config.yml

# Default parameterset for Expander
ref_genome: "/mnt/share/data/genomes/GRCh38.fa"
sample_targets: "sample_targets.tsv"

# Minimap 2 parameters (based on PacBio Repeat expansion script)
mm2.r: 10000  # bandwidth for inital chaining and base alignment extension [500]
mm2.A: 2      # matching score [2]
mm2.B: 5      # mismatching penalty [4]
mm2.z: 400    # truncate alignment if diagonal score in DP matrix drops below z [400]
mm2.Z: 50     # not documentend in minimap2 man
mm2.O: 56     # gap open penalty [4]
mm2.e: 4      # sample a high-frequency minimizer every INT basepairs [500]
mm2.E: 0      # gap extension penalty [2]
mm2.Y: true   # -Y enable softclipping  

# Tandem repeat finder parameters
trf.match: 2      # matching weight
trf.mismatch: 7   # mismatching penalty
trf.delta: 7      # indel penalty
trf.pm: 80        # match probability (int)
trf.pi: 10        # indel probabilty (int)
trf.minscore: 50  # minimum alignment score to report
trf.maxperiod: 10 # maximum period size to report

# Repeat filters (after TRF)
# Corresponds to columns of TRF output: https://blaxter-lab-documentation.readthedocs.io/en/latest/trf.html#program-outputs
f.min_period : 3         # minimum length of repeat
f.max_period : 7         # maximum length of repeat motif 
f.min_copies : 5         # minimum number of aligned repeat motifs
f.min_match:  50         # minimum percent of matches between adjacent copies overall
f.max_indels: 30         # maximum percent of indels between adjacent copies overall
f.min_score:  50         # min alignment score of repeat sequence
f.min_entropy: 0.5       # min sequence entropy of repeat sequence
f.min_reads: 4           # minimum number of reads in the same repeat cluster

# Clustering options
clust.height: 0.3     # Clustering height (distance) to bin reads into different locu 
clust.allele_height: 2   # Min clusterring height to bin reads into different alleles (will increase if >3)

# Plot options
plot_allele_clusters: true
pdf : true
png: true
jpg: false

verbose: true