/
example.yaml
133 lines (130 loc) · 4.79 KB
/
example.yaml
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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
username: arendeiro
email: arendeiro@cemm.oeaw.ac.at
website_root: http://biomedical-sequencing.at/bocklab/arendeiro/
supported_data_types:
- ATAC-seq
- ChIP-seq
- RNA-seq
- CNV
preferences:
# For the next item, environment variables are formatted if they are of the form ${VAR}
root_reference_dir: /home/${USER}/reference/
root_projects_dir: /home/${USER}/projects/
default_genome_assemblies:
- human: hg38
- mouse: mm10
# The next item is the default computing configuration to use from divvy.
# Run "divvy list" to see all options.
# See more here: http://code.databio.org/divvy/
computing_configuration: 'default'
report:
record_figures: True
record_csv: True
continuous_generation: True
timestamp_figures: True
timestamp_tables: True
graphics:
matplotlib:
backend: TkAgg # Agg
# key:values under rcParams are used to update matplotlib.rcParams
rcParams:
# this ensures text in plots is exported as text objects
svg.fonttype: "none"
seaborn:
# key:values under parameters are passed to seaborn.set
parameters:
context: "paper"
style: "white"
palette: "colorblind"
color_codes: True
figure_saving:
# these arguments are passed to matplotlib.pyplot.savefig
# https://matplotlib.org/api/_as_gen/matplotlib.pyplot.savefig.html
format: svg
dpi: 300
bbox_inches: "tight"
close_saved_figures: True
sample_input_files:
# values in this section can use string formatting
# of the form {variable} to be completed with variables from the sample objects
# Example:
# ATAC-seq:
# aligned_filtered_bam:
# "{data_dir}/{sample_name}/mapped/{sample_name}.trimmed.bowtie2.filtered.bam"
ATAC-seq:
aligned_filtered_bam: "{data_dir}/{sample_name}/mapped/{sample_name}.trimmed.bowtie2.filtered.bam"
peaks: "{data_dir}/{sample_name}/peaks/{sample_name}_peaks.narrowPeak"
summits: "{data_dir}/{sample_name}/peaks/{sample_name}_summits.bed"
ChIP-seq:
aligned_filtered_bam: "{data_dir}/{sample_name}/mapped/{sample_name}.trimmed.bowtie2.filtered.bam"
ChIPmentation:
aligned_filtered_bam: "{data_dir}/{sample_name}/mapped/{sample_name}.trimmed.bowtie2.filtered.bam"
CNV:
log2_read_counts:
1000kb: "{data_dir}/{sample_name}/{sample_name}_1000kb/CNAprofiles/log2_read_counts.igv"
100kb: "{data_dir}/{sample_name}/{sample_name}_100kb/CNAprofiles/log2_read_counts.igv"
10kb: "{data_dir}/{sample_name}/{sample_name}_10kb/CNAprofiles/log2_read_counts.igv"
RNA-seq:
aligned_filtered_bam: "{data_dir}/{sample_name}/mapped/{sample_name}.trimmed.bowtie2.filtered.bam"
counts: "{data_dir}/{sample_name}/bowtie1_{genome}/bitSeq/{sample_name}.counts"
resources:
lola:
region_databases:
# under each section, there should be a list of items
hg19:
- /home/${USER}/resources/regions/LOLACore/hg19/
- /home/${USER}/resources/regions/customRegionDB/hg19/
hg38:
- /home/${USER}/resources/regions/LOLACore/hg38/
- /home/${USER}/resources/regions/customRegionDB/hg38/
mm10:
- /home/${USER}/resources/regions/LOLACore/mm10/
- /home/${USER}/resources/regions/customRegionDB/mm10/
region_set_labeling_columns:
- "collection"
- "description"
- "filename"
- "cellType"
- "tissue"
- "antibody"
- "treatment"
output_column_names:
odds_ratio: "oddsRatio"
log_p_value: "pValueLog"
meme:
motif_databases:
human: /home/${USER}/resources/motifs/motif_databases/HUMAN/HOCOMOCOv10.meme
mouse: /home/${USER}/resources/motifs/motif_databases/MOUSE/uniprobe_mouse.meme
vertebrate: /home/arendeiro/workspace/homer_4.8/data/knownTFs/vertebrates/known.motifs
motif_id_mapping:
mouse: /home/${USER}/resources/motifs/motif_databases/MOUSE/uniprobe_mouse.id_mapping.tsv
enrichr:
gene_set_libraries:
# this should be a list of items
- "GO_Biological_Process_2015"
- "ChEA_2015"
- "KEGG_2016"
- "ESCAPE"
- "Epigenomics_Roadmap_HM_ChIP-seq"
- "ENCODE_TF_ChIP-seq_2015"
- "ENCODE_and_ChEA_Consensus_TFs_from_ChIP-X"
- "ENCODE_Histone_Modifications_2015"
- "OMIM_Expanded"
- "TF-LOF_Expression_from_GEO"
- "Gene_Perturbations_from_GEO_down"
- "Gene_Perturbations_from_GEO_up"
- "Disease_Perturbations_from_GEO_down"
- "Disease_Perturbations_from_GEO_up"
- "Drug_Perturbations_from_GEO_down"
- "Drug_Perturbations_from_GEO_up"
- "WikiPathways_2016"
- "Reactome_2016"
- "BioCarta_2016"
- "NCI-Nature_2016"
- "BioPlanet_2019"
executables:
twoBitToFa: twoBitToFa
fasta-dinucleotide-shuffle: fasta-dinucleotide-shuffle
ame: ame
findMotifsGenome.pl: findMotifsGenome.pl
compareMotifs.pl: compareMotifs.pl