example-config-pooled-feature-barcoding.yaml

# This config file describes an experiment.
# An experiment is "a collection of samples that need to be processed and analyzed together."

# The information under `experiment` is global; it does not change on a per-sample basis.
experiment:
  bcl2fastq_version: "2.20.0"      # Determines what image to run. Current Options: 2.20.0
  cellranger_version: "3.0.2"      # Determines what image to run Current Options: 2.2.0, 3.0.2
  # sequencing_runs metadata is used to generate the experiment name.
  # Based off the `sequencing_runs` data below, our generated experiment name would
  # be "run1_himc1_032519-run2_himc2_032519"
  # Sequencing run names are separated by '-'. We may have 1 or more sequencing
  # runs. When there is more than 1 run, we refer to them as "pooled runs"
  sequencing_runs:
    - id: "1" # must be a string
      himc_pool: "1" # must be a string
      date: "2019-03-25"
      bcl_file: "190325_NB501426_0271_AH2J72BGXB.tar.gz"
    - id: "2" # must be a string
      himc_pool: "2" # must be a string
      date: "2019-03-26" # YYYY-MM-DD
      bcl_file: "190326_NB501426_0272_AH2J75BGXY.tar.gz"
  meta:
    debug: true # boolean; defaults to false

# Either
# * Nothing
# * bcl2fastq
# * mkfastq
# * mkfastq & bcl2fastq
processing:
  mkfastq:
    samples:
      - name: 7002v3A
        index_location: SI-GA-E12
      - name: 7002v3B
        index_location: SI-GA-E11
  bcl2fastq:
    samples:
      - name: 7002v3A-A
        index_location: RPI9
      - name: 7002v3A-H
      # The `_s` suffix here is necessary so that we can accurately match the index_location
      # to a proper sequence in from our citeseq_sample_indices.csv file
        index_location: D709_s
      - name: 7002v3B-A
        index_location: RPI10
      - name: 7002v3B-H
      # The `_s` suffix here is necessary so that we can accurately match the index_location
      # to a proper sequence from our citeseq_sample_indices.csv file
        index_location: D710_s

analyses:
  samples:
    - name: 7002v3A
      job_type: count # may be count or vdj
      # a default chemistry of auto is usually sufficient to run cellranger count;
      # however, if errors are thrown, you may specify the chemistry
      # as per the 10x documentation: https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/count
      chemistry: auto
      reference_transcriptome:
        # may also be hg19, mm10, or vdj; see 10x-pipeline/reference_transcriptome
        # s3 bucket for currently available options for name and version. You may also reference
        # ./docs/Building_the_Pipeline.md
        name: GRCh38
        version: 1.2.0
      target_cell_count: 10000
      feature_barcoding:
        feature_type: Custom # other options include `Antibody Capture`
        directionality: 3p # may be 3p or 5p
        enabled: True # will be False if we're not performing feature barcoding
        samples:
        # We nest related CITE-seq samples under the "parent" GEX sample (e.g. 7002v3A)
          - name: 7002v3A-A
          - name: 7002v3A-H
        oligo_group_id: "1" # Refers to a specific group of oligos under the `oligo_groups` key
      pooled_run: True # will be False if we only have 1 sequencing run
    - name: 7002v3B
      job_type: count
      chemistry: auto
      reference_transcriptome:
        name: GRCh38
        version: 1.2.0
      target_cell_count: 10000
      feature_barcoding:
        feature_type: Custom
        directionality: 3p
        enabled: True
        samples:
          - name: 7002v3B-A
          - name: 7002v3B-H
        oligo_group_id: "1" # must be a string
      pooled_run: True
  oligo_groups:
    - id: "1" # must match an `oligo_group_id` value
      # Did we use Biolegend Total-Seq B or Total-Seq C antibodies?
      total_seq_b_c: False
      oligos:
      # HTO oligos must be prefixed with an 'HTO'. Our pipeline will automatically
      # prefix the ADTs with `adt_` so the ADT names should not be prefixed here.
      # These will be matched to a proper sequence from our adt_hto_bc_sequences.csv
      # file
        - CD86
        - CD274_PD-L1
        - CD26
        - CD40
        - CD3
        - CD4
        - CD8
        - CD45
        - CD19
        - CD14
        - CD33
        - CD11c
        - CD138
        - CD38
        - CD117
        - CD10
        - CD45RA
        - CD123
        - CD127
        - CD194_CCR4
        - CD16
        - CD56
        - CD25
        - CD279_PD-1
        - CD20
        - IgD
        - CD183_CXCR3
        - CD195_CCR5
        - CD196_CCR6
        - CD185_CXCR5
        - CD103
        - CD69
        - CD62L
        - CD197_CCR7
        - CD161
        - CD28
        - CD27
        - HLA-DR
        - CD1c
        - CD11b
        - CD141
        - CD66b
        - CD57
        - CD278_ICOS
        - CD24
        - CD206
        - CD169
        - CD370
        - CD314_NKG2D
        - TIGIT_VSTM3
        - CD273_PD-L2
        - CD5
        - XCR1
        - CD163
        - CD58
        - TCR_gamma_delta
        - CD272_BTLA
        - CD29
        - CD254
        - CD146
        - CD140a_PDGFRalpha
        - CD140b_PDGFRbeta
        - CD90_Thy1
        - CD105
        - CD326_Ep-CAM
        - CD44
        - CD31
        - CD134_OX40
        - CD223_LAG-3
        - CD152_CTLA-4
        - HLA-ABC
        - CD39
        - CD244_2B4
        - CD226_DNAM-1
        - CD115_CSF-1R
        - CD34
        - Podoplanin
        - CD54
        - CD9
        - FAP-IH
        - IgG4-IH
        - HTO_1
        - HTO_2
        - HTO_3
        - HTO_4
        - HTO_5
        - HTO_Mouse_A20