Variant Calling (Long-read DNA Germline)

Identify germline DNA variants in long-read DNA sequencing BAM files

tools

The following tools run by default (methods: "all"):

clair3, cutesv, deepvariant, delly2, dysgu, hificnv, longshot, nanocaller, nanovar, pbsv, sniffles2, svim

usage

nexus run --nf-workflow variant_calling_long-read-dna-germline.nf -params-file params.yaml

Note

Nextflow config files are available here. Use the config file that matches your installed nexus version (e.g. nexus_v0.2.0_nextflow_slurm.config).

parameters

Download params.yaml

# =============================================================================
# params.yaml — variant_calling_long-read-dna-germline
#
# Usage:
#   nextflow run variant_calling_long-read-dna-germline.nf -params-file params.yaml
#
# Fill in the required fields below. Optional fields can be left at their
# defaults or removed entirely.
# =============================================================================


# -----------------------------------------------------------------------------
# Required
# -----------------------------------------------------------------------------

# TSV file with columns:
#   sample_id
#   bam_file
#   bam_bai_file
samples_tsv_file: ""

# Directory to which output files will be copied
output_dir: ""

# Reference genome FASTA file
reference_genome_fasta_file: ""


# -----------------------------------------------------------------------------
# Optional — general
# -----------------------------------------------------------------------------

# Methods to run. Comma-separated list or 'all'.
# Allowed values:
#   all, clair3, cutesv, deepvariant, delly2, dysgu, hificnv,
#   longshot, nanocaller, nanovar, pbsv, sniffles2, svim
methods: "all"


# -----------------------------------------------------------------------------
# Clair3
# Optional arguments.
# -----------------------------------------------------------------------------
clair3:
  # Extra CLI arguments passed directly to Clair3.
  extra_args: "--model_path=/opt/models/hifi_sequel2/ --platform=hifi --min_coverage=3"


# -----------------------------------------------------------------------------
# CuteSV
# Optional arguments.
# -----------------------------------------------------------------------------
cutesv:
  # Extra CLI arguments passed directly to CuteSV.
  extra_args: "--max_cluster_bias_INS 1000 --diff_ratio_merging_INS 0.9 --max_cluster_bias_DEL 1000 --diff_ratio_merging_DEL 0.5 --min_support 3 --min_mapq 20 --min_size 30 --max_size -1 --report_readid --genotype"


# -----------------------------------------------------------------------------
# DeepVariant
# Required when methods includes 'deepvariant' or 'all':
#   input_path, output_path
# Optional otherwise.
# -----------------------------------------------------------------------------
deepvariant:
  # Required when running DeepVariant
  input_path: ""
  output_path: ""

  # Containerization engine: 'singularity' or 'docker'
  containerization: "singularity"

  # DeepVariant --model_type value
  model_type: "PACBIO"

  # Path to the run_deepvariant binary
  bin_path: "/opt/deepvariant/bin/run_deepvariant"

  # DeepVariant version
  bin_version: "1.9.0"


# -----------------------------------------------------------------------------
# Delly2
# Required when methods includes 'delly2' or 'all':
#   exclude_tsv_file
# Optional otherwise.
# -----------------------------------------------------------------------------
delly2:
  # Required when running Delly2
  exclude_tsv_file: ""

  # Extra CLI arguments passed directly to delly2 lr.
  extra_args: "--mapqual 20 --technology pb"


# -----------------------------------------------------------------------------
# Dysgu
# Optional arguments.
# -----------------------------------------------------------------------------
dysgu:
  # Extra CLI arguments passed directly to dysgu run.
  run_extra_args: "--mode pacbio-revio --min-support 3 --min-size 30 --mq 20"

  # Extra CLI arguments passed directly to dysgu filter.
  filter_extra_args: "--support-fraction 0.05 --min-mapq 20 --pass-prob 0.2"


# -----------------------------------------------------------------------------
# HiFiCNV
# Required when methods includes 'hificnv' or 'all':
#   exclude_bed_file
# Note: hificnv requires deepvariant to also be enabled, as it uses the
#   DeepVariant bgzipped VCF output as input.
# Optional otherwise.
# -----------------------------------------------------------------------------
hificnv:
  # Required when running HiFiCNV
  exclude_bed_file: ""

  # Extra CLI arguments passed directly to hificnv.
  extra_args: ""


# -----------------------------------------------------------------------------
# Longshot
# Optional arguments.
# -----------------------------------------------------------------------------
longshot:
  # Extra CLI arguments passed directly to longshot.
  extra_args: ""


# -----------------------------------------------------------------------------
# NanoCaller
# Optional arguments.
# -----------------------------------------------------------------------------
nanocaller:
  # Extra CLI arguments passed directly to NanoCaller.
  extra_args: "--preset ont --mode all --sequencing ont --phase --enable_whatshap"


# -----------------------------------------------------------------------------
# NanoVar
# Optional arguments.
# -----------------------------------------------------------------------------
nanovar:
  # Extra CLI arguments passed directly to NanoVar.
  extra_args: "--data_type ont"


# -----------------------------------------------------------------------------
# PBSV
# Optional arguments.
# -----------------------------------------------------------------------------
pbsv:
  # Extra CLI arguments passed directly to pbsv discover.
  discover_extra_args: "--ccs --min-gap-comp-id-perc 97 --min-mapq 20"

  # Extra CLI arguments passed directly to pbsv call.
  call_extra_args: "--ccs --call-min-reads-per-strand-all-samples 0 --call-min-read-perc-one-sample 10 --call-min-reads-all-samples 3 --call-min-reads-one-sample 3"


# -----------------------------------------------------------------------------
# Sniffles2
# Optional arguments.
# -----------------------------------------------------------------------------
sniffles2:
  # Extra CLI arguments passed directly to Sniffles2.
  extra_args: "--minsupport 3 --minsvlen 30 --mapq 20 --output-rnames"


# -----------------------------------------------------------------------------
# SVIM
# Optional arguments.
# -----------------------------------------------------------------------------
svim:
  # Extra CLI arguments passed directly to SVIM.
  extra_args: "--min_mapq 20 --min_sv_size 30 --insertion_sequences --read_names --zmws"