config.yaml

# ==== Config file for running the 10x Cell Ranger pipeline ====================


# Path to the fastq directory, multiple directories can be given.
RAW_DATA:
    - "full_raw_data/round_1,full_raw_data/round_2"

# A list of sample names. This will be the name of the output folder. All sample 
# names must be unique. There must be the same number of sample names as RNA_samples
# below.
SAMPLES:
    - "healthy_bcells_all"

# Sample names separated by groups to aggregate. If no samples to aggregate,
# leave this blank. Structure is as follows:
# AGGR_SAMPLES:
#   GROUP_NAME:
#      - "samplex"...
AGGR_SAMPLES:

# Sample names for gene expression fastqs. If the same libraries were
# sequenced multiple times, just include all the fastq directories in the
# RAW_DATA list and make sure the fastqs from all runs begin with the
# sample name. Only fastqs that begin with the sample name will be 
# included in the analysis.
RNA_SAMPLES:
    - "JH_GEX"

# Sample names for CITE-seq and cell hashing fastqs. If 
# the libraries were sequenced multiple times, just make sure the fastqs 
# from all runs begin with the sample name. If CITE-seq or cell hashing 
# was not performed, leave this blank. If you have CITE-seq on only a
# a subset of samples, keep the slot empty (ex. - "")
ADT_SAMPLES:
    - "JH_ADT"

# Sample names for VDJ fastqs. Follow the same parameters required for gene
# expression fastqs. If VDJ sequencing was not performed, leave this blank.
VDJ_SAMPLES:
    - "JH_GEX"

# Path to the output directory.
RESULTS:
    "results_vdj"

# Path to the Cell Ranger genome reference.
GENOME:
    "/beevol/home/rbilab/ref/cellranger/human/refdata-gex-GRCh38-2020-A"

# Path to the antibody reference table used to extract the antibody name 
# and barcode. If CITE-seq or cell hashing was not performed, leave this 
# blank.
ADT_REF:
    "files/antibody_barcodes.csv"

# Path to the Cell Ranger VDJ reference. If VDJ sequencing was not performed,
# leave this blank.
VDJ_REF:
    "/beevol/home/rbilab/ref/cellranger/mouse/refdata-cellranger-vdj-GRCm38-alts-ensembl-5.0.0"

# Maximum number of jobs per sample that can be submitted by Cell Ranger
# at a time.
MAX_JOBS:
    24

# Path to an LSF template, this is optional.
LSF_TEMPLATE:
    "lsf.template"

# Arguments to pass for chemistry. Only use this if the run failed.
CHEMISTRY:
    

VELOCYTO_GROUP: