config.yaml

# -----------------------------------------------------------------
# General options related to pipeline setup
# -----------------------------------------------------------------
max_cpus: 4  # max CPUs for any single job

scratch_dir: results/_scratch/  # put scratch files here

# -----------------------------------------------------------------
# Viral reference genomes
# -----------------------------------------------------------------

# align viral reads against this reference genome, which is constructed
# by adding to Wuhan-Hu-1 three mutations as described in
# https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7523107/
ref_genome:
  fasta: ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/858/895/GCF_009858895.2_ASM985889v3/GCF_009858895.2_ASM985889v3_genomic.fna.gz
  gff: ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/858/895/GCF_009858895.2_ASM985889v3/GCF_009858895.2_ASM985889v3_genomic.gff.gz
  name: proCoV2
  add_mutations: [C8782T, C18060T, T28144C]

# when mismatches, are they also present in these close-ish viral relatives?
# Note RaTG13 has highest overall identity, but according to
# https://www.biorxiv.org/content/10.1101/2021.01.22.427830v3.full,
# it is RmYN02, PrC31, and RpYN06 that are closest relatives after
# accounting for recombination. Of these, we use RpYN06 and RmYN02,
# which have higher identity overall.
comparator_genomes:
  RaTG13:
    gisaid: EPI_ISL_402131
  RpYN06:
    gisaid: EPI_ISL_1699446
  RmYN02:
    gisaid: EPI_ISL_412977
# directories with GISAID augur format downloads of comparator genomes
gisaid_comparator_dirs:
  - data/comparator_genomes_gisaid

# early consensus sequences to align and include in analysis
early_seqs:
  gisaid:
    # subdirectories with GISAID augur format downloads
    gisaid_through_Feb2020: data/gisaid_sequences_through_Feb2020/

# information to include in headers for early sequences
early_seq_header_props:
  - strain
  - gisaid_epi_isl
  - date
  - genbank_accession
  - country
  - location
  - age
  - sex

# -----------------------------------------------------------------
# General alignment and consensus / variant calling options
# -----------------------------------------------------------------
# short-read aligners to use
aligners:
  - minimap2
# since they give similar results, for now just minimap2 for smaller
# output files
#  - bwa-mem2

# in pileups, only consider sites where Q score >= this;
# also used for `fastp` preprocessing and `ivar` variant calling
minq: 20
# in `fastp` pre-processing require at least this read length
min_read_length: 20

# adapters to trim from reads
adapters_to_trim: data/Wang_et_al_primers.fasta

# Criteria used to call consensus from pileup
consensus_min_coverage: 3  # require >= this coverage
consensus_min_frac: 0.8  # require most common base > this fraction

# -----------------------------------------------------------------
# Parameters for analysis
# -----------------------------------------------------------------
# focus on spike through ORF10, which is region fully sequenced in:
# https://www.medrxiv.org/content/10.1101/2020.03.04.20029538v1.full-text
region_of_interest:
  start: 21570  # sequenced region supposedly start 21563, but often not coverage until later
  end: 29550  # sequenced region supposedly ends 29674, but often coverage not until earlier

# sequences from WHO-China joint report
who_china_report_cases: data/WHO_China_Report_Dec2019_cases.yaml
who_china_report_last_date: 2020-01-02  # check seqs up to this date to be in report

# sequences of individuals infected in Wuhan but exported and sequenced elsewhere
wuhan_exports: data/Wuhan_exports.yaml

# early sequences manually specified for exclusion
early_seqs_to_exclude: data/seqs_to_exclude.yaml

# ignore mutations before or after these sites, which define the beginning
# of ORF1ab and the end of ORF10. The reason is that there seem to be a lot
# of suspicious mutations near termini beyond these coding genes
# as there seem to be a lot called strings of mutations near termini
early_seqs_ignore_muts_before: 266
early_seqs_ignore_muts_after: 29674
# filter early consensus (GISAID) sequences on these criteria
# filter sequences with mutation runs (after doing above filtering
# on termini), so that any sequence with `n_muts` or more mutations
# in a span of `span` nucleotides is filtered
early_seqs_filter_runs:
  n_muts: 4
  span: 10
# remove if alignment covers < this fraction of reference
early_seqs_min_coverage: 0.9
# remove if >= this many substitutions relative to reference
early_seqs_max_subs: 15
# remove if >= this many ambiguous nucleotides in alignment to reference
early_seqs_max_ambiguous: 5000
# remove sequences collected after this date
early_seqs_max_date: 2020-02-28

# only work with samples from recovered sequences with fractional
# coverage >= this over the region of interest.
min_frac_coverage: 0.9

