Remove support for legacy sample sheet and adjust multiregion sheet

CHANGELOG.md

@@ -32,6 +32,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 | --RV_primer       | --primer_rev                  |         |
 | --classifier      | --qiime_classifier            |         |
 
+- [#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)
+
 ### `Fixed`
 
 - [#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
 
 ### `Removed`
 
+- [#1028](https://github.com/nf-core/ampliseq/pull/1028) - Removed support for the legacy sample sheet to simplify parsing (by @d4straub)
+
 ## nf-core/ampliseq version 2.18.0 - 2026-06-18
 
 ### `Added`

assets/schema_input.json

@@ -7,31 +7,12 @@
     "items": {
         "type": "object",
         "properties": {
-            "sampleID": {
+            "sample": {
                 "type": "string",
                 "pattern": "^[a-zA-Z][a-zA-Z0-9_]+$",
                 "errorMessage": "Unique sample ID must be provided: Must start with a letter, and can only contain letters, numbers or underscores; Regex: '^[a-zA-Z][a-zA-Z0-9_]+$'",
                 "meta": ["sample"]
             },
-            "forwardReads": {
-                "type": "string",
-                "format": "file-path",
-                "exists": true,
-                "pattern": "^([\\S\\s]*\\/)?[^\\s\\/]+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
-            },
-            "reverseReads": {
-                "type": "string",
-                "format": "file-path",
-                "exists": true,
-                "pattern": "^([\\S\\s]*\\/)?[^\\s\\/]+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
-            },
-            "sample": {
-                "type": "string",
-                "pattern": "^[a-zA-Z][a-zA-Z0-9_]+$",
-                "errorMessage": "Unique sample ID must be provided: Must start with a letter, and can only contain letters, numbers or underscores; Regex: '^[a-zA-Z][a-zA-Z0-9_]+$'"
-            },
             "fastq_1": {
                 "type": "string",
                 "format": "file-path",
@@ -65,49 +46,7 @@
                 "meta": ["quant_reading"]
             }
         },
-        "oneOf": [
-            {
-                "required": ["sampleID", "forwardReads"],
-                "not": {
-                    "anyOf": [
-                        {
-                            "required": ["sample"]
-                        },
-                        {
-                            "required": ["fastq_1"]
-                        },
-                        {
-                            "required": ["fastq_2"]
-                        }
-                    ]
-                },
-                "errorMessage": "When using legacy format (sampleID/forwardReads), do not use standardized fields (sample/fastq_1/fastq_2)"
-            },
-            {
-                "required": ["sample", "fastq_1"],
-                "not": {
-                    "anyOf": [
-                        {
-                            "required": ["sampleID"]
-                        },
-                        {
-                            "required": ["forwardReads"]
-                        },
-                        {
-                            "required": ["reverseReads"]
-                        }
-                    ]
-                },
-                "errorMessage": "When using standardized format (sample/fastq_1), do not use legacy fields (sampleID/forwardReads/reverseReads)"
-            }
-        ]
+        "required": ["sample", "fastq_1"]
     },
-    "allOf": [
-        {
-            "uniqueEntries": ["sample"]
-        },
-        {
-            "uniqueEntries": ["sampleID"]
-        }
-    ]
+    "uniqueEntries": ["sample"]
 }

assets/schema_multiregion.json

@@ -18,20 +18,20 @@
                 "errorMessage": "Length of region must be an integer",
                 "meta": ["region_length"]
             },
-            "FW_primer": {
+            "primer_fwd": {
                 "type": "string",
                 "pattern": "^[ATUGCYRSWKMBDHVN]*$",
-                "errorMessage": "FW_primer must be provided and may contain only uppercase nucleotide IUPAC code [ATUGCYRSWKMBDHVN]",
+                "errorMessage": "primer_fwd must be provided and may contain only uppercase nucleotide IUPAC code [ATUGCYRSWKMBDHVN]",
                 "meta": ["primer_fwd"]
             },
-            "RV_primer": {
+            "primer_rev": {
                 "type": "string",
                 "pattern": "^[ATUGCYRSWKMBDHVN]*$",
-                "errorMessage": "RV_primer must be provided and may contain only uppercase nucleotide IUPAC code [ATUGCYRSWKMBDHVN]",
+                "errorMessage": "primer_rev must be provided and may contain only uppercase nucleotide IUPAC code [ATUGCYRSWKMBDHVN]",
                 "meta": ["primer_rev"]
             }
         },
-        "required": ["region", "region_length", "FW_primer", "RV_primer"]
+        "required": ["region", "region_length", "primer_fwd", "primer_rev"]
     },
     "uniqueEntries": ["region"]
 }

