removing all references to sequencing summary (samplesheet input)

Author: number-25

README.md

@@ -1,5 +1,3 @@
-![cover image](docs/images/cover_image.jpg)
-
 [![nf-core CI](https://github.com/number-25/LongTranscriptomics/actions/workflows/ci.yml/badge.svg?branch=dev)](https://github.com/number-25/LongTranscriptomics/actions/workflows/ci.yml)
 [![nf-core linting comment](https://github.com/number-25/LongTranscriptomics/actions/workflows/linting_comment.yml/badge.svg)](https://github.com/number-25/LongTranscriptomics/actions/workflows/linting_comment.yml)
 [![GitHub Actions Linting Status](https://github.com/number-25/LongTranscriptomics/actions/workflows/linting.yml/badge.svg)](https://github.com/number-25/LongTranscriptomics/actions/workflows/linting.yml)
@@ -41,9 +39,8 @@ reads in BAM format. These are provided to the samplesheet as input.
    3. [`IsoQuant`](https://ablab.github.io/IsoQuant/) - allows read correction
    4. [`StringTie`](https://github.com/skovaka/stringtie2)
    <!-- 7. Fusion gene detection [`JAFFA`](github.com/Oshlack/JAFFA) -->
-7. Transcriptome assessment [`gffcompare`](https://ccb.jhu.edu/software/stringtie/gff.shtml)
-8. Transcript quantification
-   1. [`oarfish`](https://github.com/COMBINE-lab/oarfish)
+7. Transcriptome assessment ( [`gffcompare`](https://ccb.jhu.edu/software/stringtie/gff.shtml) )
+8. Transcript quantification ( [`oarfish`](https://github.com/COMBINE-lab/oarfish) )
      <!-- ( [`TranSigner`](https://github.com/haydenji0731/TranSigner),
    Small test datasets for the pipeline are included in the [assets directory](https://github.com/number-25/LongTranscriptomics/assets/test_data). -->
 
@@ -57,9 +54,9 @@ First, prepare a samplesheet with your input data that looks as follows:
 `samplesheet.csv`:
 
 ```csv
-sample,replicate,sequencing_summary_path,read_path
-CONTROL1,1,data/long_reads_sequencingsummary_1.txt,data/long_reads_1.fastq.gz
-CONTROL1,2,data/long_reads_sequencingsummary_2.txt,data/long_reads_2.fastq.gz
+sample,replicate,read_path
+CONTROL1,1,data/long_reads_1.fastq.gz
+CONTROL1,2,data/long_reads_2.fastq.gz
 ```
 
 Each row represents a fastq file. Replicate refers to a technical replicate, biological replicates should be named uniquely. Be sure to pay attention to sample naming, in

assets/samplesheet.csv

@@ -1,2 +1,2 @@
-sample,replicate,sequencing_summary_path,read_path
-COLOBL_RNA_600,,/mnt/hdd1/MedGen_RNA_datasets/COLOBL_RNA_600/fastq_pass/sequencing_summary_PAW55908_25243b4b_de7ed5dd.txt,/mnt/hdd1/MedGen_RNA_datasets/COLOBL_RNA_600/fastq_pass/COLOBL_RNA_660.fastq.gz
+sample,replicate,read_path
+COLOBL_RNA_600,,/mnt/hdd1/MedGen_RNA_datasets/COLOBL_RNA_600/fastq_pass/COLOBL_RNA_660.fastq.gz

assets/schema_input.json

@@ -19,13 +19,6 @@
                 "errorMessage": "Replicate must be an integer",
                 "meta": ["replicate"]
             },
-            "sequencing_summary": {
-                "type": "string",
-                "format": "file-path",
-                "exists": true,
-                "pattern": "^\S+.txt$",
-                "errorMessage": "Sequencing summary file cannot contain spaces and must have extension '.txt'"
-            },
             "fastq": {
                 "type": "string",
                 "format": "file-path",
@@ -34,6 +27,6 @@
                 "errorMessage": "FastQ file must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
             }
         },
-        "required": ["sample", "sequencing_summary", "fastq"]
+        "required": ["sample", "fastq"]
     }
 }

bin/check_samplecsv.jl

@@ -35,13 +35,13 @@ header = input_samplesheet[1]
 split_header = split(header, ',')
 
 ## length
-length(split_header) == 4 || throw("The header is the incorrect size, check how many columns you have provided (4 is required")
+length(split_header) == 3 || throw("The header is the incorrect size, check how many columns you have provided (3 is required")
 println("sample sheet has the correct number of columns")
 
 ## check that the header names are correct
-header_names = ("sample", "replicate", "sequencing_summary_path", "read_path")
+header_names = ("sample", "replicate"", "read_path")
 for colname in header_names
-    colname ∈ split_header || throw("column names are incorrectly spelled, ensure that they are sample,replicate,sequencing_summary_path,readpath")
+    colname ∈ split_header || throw("column names are incorrectly spelled, ensure that they are sample,replicate,readpath")
 end
 println("the header names are spelled correctly")
 