# -----------------------------------------------------------------
# Parameters for phylogenetic analysis
# -----------------------------------------------------------------
# last date of sequences to include for phylogenetic analyses
phylo_last_date: 2020-01-31
# only use GISAID sequences with >= this much of region of interest called for phylogenetics
phylo_min_frac_called: 0.95
# ignore (remove) mutations annotated as spurious in Table S1 of
# https://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1009175
phylo_muts_to_ignore: [G3564T, G8790T, G24933T, G2198A, G3145T, A3778G, C6255T,
                       A4050C, T8022G, T13402G, A13947T, A24389C, G24390C,
                       G1149T, C22802G, T153G]
# eliminate any mutations seen no more than this many times in the entire dataset
phylo_collapse_rare_muts: 0
# eliminate any sequences with mutation combinations seen no more than this many time
# after above collapsing
phylo_filter_rare_variants: 1

# color schemes
cat_colors:
  Wuhan: '#56B4E9'  # cbPalette light blue
  other China: '#009E73'  # cbPalette green
  outside China: '#F0E442'  # cbPalette yellow
subcat_colors:
  Huanan Seafood Market: '#0072B2'  # cbPalette dark blue
  deleted early Wuhan: '#E69F00'  # cbPalette orange
  Guangdong patient infected in Wuhan before Jan 5: '#D55E00'  # cbPalette red
  other Wuhan: '#56B4E9'  # cbPalette light blue
  other China: '#009E73'  # cbPalette green
  outside China: '#F0E442'  # cbPalette yellow

# ---------------------------------------------------------------------
# Specific samples not obtainable from cloud that are located elsewhere.
# The information on how to obtain these samples from various other
# locations was independently provided by the following individuals after
# publication of my initial pre-print:
#  - Andrew Fire (Stanford, https://en.wikipedia.org/wiki/Andrew_Fire)
#  - Theo Sanderson (Crick Institute, https://theo.io/)
#  - Francisco de Asis (DRASTIC Research, https://drasticresearch.org/tag/francisco-de-asis/)
# ---------------------------------------------------------------------
alternative_fastq_locations:
  SRR11313490: https://lifebit-sars-cov-2.s3-eu-west-1.amazonaws.com/reads/PRJNA612766/SRR11313490.fastq.gz
  SRR11313499: https://lifebit-sars-cov-2.s3-eu-west-1.amazonaws.com/reads/PRJNA612766/SRR11313499.fastq.gz

# -----------------------------------------------------------------
# Samples on SRA to download using `fasterq-dump`
# -------------------------------------------------------------------
samples_fasterq_dump: {}

