demultiplex 1.1

modules/goodwright/ultraplex/samplesheet_to_barcode/templates/samplesheet_to_barcode.py

@@ -53,6 +53,20 @@ def main(process_name, samplesheet, output):
     five_prime = df_samplesheet["5' Barcode Sequence"]
     three_prime = df_samplesheet["3' Barcode Sequence"]
     three_prime_adapter = df_samplesheet["3' Adapter Sequence"]
+
+    # If only three prime barcodes are present, treat them as five prime barcodes, print a message to
+    # the user so they know this is happening and to remind them to use the correct ultraplex settings
+    if (five_prime.str.len() == 0).all():
+        print(
+            "NOTE: No 5' barcode sequence found in sample sheet, 3' barcodes will be formatted as 5' barcodes \
+            for Ultraplex input, ensure that Ultraplex is run with --three_prime_only flag. If using TSOs, \
+            ensure that --tso_seq flag is also used and set to the correct sequence."
+        )
+        five_prime = three_prime
+        three_prime = pd.Series([""] * len(five_prime))
+        five_prime.name = "5' Barcode Sequence"
+        three_prime.name = "3' Barcode Sequence"
+
     df_samplesheet = pd.concat([sample_names, five_prime, three_prime, three_prime_adapter], axis=1)
 
     # Init for loop

modules/goodwright/ultraplex/ultraplex/main.nf

@@ -2,10 +2,10 @@ process ULTRAPLEX {
     tag "${meta.id}"
     label "process_high"
 
-    conda "bioconda::ultraplex=1.2.5"
+    conda "bioconda::ultraplex=1.2.9"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/ultraplex:1.2.5--py38h4a8c8d9_0' :
-        'biocontainers/ultraplex:1.2.5--py38h4a8c8d9_0' }"
+        'https://depot.galaxyproject.org/singularity/ultraplex:1.2.9--py39hf95cd2a_0' :
+        'biocontainers/ultraplex:1.2.9--py39hf95cd2a_0' }"
 
     input:
     tuple val(meta), path(reads)
@@ -22,7 +22,7 @@ process ULTRAPLEX {
     task.ext.when == null || task.ext.when
 
     script:
-    def VERSION = "1.2.5" // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+    def VERSION = "1.2.9" // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
     def args = task.ext.args ?: ''
     prefix   = task.ext.prefix ?: "${meta.id}"
 

