Sequencing/config_template.yaml at main · gotencoder/Sequencing · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
## path to tools
samTools: samtools #/data/programs/samtools-1.10  #/path/to/samtools
bcfTools: bcftools  #/data/programs/bcftools-1.10.2  #/path/to/bcftools

## path to scripts ##
#Download these files and set paths below
readCounterScript: /czlab/inasim/hmmcopy_utils/bin/readCounter  #/path/to/readCounter
ichorCNA_rscript: /czlab/inasim/ichorCNA/scripts/runIchorCNA.R  #/path/to/ichorCNA.R - think it is called runIchorCNA.R now!
ichorCNA_libdir: /czlab/inasim/ichorCNA  #/path/to/ichorCNA_code - this is optional, point to the R dir of ichorCNA
pyCountScript: /czlab/inasim/titan_files/countPysam.py  #code/countPysam.py
TitanCNA_rscript: /czlab/inasim/titan_files/titanCNA.R   #../R_scripts/titanCNA.R
TitanCNA_combineTitanIchorCNA: /czlab/inasim/titan_files/combineTITAN-ichor.R #code/combineTITAN-ichor.R
TitanCNA_selectSolutionRscript: /czlab/inasim/titan_files/selectSolution.R  #../R_scripts/selectSolution.R
TitanCNA_libdir: /czlab/inasim/TitanCNA #../../R/


#hg38 version is below
genomeBuild: hg38 # Use "None" if hg19
genomeStyle:  UCSC
refFasta: /czlab/References/GRCh38/Homo_sapiens_assembly38.fasta  #/path/to/Homo_sapiens_assembly38.fasta
snpVCF: /czlab/References/GRCh38/Broad/hapmap_3.3.hg38.vcf.gz  #/path/to/hapmap_3.3.hg38.vcf.gz
ichorCNA_exons: abcdefgh
cytobandFile:  /czlab/inasim/titan_files/cytoBand_hg38.txt # only need if hg38
centromere:  /czlab/inasim/titan_files/GRCh38.GCA_000001405.2_centromere_acen.txt
sex:  None   # use "None" if both females and males are in sample set

## params for each step of the snakemake ##

## read depth params ##
# use this for NCBI chr naming
#chrs: 1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,X,Y #Make sure the bam has the same chr naming convention
# use this for UCSC chr naming
chrs: chr1,chr2,chr3,chr4,chr5,chr6,chr7,chr8,chr9,chr10,chr11,chr12,chr13,chr14,chr15,chr16,chr17,chr18,chr19,chr20,chr21,chr22,chrX,chrY
binSize:  50000

## ichorCNA params ##
#Need the hg38 wig files - set paths here!
ichorCNA_gcWig:  /czlab/inasim/titan_files/gc_hg38_50kb.wig  #/path/to/gc_hg19_10kb.wig
ichorCNA_mapWig: /czlab/inasim/titan_files/map_hg38_50kb.wig   #/path/to/map_hg19_10kb.wig
ichorCNA_repTimeWig: /czlab/inasim/ichorCNA/inst/extdata/Koren_repTiming_hg38_50kb.wig
ichorCNA_chrs:  c(1:22, \"X\")
ichorCNA_normal:  c(0.5)
ichorCNA_ploidy:  c(2,3,4,5)
ichorCNA_estimateNormal:  TRUE
ichorCNA_estimatePloidy:  TRUE
ichorCNA_estimateClonality: TRUE
ichorCNA_scStates:  c(1,3)
ichorCNA_maxCN:  8


ichorCNA_chrTrain:  paste0('chr', c(1:22))
# penalize subclonal events - n-fold multiplier; n=1 for no penalty,
ichorCNA_scPenalty: 1
ichorCNA_likModel: t  # if multisample, use "gauss"

# TRUE/FALSE to include homozygous deletion state
ichorCNA_includeHOMD: TRUE
# control segmentation - higher (e.g. 0.9999999) leads to higher specificity and fewer segments
ichorCNA_minMapScore: 0.75
ichorCNA_maxFracGenomeSubclone: 0.5
ichorCNA_maxFracCNASubclone: 0.7
# Ignore subclonal analysis when initial normal setting >= this value
ichorCNA_normal2IgnoreSC: 0.90
# lower (e.g. 0.99) leads to higher sensitivity and more segments
ichorCNA_txnE:  0.9999
# control segmentation - higher (e.g. 10000000) leads to higher specificity and fewer segments
# lower (e.g. 100) leads to higher sensitivity and more segments
ichorCNA_txnStrength:  10000
ichorCNA_plotFileType:  pdf
ichorCNA_plotYlim:  c(-2,4)


## allele counts - samtools, pysam ##
# USERS MUST MODIFY getAlleleCounts.snakefile to use the correct CHRS naming
map_quality:  10
base_quality: 10
vcf_quality:  100

## TitanCNA params ##
TitanCNA_maxNumClonalClusters: 2
TitanCNA_chrs:  c(1:22, \"X\")
TitanCNA_normalInit: 0.5
TitanCNA_maxPloidy: 5
TitanCNA_estimateNormal:  map
TitanCNA_estimatePloidy:  TRUE
TitanCNA_estimateClonality: TRUE
TitanCNA_alleleModel: binomial
TitanCNA_alphaK:  10000
TitanCNA_alphaR:  10000
TitanCNA_txnExpLen: 1e15
TitanCNA_plotYlim:  c(-2,4)
TitanCNA_solutionThreshold: 0.05
TitanCNA_numCores: 1

## Combine TitanCNA & ichorCNA
mergeIchorHOMD: FALSE  # consider setting to TRUE when working with pure tumor