diff --git a/CHANGELOG.md b/CHANGELOG.md index 6196f38..2b33f60 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,10 +1,13 @@ # Changelog -## [1.0.5] - 2024-01-XX +## [1.0.6] - 2024-11-XX ### Added - include as default `dsb` ambient protein background correction for ADT counts, for experiments without hashing deconvolution +## [1.0.5] - 2024-10-09 +- removed `SeqRunName` variable, as it is not needed by cellranger anymore + ## [1.0.4] - 2023-09-19 ### Changed diff --git a/config/README.md b/config/README.md index 3e37b1a..c920881 100644 --- a/config/README.md +++ b/config/README.md @@ -29,22 +29,15 @@ A pre-configured samplemap ready to run on the test data that can be adapted is Example samplemap: ``` -sample HashingFile SeqRunName nTargetCells featureReferenceFile -sampleA HashingFileA SeqRunNameA 10000 featureReferenceFileA -sampleB HashingFileB SeqRunNameB 15000 featureReferenceFileB +sample HashingFile nTargetCells featureReferenceFile +sampleA HashingFileA 10000 featureReferenceFileA +sampleB HashingFileB 15000 featureReferenceFileB ``` With one line per set of samples - `sample` contains the sample identifier that is used throughout the pipeline - `HashingFile` contains the full path to the comma separated text file containing the hashtag barcodes and their assignment to individual sample names (see [HashingFile](#hashingfile)). -- `SeqRunName` corresponds to the sequencing sample name of the ADT sample; this parameter is only required for the Cellranger run of ADT data. It can be retrieved from the FASTQ file names as follows: - -``` -[SeqRunName]_S[Number]_L00[Lane Number]_[Read Type]_001.fastq.gz -``` - -Where Read Type is one of: I1, R1, R2. - `nTargetCells` corresponds to the number of targeted cells for the sample. - `featureReferenceFile` corresponds to the ADT feature reference file for the sample set. For further information please consult the Cellranger tool documentation. diff --git a/config/samplemap b/config/samplemap index 7ede6e0..8dd55db 100644 --- a/config/samplemap +++ b/config/samplemap @@ -1,2 +1,2 @@ -sample HashingFile SeqRunName nTargetCells featureReferenceFile -PBMC_D1 testdata/HashingFile_PBMC_D1.csv BSSE_QGF_132646_HHVFNDRXX_1_PBMC_mix_20k_ADT_E3_SI-NA-E3 20000 testdata/feature_reference.txt +sample HashingFile nTargetCells featureReferenceFile +PBMC_D1 testdata/HashingFile_PBMC_D1.csv 20000 testdata/feature_reference.txt diff --git a/workflow/rules/adt_cellranger.smk b/workflow/rules/adt_cellranger.smk index 164edaa..e471c43 100644 --- a/workflow/rules/adt_cellranger.smk +++ b/workflow/rules/adt_cellranger.smk @@ -17,7 +17,6 @@ rule create_library_file_adt: library_file=WORKDIR + "/results/pooled_samples/cellranger_adt/{sample_set}.adt_library.txt", params: - seqRunName=getSeqRunName, threads: config["computingResources"]["threads"]["low"] resources: mem_mb=config["computingResources"]["mem_mb"]["low"], diff --git a/workflow/rules/misc_snake.smk b/workflow/rules/misc_snake.smk index 78ef8d6..413809c 100644 --- a/workflow/rules/misc_snake.smk +++ b/workflow/rules/misc_snake.smk @@ -120,17 +120,6 @@ def getTargetCellsCellranger_simple(wildcards): return out -# Retrieve the ADT sequencing run name corresponding to a given sample set -def getSeqRunName(wildcards): - # Create dictionary with samples and SeqRunName - sampleMap = dict(zip(samples["sample"], samples["SeqRunName"])) - if wildcards.sample_set not in sampleMap.keys(): - raise ValueError( - "Sample '%s' not found in the sample map!" % (wildcards.sample_set) - ) - return sampleMap[wildcards.sample_set] - - # Retrieve the ADT feature reference file corresponding to a given sample set def getFeatRefFile(wildcards): # Create dictionary with samples and FeatureRefFile diff --git a/workflow/schema/sample_map.schema.yaml b/workflow/schema/sample_map.schema.yaml index 3bf497e..91fb72a 100644 --- a/workflow/schema/sample_map.schema.yaml +++ b/workflow/schema/sample_map.schema.yaml @@ -7,9 +7,6 @@ properties: HashingFile: type: string description: Path to the Tag File - SeqRunName: - type: string - description: Sequencing sample name of ADT Fastq Files nTargetCells: type: integer description: The number of cells that were targeted in the lab @@ -20,7 +17,6 @@ properties: required: - sample - HashingFile - - SeqRunName - nTargetCells - featureReferenceFile