schema/demultiplex.json

@@ -1,31 +1,74 @@
 {
-    "inputs": {
-        "file_options": {
+    "inputs": [
+        {
             "name": "File options",
             "description": "The files needed for demultiplexing.",
-            "properties": {
+            "modes": ["Single-end", "Paired-end"],
+            "params": {
                 "samplesheet": {
                     "name": "Annotation",
-                    "type": "file",
+                    "type": "data",
                     "pattern": "xlsx|csv",
                     "category": 2,
                     "required": true,
+                    "modes": ["Single-end", "Paired-end"],
                     "description": "Sample annotation sheet."
                 },
                 "fastqs": {
                     "name": "FASTQ",
-                    "type": "lane",
-                    "pattern": "fq\\.gz$|fastq\\.gz$|fq$|fastq$",
+                    "description": "The multiplexed FASTQ file(s) to demultiplex. You can provide one or multiple files to be concatenated, for both single and paired end data. At least one file must be provided.",
+                    "required": true,
+                    "type": "csv",
+                    "output_headers": false,
+                    "takes_filesets": true,
+                    "fileset_category": 3,
+                    "fileset_size": 1,
+                    "modes": ["Single-end"],
+                    "columns": [
+                        {
+                            "name": "fastq_1",
+                            "type": "data",
+                            "required": true,
+                            "render": false,
+                            "from_fileset": 1
+                        }
+                    ]
+                },
+                "fastqs_": {
+                    "param": "fastqs",
+                    "name": "FASTQ",
+                    "description": "The multiplexed FASTQ file(s) to demultiplex. You can provide one or multiple files to be concatenated, for both single and paired end data. At least one file must be provided.",
                     "required": true,
-                    "description": "The multiplexed FASTQ file(s) to demultiplex. You can provide one or multiple files to be concatenated, for both single and paired end data. At least one file must be provided."
+                    "type": "csv",
+                    "output_headers": false,
+                    "takes_filesets": true,
+                    "fileset_category": 3,
+                    "fileset_size": 2,
+                    "modes": ["Paired-end"],
+                    "columns": [
+                        {
+                            "name": "fastq_1",
+                            "type": "data",
+                            "required": true,
+                            "render": false,
+                            "from_fileset": 1
+                        },
+                        {
+                            "name": "fastq_2",
+                            "type": "data",
+                            "required": true,
+                            "render": false,
+                            "from_fileset": 2
+                        }
+                    ]
                 }
             }
         },
-        "ultraplex_options": {
+        {
             "name": "Ultraplex options",
             "description": "Advanced options for Ultraplex.",
             "advanced": true,
-            "properties": {
+            "params": {
                 "fiveprimemismatches": {
                     "name": "5’ mismatches",
                     "description": "This option allows the user to specify how many mismatches are permitted when detecting which 5’ barcode a read contains. If set to zero, then the 5’ barcode must match the expected barcode perfectly. By default, this value is set to one mismatch.",
@@ -79,16 +122,34 @@
                     "description": "This option does not write out reads for which there was no barcode match, which may save time.",
                     "type": "boolean",
                     "required": false
+                },
+                "three_prime_only": {
+                    "name": "3' barcodes only",
+                    "description": "This is when you only have 3' barcodes. In this case, write each barcode on a new line in the barcode csv. Feel free to add names too like with 5' barcodes. The format of the barcode CSV should be exactly the same as if you only had 5' barcodes (see above). Barcode sequences should be as they would be in read 1 (just as above for 3' barcodes). Ultraplex uses the read 2 for demultiplexing here, and handles all reverse complementing internally.",
+                    "type": "boolean",
+                    "required": false
+                },
+                "tso_seq": {
+                    "name": "TSO-seq",
+                    "description": "This is used solely in conjunction with the option --three_prime_barcode. It is solely for TSOs that have a p5 sequence (i.e. give rise to the read 1). Give a sequence of Ns followed by Is. Ns are moved to the UMI. Is are trimmed from the read but not moved to the UMI. For example, if using a TSO of sequence (p5)NNNNNrGrGrG, you would specify --tso_seq NNNNNIII. This would move the five random bases to the UMI, but the three non-random bases from the rGs would be trimmed and ignored.",
+                    "type": "string",
+                    "required": false
                 }
             }
         }
-    },
+    ],
     "outputs": [
         {
             "name": "FASTQ Files",
             "description": "The demultiplexed FASTQ files.",
             "filetype": "fastq.gz",
             "process": "ULTRAPLEX"
+        },
+        {
+            "name": "Ultraplex log",
+            "description": "Log file from demultiplexing",
+            "filetype": "log",
+            "process": "ULTRAPLEX"
         }
     ]
 }

schema/icount_segment.json

@@ -1,26 +1,26 @@
 {
-    "inputs": {
-        "genome_options": {
+    "inputs": [
+        {
             "name": "File options",
             "description": "The files needed for running.",
-            "properties": {
+            "params": {
                 "gtf": {
                     "name": "GTF",
-                    "type": "file",
-                    "pattern": "gtf",
+                    "type": "data",
+                    "pattern": "\\.gtf$",
                     "required": true,
                     "description": "A genome annotation file."
                 },
                 "fai": {
                     "name": "FAI",
-                    "type": "file",
-                    "pattern": "fai",
+                    "type": "data",
+                    "pattern": "\\.fai$",
                     "required": true,
                     "description": "A faidx genome index."
                 }
             }
         }
-    },
+    ],
     "outputs": [
         {
             "name": "Segmentation GTF",

tests/config/test_data.config

@@ -9,6 +9,7 @@ params {
             clip_samplesheet_xlsx         = "${gw_test_data_dir}/samplesheets/clip-samplesheet.xlsx"
             clip_samplesheet_small        = "${gw_test_data_dir}/samplesheets/clip-samplesheet-small.csv"
             clip_samplesheet_adapter_mis  = "${gw_test_data_dir}/samplesheets/clip-samplesheet-mismatch-adapter.csv"
+            clip_3bc_only                 = "${gw_test_data_dir}/samplesheets/clip-samplesheet-3prime-barcode-only.csv"
 
             base_valid_single_pe          = "${gw_test_data_dir}/samplesheets/base_samplesheet/valid-single-sample-pe.csv"
             base_valid_single_se          = "${gw_test_data_dir}/samplesheets/base_samplesheet/valid-single-sample-se.csv"