conf/test.config

@@ -25,7 +25,7 @@ params {
     // Input data
     primer_fwd = "GTGYCAGCMGCCGCGGTAA"
     primer_rev = "GGACTACNVGGGTWTCTAAT"
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_standardized.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_v3.tsv"
     metadata = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Metadata.tsv"
     dada_ref_taxonomy = "gtdb=R07-RS207"
     cut_dada_ref_taxonomy = true

conf/test_doubleprimers.config

@@ -26,7 +26,7 @@ params {
     primer_fwd = "NNNNCCTAHGGGRBGCAGCAG"
     primer_rev = "GACTACHVGGGTATCTAATCC"
     double_primer = true
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_double_primer.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_double_primer_v3.tsv"
     sample_inference = "independent"
     trunc_qmin = 30
     kraken2_ref_taxonomy = "greengenes"

conf/test_failed.config

@@ -25,7 +25,7 @@ params {
     // Input data
     primer_fwd = "GTGYCAGCMGCCGCGGTAA"
     primer_rev = "GGACTACNVGGGTWTCTAAT"
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_failed_sample.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_failed_sample_v3.tsv"
     metadata = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Metadata_failed_sample.tsv"
     sample_inference = "independent"
     dada_ref_tax_custom = "https://zenodo.org/records/4310151/files/rdp_train_set_18.fa.gz"

conf/test_full.config

@@ -17,7 +17,7 @@ params {
     // Input data for full size test
     primer_fwd = "GTGYCAGCMGCCGCGGTAA"
     primer_rev = "GGACTACNVGGGTWTCTAAT"
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_full.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_full_v3.tsv"
     metadata = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Metadata_full.tsv"
     sample_inference = "independent"
     dada_ref_taxonomy = "sbdi-gtdb"

conf/test_glosed.config

@@ -24,7 +24,7 @@ params {
 
     primer_fwd = "GTGYCAGCMGCCGCGGTAA"
     primer_rev = "GGACTACNVGGGTWTCTAAT"
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_v3.tsv"
     sample_inference = "independent"
     dada_ref_taxonomy = "glosed"
     skip_qiime = true

conf/test_iontorrent.config

@@ -27,7 +27,7 @@ params {
     primer_rev = "TCCTCSSCTTATTGATATGC"
     sintax_ref_tax_custom = "https://s3.hpc.ut.ee/plutof-public/original/a6c4d680-c99a-4252-ba67-748271c7d7f4.gz"
     sintax_assign_taxlevels = "Domain,Phylum,Class,Order,Family,Genus,Species"
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_it_SE_ITS.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_it_SE_ITS_v3.tsv"
     sequencing_type = "iontorrent"
     sample_inference = "independent"
     max_ee = 5

conf/test_multi.config

@@ -30,7 +30,7 @@ params {
     skip_dada_quality = true
     dada_ref_taxonomy = "rdp=18"
     skip_dada_addspecies = true
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_multi.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_multi_v3.tsv"
 
     skip_phyloseq = true
     skip_tse = true

conf/test_multiregion.config

@@ -23,9 +23,9 @@ params {
     config_profile_description = 'Test dataset to check multi-region pipeline function'
 
     // Input data
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/samplesheet_multiregion.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/samplesheet_multiregion_v3.tsv"
     metadata = params.pipelines_testdata_base_path + "ampliseq/samplesheets/metadata_multiregion.tsv"
-    multiregion = params.pipelines_testdata_base_path + "ampliseq/samplesheets/regions_multiregion.tsv"
+    multiregion = params.pipelines_testdata_base_path + "ampliseq/samplesheets/regions_multiregion_v3.tsv"
     sidle_ref_taxonomy = "greengenes88"
     sample_inference = "independent"
 

conf/test_novaseq.config

@@ -23,7 +23,7 @@ params {
     config_profile_description = 'Minimal test dataset to check pipeline function with Novaseq data and codon filtering'
 
