
3030
sample_inference = "independent"
3131
trunc_qmin = 30
3232
kraken2_ref_taxonomy = "greengenes"

‎conf/test_failed.config‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@ params {
2525
// Input data
2626
primer_fwd = "GTGYCAGCMGCCGCGGTAA"
2727
primer_rev = "GGACTACNVGGGTWTCTAAT"
28-
input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_failed_sample.tsv"
28+
input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_failed_sample_v3.tsv"
2929
metadata = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Metadata_failed_sample.tsv"
3030
sample_inference = "independent"
3131
dada_ref_tax_custom = "https://zenodo.org/records/4310151/files/rdp_train_set_18.fa.gz"

‎conf/test_full.config‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,7 @@ params {
1717
// Input data for full size test
1818
primer_fwd = "GTGYCAGCMGCCGCGGTAA"
1919
primer_rev = "GGACTACNVGGGTWTCTAAT"
20-
input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_full.tsv"
20+
input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_full_v3.tsv"
2121
metadata = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Metadata_full.tsv"
2222
sample_inference = "independent"
2323
dada_ref_taxonomy = "sbdi-gtdb"

‎conf/test_glosed.config‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,7 @@ params {
2424

2525
primer_fwd = "GTGYCAGCMGCCGCGGTAA"
2626
primer_rev = "GGACTACNVGGGTWTCTAAT"
27-
input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet.tsv"
27+
input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_v3.tsv"
2828
sample_inference = "independent"
2929
dada_ref_taxonomy = "glosed"
3030
skip_qiime = true

0 commit comments

Comments
 (0)