tests/config/ultraplex-3prime-only.config

@@ -0,0 +1,33 @@
+params {
+    fastq2 = null
+    fiveprimemismatches = 1
+    threeprimemismatches = 0
+    adapter2 = null
+    phredquality = 30
+    phred_quality_5_prime = 0
+    min_trim = 3
+    final_min_length = 0
+    keep_barcodes = false
+    ignore_no_match = false
+    three_prime_only = true
+    tso_seq = false
+}
+
+process {
+    withName: '.*ULTRAPLEX.*' {
+        ext.args = 'test'
+        ext.args   = [
+            "-m5 ${params.fiveprimemismatches}",
+            "-m3 ${params.threeprimemismatches}",
+            params.adapter2 ? "-a2 ${params.adapter2}" : '',
+            "-q ${params.phredquality}",
+            "-q5 ${params.phred_quality_5_prime}",
+            "-mt ${params.min_trim}",
+            params.final_min_length != 0 ? "-l ${params.final_min_length}" : '',
+            params.keep_barcodes ? '-kbc' : '',
+            params.ignore_no_match ? '-inm' : '',
+            params.three_prime_only ? '--three_prime_only' : '',
+            params.tso_seq ? '--tso_seq' : ''
+        ].flatten().unique(false).join(' ').trim()
+    }
+}

tests/data/samplesheets/clip-samplesheet-3prime-barcode-only.csv

@@ -0,0 +1,3 @@
+Sample Name,5' Barcode Sequence,3' Barcode Sequence,3' Adapter Sequence
+sample_clip_1,,NNGACNN,AGATCGGAAGAGCGGTTCAG
+sample_clip_2,,NNTACNN,AGATCGGAAGAGCGGTTCAG

tests/subworkflows/demultiplex/main.nf

@@ -70,3 +70,12 @@ workflow test_channel_samplesheet {
     DEMULTIPLEX ( samplesheet, fastq )
     DEMULTIPLEX.out.fastq | view
 }
+
+workflow test_threeprimebarcode_only {
+
+    samplesheet = file(params.goodwright_test_data['samplesheets']['clip_3bc_only'], checkIfExists: true)
+    fastq       = file(params.goodwright_test_data['ultraplex']['multiplexed_fastq'], checkIfExists: true)
+
+    DEMULTIPLEX ( samplesheet, fastq )
+    DEMULTIPLEX.out.fastq | view
+}

tests/subworkflows/demultiplex/test_workflow.yml

@@ -56,3 +56,9 @@
   tags:
     - "subworkflows"
     - "demultiplex"
+
+- name: "test_sw_demultiplex_3bc_only"
+  command: nextflow run ./tests/subworkflows/demultiplex -c ./tests/config/ultraplex-3prime-only.config -c ./tests/config/nextflow.config -entry test_threeprimebarcode_only
+  tags:
+    - "subworkflows"
+    - "demultiplex"

tests/wrappers/subworkflows/demultiplex/test.yml

@@ -25,3 +25,10 @@
     - "wrappers"
     - "wrappers/subworkflows"
     - "wrappers/subworkflows/demultiplex"
+
+- name: "test_wrappers_demultiplex_single_se_threeprimeonly"
+  command: nextflow run ./wrappers/subworkflows/demultiplex/main.nf -c tests/config/ultraplex-3prime-only.config -c ./tests/config/nextflow.config --samplesheet ./tests/data/samplesheets/clip-samplesheet-3prime-barcode-only.csv --fastqs ./tests/data/fastq_list/single_se_fastq.csv
+  tags:
+    - "wrappers"
+    - "wrappers/subworkflows"
+    - "wrappers/subworkflows/demultiplex"

wrappers/subworkflows/demultiplex/nextflow.config

@@ -6,9 +6,11 @@ params {
     phredquality = 30
     phred_quality_5_prime = 0
     min_trim = 3
-    final_min_length = 0
+    final_min_length = 16
     keep_barcodes = false
     ignore_no_match = false
+    three_prime_only = false
+    tso_seq = null
 }
 
 process {
@@ -21,9 +23,11 @@ process {
             "-q ${params.phredquality}",
             "-q5 ${params.phred_quality_5_prime}",
             "-mt ${params.min_trim}",
-            params.final_min_length != 0 ? "-l ${params.final_min_length}" : '',
+            "-l ${params.final_min_length}",
             params.keep_barcodes ? '-kbc' : '',
-            params.ignore_no_match ? '-inm' : ''
+            params.ignore_no_match ? '-inm' : '',
+            params.three_prime_only ? '--three_prime_only' : '',
+            params.tso_seq ? "--tso_seq ${params.tso_seq}" : ''
         ].flatten().unique(false).join(' ').trim()
     }
 }