     // Input data
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_novaseq.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_novaseq_v3.tsv"
     binned_quality = "2,11,25,37"
     sample_inference = "independent"
 

conf/test_pacbio_its.config

@@ -26,7 +26,7 @@ params {
     primer_fwd = "CTTGGTCATTTAGAGGAAGTAA"
     primer_rev = "TCCTGAGGGAAACTTCG"
     sintax_ref_taxonomy = "unite-fungi=8.2"
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_pacbio_ITS.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_pacbio_ITS_v3.tsv"
     metadata = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Metadata_pacbio_ITS.tsv"
     sequencing_type = "pacbio"
     sample_inference = "independent"

conf/test_pplace.config

@@ -25,7 +25,7 @@ params {
     // Input data
     primer_fwd = "GTGYCAGCMGCCGCGGTAA"
     primer_rev = "GGACTACNVGGGTWTCTAAT"
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_v3.tsv"
     metadata = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Metadata.tsv"
     sample_inference = "independent"
     skip_dada_taxonomy = true

conf/test_pplace_sheet.config

@@ -25,7 +25,7 @@ params {
     // Input data
     primer_fwd = "GTGYCAGCMGCCGCGGTAA"
     primer_rev = "GGACTACNVGGGTWTCTAAT"
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_v3.tsv"
     skip_dada_taxonomy = true
     qiime_ref_taxonomy = "greengenes85"
 

conf/test_qiimecustom.config

@@ -25,7 +25,7 @@ params {
     // Input data
     primer_fwd = "GTGYCAGCMGCCGCGGTAA"
     primer_rev = "GGACTACNVGGGTWTCTAAT"
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_v3.tsv"
     sample_inference = "independent"
 
     // Comparison to expected

conf/test_reftaxcustom.config

@@ -25,7 +25,7 @@ params {
     // Input data
     primer_fwd = "GTGYCAGCMGCCGCGGTAA"
     primer_rev = "GGACTACNVGGGTWTCTAAT"
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_v3.tsv"
     sample_inference = "independent"
 
     // Custom reference taxonomy

conf/test_savont.config

@@ -23,7 +23,7 @@ params {
     config_profile_description = 'Minimal test dataset to check pipeline function with Savont'
 
     // Input data
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_nanopore.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_nanopore_v3.tsv"
     sequencing_type = "nanopore"
 
     // cutadapt

conf/test_single.config

@@ -25,7 +25,7 @@ params {
     // Input data
     primer_fwd = "GTGYCAGCMGCCGCGGTAA"
     primer_rev = "GGACTACNVGGGTWTCTAAT"
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_v3.tsv"
     sequencing_type = "illumina_se"
     dada_ref_taxonomy = "rdp=18"
     cut_dada_ref_taxonomy = true

conf/test_sintax.config

@@ -25,7 +25,7 @@ params {
     // Input data
     primer_fwd = "CTTGGTCATTTAGAGGAAGTAA"
     primer_rev = "TCCTGAGGGAAACTTCG"
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_pacbio_ITS.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_pacbio_ITS_v3.tsv"
     metadata = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Metadata_pacbio_ITS.tsv"
     sequencing_type = "pacbio"
     sample_inference = "independent"

conf/test_vsearch_lca.config

@@ -25,7 +25,7 @@ params {
     // Input data
     primer_fwd = "CTTGGTCATTTAGAGGAAGTAA"
     primer_rev = "TCCTGAGGGAAACTTCG"
-    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_pacbio_ITS.tsv"
+    input = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Samplesheet_pacbio_ITS_v3.tsv"
     metadata = params.pipelines_testdata_base_path + "ampliseq/samplesheets/Metadata_pacbio_ITS.tsv"
     sample_inference = "independent"
     sequencing_type = "pacbio"

docs/output.md

@@ -484,9 +484,9 @@ Additional output includes reconstruction of abundance table and taxonomic infor
 <summary>Output files</summary>
 
 - `sidle/per-region/`
-  - `ASV_seqs_region*_<FW_primer>_<RV_primer>.fasta`: ASV sequences per region
-  - `ASV_table_region*_<FW_primer>_<RV_primer>.fasta`: ASV abundances per region
-  - `DADA2_table_region*_<FW_primer>_<RV_primer>.fasta`: ASV abundances and sequences per region
+  - `ASV_seqs_region*_<primer_fwd>_<primer_rev>.fasta`: ASV sequences per region
+  - `ASV_table_region*_<primer_fwd>_<primer_rev>.fasta`: ASV abundances per region
+  - `DADA2_table_region*_<primer_fwd>_<primer_rev>.fasta`: ASV abundances and sequences per region
 - `sidle/DB/3_reconstructed/reconstruction_summary/index.html`: Information about the reconstructed reference taxonomy database
 - `sidle/reconstructed/`
   - `reconstructed_feature-table.biom`: Unified abundance table in biom format

docs/usage.md

@@ -120,26 +120,23 @@ For example, the tab-separated sample sheet may contain:
 | sample3 | ./S4x.fastq.gz            | ./S4y.fastq.gz            | B   | control | 1100          |
 | sample4 | ./a.fastq.gz              | ./b.fastq.gz              | B   | sample  | 11000         |
 