# -----------------------------------------------------------------
# Samples on SRA to download using `wget`
# -------------------------------------------------------------------
samples_wget:
  # -----------------------------------------------------------------
  # BioProject PRJNA612766, human samples
  # The samples commented out could not be downloaded even using wget
  # -----------------------------------------------------------------
  A1:
    accessions: ['SRR11313282', 'SRR11313334']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  A2:
    accessions: ['SRR11313271', 'SRR11313461']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  A4:
    accessions: ['SRR11313417', 'SRR11313428']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  A6:
    # sample SRR11313490 is at an alternative location
    accessions: ['SRR11313479', 'SRR11313490']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  A9:
    accessions: ['SRR11313345', 'SRR11313356']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  A11:
    accessions: ['SRR11313455', 'SRR11313456']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  A12:
    accessions: ['SRR11313473', 'SRR11313474']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  B1:
    accessions: ['SRR11313453', 'SRR11313454']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  B2:
    accessions: ['SRR11313451', 'SRR11313452']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  B3:
    accessions: ['SRR11313448', 'SRR11313449']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  B4:
    accessions: ['SRR11313322', 'SRR11313333']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  B9:
    accessions: ['SRR11313445', 'SRR11313446']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  C1:
    accessions: ['SRR11313287', 'SRR11313289']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  C2:
    accessions: ['SRR11313285', 'SRR11313286']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  C9:
    accessions: ['SRR11313441', 'SRR11313442']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  C11:
    accessions: ['SRR11313300', 'SRR11313311']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  C12:
    accessions: ['SRR11313443', 'SRR11313444']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  D9:
    accessions: ['SRR11313436', 'SRR11313437']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  D11:
    accessions: ['SRR11313438', 'SRR11313440']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  D12:
    accessions: ['SRR11313280', 'SRR11313281']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  E1:
    accessions: ['SRR11313276', 'SRR11313277']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  E3:
    accessions: ['SRR11313430', 'SRR11313431']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  E5:
    accessions: ['SRR11313274', 'SRR11313275']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  E6:
    accessions: ['SRR11313427', 'SRR11313429']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  E11:
    accessions: ['SRR11313434', 'SRR11313435']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  E12:
    accessions: ['SRR11313432', 'SRR11313433']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  F5:
    accessions: ['SRR11313270', 'SRR11313470']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  F8:
    accessions: ['SRR11313423', 'SRR11313424']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  F11:
    accessions: ['SRR11313425', 'SRR11313426']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  G1:
    accessions: ['SRR11313468', 'SRR11313469']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  G11:
    accessions: ['SRR11313421', 'SRR11313422']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  G12:
    accessions: ['SRR11313419', 'SRR11313420']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  H9:
    accessions: ['SRR11313464', 'SRR11313465']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  H12:
    accessions: ['SRR11313466', 'SRR11313467']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: early outpatient
  R01:
    accessions: ['SRR11313409', 'SRR11313410']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R02:
    accessions: ['SRR11313406', 'SRR11313408']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R03:
    accessions: ['SRR11313269', 'SRR11313471']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R04:
    accessions: ['SRR11313509']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R05:
    accessions: ['SRR11313507', 'SRR11313508']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R06:
    accessions: ['SRR11313505', 'SRR11313506']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R07:
    accessions: ['SRR11313503', 'SRR11313504']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R08:
    accessions: ['SRR11313500', 'SRR11313502']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R09:
    # sample SRR11313499 is at an alternative location
    accessions: ['SRR11313498', 'SRR11313499']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R10:
    accessions: ['SRR11313496', 'SRR11313497']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R11:
    accessions: ['SRR11313494', 'SRR11313495']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R12:
    accessions: ['SRR11313492', 'SRR11313493']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R13:
    accessions: ['SRR11313489', 'SRR11313491']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R14:
    accessions: ['SRR11313487', 'SRR11313488']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R15:
    accessions: ['SRR11313485', 'SRR11313486']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  R16:
    accessions: ['SRR11313483', 'SRR11313484']
    collected_by: Renmin Hospital of Wuhan University
    patient_group: hospital patient (Feb)
  #
  # plasmid samples
  plasmid-1000cp-replicate01-1h_PRJNA612766:
    accessions: ['SRR11313331']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate01-2h_PRJNA612766:
    accessions: ['SRR11313330']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate01-4h_PRJNA612766:
    accessions: ['SRR11313329']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate01-10min_PRJNA612766:
    accessions: ['SRR11313335']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate01-30min_PRJNA612766:
    accessions: ['SRR11313332']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate02-1h_PRJNA612766:
    accessions: ['SRR11313326']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate02-2h_PRJNA612766:
    accessions: ['SRR11313325']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate02-4h_PRJNA612766:
    accessions: ['SRR11313324']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate02-10min_PRJNA612766:
    accessions: ['SRR11313328']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate02-30min_PRJNA612766:
    accessions: ['SRR11313327']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate03-1h_PRJNA612766:
    accessions: ['SRR11313320']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate03-2h_PRJNA612766:
    accessions: ['SRR11313319']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate03-4h_PRJNA612766:
    accessions: ['SRR11313318']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate03-10min_PRJNA612766:
    accessions: ['SRR11313323']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate03-30min_PRJNA612766:
    accessions: ['SRR11313321']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate04-1h_PRJNA612766:
    accessions: ['SRR11313315']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate04-2h_PRJNA612766:
    accessions: ['SRR11313314']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate04-4h_PRJNA612766:
    accessions: ['SRR11313313']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate04-10min_PRJNA612766:
    accessions: ['SRR11313317']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-1000cp-replicate04-30min_PRJNA612766:
    accessions: ['SRR11313316']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate01-1h_PRJNA612766:
    accessions: ['SRR11313309']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate01-2h_PRJNA612766:
    accessions: ['SRR11313308']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate01-4h_PRJNA612766:
    accessions: ['SRR11313307']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate01-10min_PRJNA612766:
    accessions: ['SRR11313312']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate01-30min_PRJNA612766:
    accessions: ['SRR11313310']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate02-1h_PRJNA612766:
    accessions: ['SRR11313304']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate02-2h_PRJNA612766:
    accessions: ['SRR11313303']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate02-4h_PRJNA612766:
    accessions: ['SRR11313302']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate02-10min_PRJNA612766:
    accessions: ['SRR11313306']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate02-30min_PRJNA612766:
    accessions: ['SRR11313305']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate03-1h_PRJNA612766:
    accessions: ['SRR11313298']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate03-2h_PRJNA612766:
    accessions: ['SRR11313297']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate03-4h_PRJNA612766:
    accessions: ['SRR11313296']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate03-10min_PRJNA612766:
    accessions: ['SRR11313301']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate03-30min_PRJNA612766:
    accessions: ['SRR11313299']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate04-1h_PRJNA612766:
    accessions: ['SRR11313293']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate04-2h_PRJNA612766:
    accessions: ['SRR11313292']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate04-4h_PRJNA612766:
    accessions: ['SRR11313291']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate04-10min_PRJNA612766:
    accessions: ['SRR11313295']
    collected_by: Aisi Fu
    patient_group: plasmid
  plasmid-3000cp-replicate04-30min_PRJNA612766:
    accessions: ['SRR11313294']
    collected_by: Aisi Fu
    patient_group: plasmid