@@ -50,9 +50,9 @@ samplesheet_body = input_samplesheet[2:end]
 for row in samplesheet_body
     rownumber = 1
     split_row = split(row, ',')
-    length(split(row, ',')) == 4 || throw("row number $(rownumber) has the incorrect number of columns, please check formatting")
+    length(split(row, ',')) == 3 || throw("row number $(rownumber) has the incorrect number of columns, please check formatting")
 # check to see if sample name is a single string and not spaced
-    first_column, second_column, third_column, fourth_column = split_row[1:end]
+    first_column, second_column, third_column = split_row[1:end]
     !occursin(' ', first_column) || throw("sample name is separated by a space, please format it so that it is one continuous string")
 # check to see if the replicate is an interger (if provided))
     if !isempty(second_column)
@@ -62,12 +62,8 @@ for row in samplesheet_body
             throw("The replicate is not an integer, please change it to one e.g 1, 2")
         end
     end
-# check to see if sequencing summary exists and isn't empty
-    path_to_summary = nextflow_path * '/' * third_column
-    ispath(path_to_summary) || throw("sequencing summary file doesn't exist, or the path pointing to it is incorrect")
-    # is it empty?
 # check to see if the reads path points to a valid path or a valid file
-    path_to_reads = nextflow_path * '/' * fourth_column
+    path_to_reads = nextflow_path * '/' * third
     ispath(path_to_reads) || isfile(path_to_reads) || throw("the path to the reads either doesn't exist, or the path pointing to a specific fastq file doesn't exist, please check paths")
     if ispath(path_to_reads) && !isfile(path_to_reads)
         !isempty(readdir(glob"*.fq", path_to_reads)) ||

docs/usage.md

@@ -19,16 +19,15 @@ The pipeline will auto-detect whether the sequencing summary files, and reads ar
 A final samplesheet file consisting of long-read data may look something like the one below. This is for **one biological** sample which has been sequenced twice, giving two technical replicates.
 
 ```csv title="samplesheet.csv"
-sample,replicate,sequencing_summary_path,read_path
-CONTROL1,1,data/long_reads_sequencingsummary_1.txt,data/long_reads_1.fastq.gz
-CONTROL1,2,data/long_reads_sequencingsummary_2.txt,data/long_reads_2.fastq.gz
+sample,replicate,read_path
+CONTROL1,1,data/long_reads_1.fastq.gz
+CONTROL1,2,data/long_reads_2.fastq.gz
 ```
 
 | Column                    | Description                                                              |
 | ------------------------- | ------------------------------------------------------------------------ |
 | `sample`                  | Sample name.                                                             |
 | `replicate`               | Technical replicate number                                               |
-| `sequencing_summary_path` | Full path to nanopore sequencing summary file (usually a .txt file).gz". |
 | `read_path`               | Full path to fastq reads.                                                |
 
 An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.

subworkflows/local/input_check/main.nf

@@ -23,7 +23,7 @@ workflow INPUT_CHECK {
         ch_sample.view() */
 
     emit:
-    ch_sample // [ sample, replicate, sequencing_summary_file, path_to_reads ]
+    ch_sample // [ sample, replicate, path_to_reads ]
     //ch_versions = ch_versions.mix(CHECK_SAMPLESHEET.out.versions.first())
 }
 
@@ -32,8 +32,7 @@ def get_sample_info(LinkedHashMap row) {
     // create meta map
     def meta = [:]
     meta.id           = row.sample
-    meta.replicate   = row.replicate
-    meta.sequencing_summary = row.sequencing_summary_path
+    meta.replicate    = row.replicate
     //meta.fastq = row.read_path
 
     // add path(s) of the fastq file to the meta map

test/samplesheets/samplesheet_test_dRNA.csv

@@ -1,2 +1,2 @@
-sample,replicate,sequencing_summary_path,read_path
-KCMF1,1,assets/test_data/dummy_sequencing_summary.txt,assets/test_data/sample_nobc_dx.fastq.gz
+sample,replicate,read_path
+KCMF1,1,assets/test_data/sample_nobc_dx.fastq.gz

test/samplesheets/samplesheet_test_local.csv

@@ -1,2 +1,2 @@
-sample,replicate,sequencing_summary_path,read_path
-COLOBL_RNA600,1,assets/fulltest_data/sequencing_summary_PAW55908_25243b4b_de7ed5dd.txt,assets/fulltest_data/COLOBL_RNA_660.fastq.gz
+sample,replicate,read_path
+COLOBL_RNA600,1,assets/fulltest_data/COLOBL_RNA_660.fastq.gz