Removing the custom barcode logic for initial release

nf-core · Jan 11, 2024 · 3c76858 · 3c76858
1 parent 42a8665
commit 3c76858
Show file tree

Hide file tree

Showing 10 changed files with 40 additions and 328 deletions.
diff --git a/bin/create_regex.py b/bin/create_regex.py
diff --git a/bin/pre_extract_barcodes.py b/bin/pre_extract_barcodes.py
@@ -22,7 +22,7 @@ def parse_args():
     )
     arg_parser.add_argument("-o", "--output_file", required=True, type=str, help="The output fastq")
     arg_parser.add_argument(
-        "-f", "--barcode-format", required=False, type=str, help="The barcode/umi format (Options: cellranger)"
+        "-f", "--barcode-format", required=True, type=str, help="The barcode/umi format (Options: cellranger)"
     )
 
     args = arg_parser.parse_args()
@@ -88,7 +88,7 @@ def extract_barcode(input_file, barcode_file, output, bc_format):
                     read_info = {}
 
                     # Strip the primer, bc, umi, and poly-T
-                    if bc_format == "cellranger":
+                    if bc_format in ["cellranger_3_prime", "cellranger_5_prime"]:
                         read_info = strip_read_cellranger(bc_index, seq, quals)
 
                     if read_info:

diff --git a/conf/test.config b/conf/test.config
@@ -27,10 +27,6 @@ params {
     gtf                  = "https://raw.githubusercontent.com/nf-core/test-datasets/scnanoseq/reference/chr21.gtf"
 
     // Barcode options
-    cell_barcode_pattern = ""
-    identifier_pattern   = "fixed_seq_1,cell_barcode_1,umi_1,fixed_seq_2"
-    cell_barcode_lengths = "16"
-    umi_lengths          = "12"
-    fixed_seqs           = "CTACACGACGCTCTTCCGATCT, TTTTTTTTTT"
+    barcode_format       = "cellranger_3_prime"
 
 }
diff --git a/modules/local/create_regex.nf b/modules/local/create_regex.nf
diff --git a/modules/local/preextract_fastq.nf b/modules/local/preextract_fastq.nf
@@ -10,6 +10,7 @@ process PREEXTRACT_FASTQ {
 
     input:
     tuple val(meta), path(reads), path(bc_list)
+    val bc_format
 
     output:
     tuple val(meta), path("*.R1.fastq.gz"), emit: r1_reads
@@ -27,7 +28,7 @@ process PREEXTRACT_FASTQ {
     pre_extract_barcodes.py -i ${reads} \\
                             -b ${bc_list} \\
                             -o ${prefix} \\
-                            -f cellranger
+                            -f ${bc_format}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

diff --git a/modules/local/tag_barcodes.nf b/modules/local/tag_barcodes.nf
@@ -8,7 +8,9 @@ process TAG_BARCODES {
         'biocontainers/pysam:0.19.1--py310hff46b53_1' }"
 
     input:
-    tuple val(meta), path(bam), path(bai), path(r1_fastq), val(bc_length), val(umi_length)
+    tuple val(meta), path(bam), path(bai), path(r1_fastq)
+    val bc_length
+    val umi_length
 
     output:
     tuple val(meta), path("*.tagged.bam"), emit: tagged_bam

diff --git a/nextflow.config b/nextflow.config
@@ -27,13 +27,8 @@ params {
     skip_trimming              = false
 
     // Cell barcode options
-    cell_barcode_pattern       = null
     whitelist                  = null
-    identifier_pattern         = null
-    cell_barcode_lengths       = null
-    umi_lengths                = null
-    fixed_seqs                 = null
-    barcode_preset             = null
+    barcode_format             = null
 
     // Library strandness option
     stranded                   = null

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -98,7 +98,8 @@
                 "split_amount": {
                     "type": "integer",
                     "description": "The amount of lines to split  the fastq into (Default: 0)",
-                    "default": 0
+                    "default": 0,
+                    "fa_icon": "fas fa-cut"
                 }
             }
         },
@@ -137,35 +138,18 @@
                 "whitelist": {
                     "type": "string",
                     "description": "The file containing a list of barcodes.",
-                    "format": "file-path"
-                },
-                "cell_barcode_pattern": {
-                    "type": "string",
-                    "description": "Regex for the cell barcode pattern."
-                },
-                "identifier_pattern": {
-                    "type": "string",
-                    "description": "Human readable regex for the cell barcode pattern."
-                },
-                "cell_barcode_lengths": {
-                    "type": "string",
-                    "description": "The comma delimited list of cell barcode lengths."
-                },
-                "umi_lengths": {
-                    "type": "string",
-                    "description": "The comma delimited list of umi lengths."
-                },
-                "fixed_seqs": {
-                    "type": "string",
-                    "description": "The comma delimited list of fixed barcode sequences."
+                    "format": "file-path",
+                    "fa_icon": "far fa-file-alt"
                 },
-                "barcode_preset": {
+                "barcode_format": {
                     "type": "string",
-                    "description": "Specify a preset option for barcode formatting.",
-                    "enum": ["cellranger_3_prime", "cellranget_5_prime"]
+                    "description": "Specify the format for the barcode+umi",
+                    "enum": ["cellranger_3_prime"],
+                    "fa_icon": "fas fa-barcode"
                 }
             },
-            "fa_icon": "fas fa-microscope"
+            "fa_icon": "fas fa-microscope",
+            "required": ["barcode_format"]
         },
         "mapping": {
             "title": "Mapping",
@@ -176,12 +160,14 @@
                 "stranded": {
                     "type": "string",
                     "enum": ["None", "reverse", "forward"],
-                    "description": "Library strandness option."
+                    "description": "Library strandness option.",
+                    "fa_icon": "fas fa-dna"
                 },
                 "kmer_size": {
                     "type": "integer",
                     "default": 14,
-                    "description": "Minimizer k-mer length."
+                    "description": "Minimizer k-mer length.",
+                    "fa_icon": "fas fa-sort-amount-down"
                 },
                 "save_secondary_alignment": {
                     "type": "boolean",
@@ -199,17 +185,20 @@
             "properties": {
                 "analyze_uncorrected_bam": {
                     "type": "boolean",
-                    "description": "Run downstream steps on the bam that contains reads that could not be corrected. Do not use this if no whitelist is provided."
+                    "description": "Run downstream steps on the bam that contains reads that could not be corrected. Do not use this if no whitelist is provided.",
+                    "fa_icon": "fas fa-search"
                 },
                 "counts_level": {
                     "type": "string",
                     "description": "What level to generate the counts matrix at. Options: 'gene', 'transcript'.",
-                    "enum": ["gene", "transcript", "both"]
+                    "enum": ["gene", "transcript", "both"],
+                    "fa_icon": "fas fa-file-csv"
                 },
                 "retain_introns": {
                     "type": "boolean",
                     "default": true,
-                    "description": "Indicate whether to include introns in the count matrices"
+                    "description": "Indicate whether to include introns in the count matrices",
+                    "fa_icon": "fas fa-filter"
                 }
             },
             "required": ["counts_level"]
@@ -247,7 +236,7 @@
                     "description": "Skip NanoComp from BAM file(s)."
                 },
                 "skip_rseqc": {
-                    "type": "string",
+                    "type": "boolean",
                     "fa_icon": "fas fa-forward"
                 },
                 "skip_seurat": {