-Two header layouts are supported, a legacy and a standardized layout (the latter is described above):
-
-| Layout       | Required columns           | Optional columns                                  |
-| ------------ | -------------------------- | ------------------------------------------------- |
-| Legacy       | `sampleID`, `forwardReads` | `reverseReads`, `run`, `control`, `quant_reading` |
-| Standardized | `sample`, `fastq_1`        | `fastq_2`, `run`, `control`, `quant_reading`      |
+| Required columns    | Optional columns                             |
+| ------------------- | -------------------------------------------- |
+| `sample`, `fastq_1` | `fastq_2`, `run`, `control`, `quant_reading` |
 
 Please note the following requirements:
 
 - 2 to 6 columns/entries
 - File extensions `.tsv`,`.csv`,`.yml`,`.yaml` specify the file type, otherwise file type will be derived from content, if possible
-- Must contain either `sample` and `fastq_1` (standardized) OR `sampleID` and `forwardReads` (legacy)
-- May contain `fastq_2`/`reverseReads`, `run`, `control`, and `quant_reading`
+- Must contain either `sample` and `fastq_1`
+- May contain `fastq_2`, `run`, `control`, and `quant_reading`
 - Sample IDs must be unique
 - Sample IDs must start with a letter
 - Sample IDs can only contain letters, numbers or underscores
 - FastQ files must be compressed (`.fastq.gz`, `.fq.gz`)
 - Within one samplesheet, only one type of raw data should be specified (same amplicon & sequencing method)
 
-Examples for both layouts are provided within the pipeline code in folder `assets` as `samplesheet_legacy.tsv` and `samplesheet_standardized.tsv`.
+Examples for the layout is provided within the pipeline code in folder `assets` as `samplesheet.tsv`.
 
 To avoid producing a sample sheet, [Direct FASTQ input](#direct-fastq-input) may be used instead.
 
@@ -295,7 +292,7 @@ For example, multiple variable regions of the 16S rRNA gene were sequenced with
 Information about sequencing data via [`--input`](#sample-sheet-input), region primers length information via [`--multiregion`](https://nf-co.re/ampliseq/parameters#multiregion), and a taxonomic database via [`--sidle_ref_taxonomy`](https://nf-co.re/ampliseq/parameters#sidle_ref_taxonomy) or [`--sidle_ref_tax_custom`](https://nf-co.re/ampliseq/parameters#sidle_ref_tax_custom) with [`--sidle_ref_seq_custom`](https://nf-co.re/ampliseq/parameters#sidle_ref_seq_custom) is required.
 
 ```bash
---input "samplesheet_multiregion.tsv"  --multiregion "regions_multiregion.tsv" --sidle_ref_taxonomy "silva=128"
+--input "samplesheet_multiregion_v3.tsv"  --multiregion "regions_multiregion_v3.tsv" --sidle_ref_taxonomy "silva=128"
 ```
 
 The region information file can be tab-separated (.tsv), comma-separated (.csv), or in YAML format (.yml/.yaml) and can have two to four columns/entries with the following headers:
@@ -304,12 +301,12 @@ The region information file can be tab-separated (.tsv), comma-separated (.csv),
 | ------------- | ------------------------------------------------------------------------- |
 | region        | Unique region identifier                                                  |
 | region_length | Minimum region length, sequences are trimmed and shorter ones are omitted |
-| FW_primer     | Forward primer sequence                                                   |
-| RV_primer     | Reverse primer sequence                                                   |
+| primer_fwd    | Forward primer sequence                                                   |
+| primer_rev    | Reverse primer sequence                                                   |
 
-For example, the tab-separated `regions_multiregion.tsv` may contain:
+For example, the tab-separated `regions_multiregion_v3.tsv` may contain:
 
-| region  | FW_primer             | RV_primer            | region_length |
+| region  | primer_fwd            | primer_rev           | region_length |
 | ------- | --------------------- | -------------------- | ------------- |
 | region1 | TGGCGAACGGGTGAGTAA    | CCGTGTCTCAGTCCCARTG  | 145           |
 | region2 | ACTCCTACGGGAGGCAGC    | GTATTACCGCGGCTGCTG   | 135           |