-
Notifications
You must be signed in to change notification settings - Fork 2
/
mapping_config.yaml
97 lines (78 loc) · 3.5 KB
/
mapping_config.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
## -------------------- QUICK START ------------------------
# 1. Add organism defaults (e.g. Homo_sapiens.yaml or Mus_musculus.yaml)
# (optional) Overwrite the organism defaults under `organism:`
# 2. Under `pipeline_param:`, configure the paths
# 3. Under `pipeline_param:`, select the steps you wish to run
# 4. Under `report`, enter the meta data (like your name)
# 5. Run `sea-snap sample_info` to generate the sample_info.yaml file
# 5b. To test the configuration, run `sea-snap mapping l -np --cores 1`
# 6. Run `sea-snap mapping l --cores 1` (local, choose how many cores you want) or
# `sea-snap mapping --slumr c` (cluster)
## -------------------- PIPELINE CONFIGURATION ------------------------
# 1. --- organism annotation
organism_defaults: ### FILL HERE ### (e.g. Homo_sapiens.yaml)
## See in {sea-snap-directory}/defaults/ for predefined organism files
organism:
__options__: [name, genus, taxon, files, star_index, salmon_index, R]
### OVERWRITE ### organism defaults (e.g. gtf, genome and indices)
# --- general pipeline parameters
pipeline_param:
__options__: [out_path_pattern, log_path_pattern, in_path_pattern, mapping_results, QC_results]
# 2. configure the paths
in_path_pattern: ### FILL HERE ### (path pattern where fastq files are stored, without fastq.gz extension)
out_path_pattern: ### FILL HERE ###
log_path_pattern: ### FILL HERE ###
# Note:
# you need to use every wildcard from `in_path_pattern` both in folder names and file names
# of the output patterns.
#
# Examples:
# in_path_pattern: ../fastq/{sample}/{sample}
# out_path_pattern: mapping/{step}/{sample}/out/{step}.{sample}.{extension}
# log_path_pattern: mapping/{step}/{sample}/report/{step}.{sample}.{extension}
#
# in_path_pattern: input/{sample}/HLFFWDRXX/{lane}/{sample}_{library}_{lane}_{mate}_001
# out_path_pattern: mapping/{step}/{lane}/{library}/{mate}/{sample}/out/{step}.{lane}.{library}.{mate}.{sample}.{extension}
# log_path_pattern: mapping/{step}/{lane}/{library}/{mate}/{sample}/report/{step}.{lane}.{library}.{mate}.{sample}.{extension}
# Default output patterns:
out_path_pattern: mapping/{step}/{sample}/out/{step}.{sample}.{extension}
log_path_pattern: mapping/{step}/{sample}/report/{step}.{sample}.{extension}
# 3. adjust to select which steps to perform
mapping_results:
- salmon-transcript_counts
- star-gene_counts
- ciri-circRNA
## The QC results will be summarized by the multiqc step
## You will find the output under
## mapping/multiqc/.../out/multiqc....html
QC_results:
- fastqc
- dupradar
- infer_experiment
- qualimap_rnaseq
- qualimap_bamqc
#- rna_seqc
- preseq_c_curve
- preseq_lc_extrap
#- bw_from_bed
#ATAC_Seq:
# - macs2
#--- parameters for rules
# See {sea-snap-dir}/defaults/mapping_config_defaults.yaml for more information
rule_options:
__options__: [star, star_index, salmon, salmon_index]
# 4. --- report settings and metadata
report:
__options__: [multiqc]
multiqc:
report_header_info: ### UNCOMMENT AND FILL (OPTIONAL) ###
# - Contact E-mail: '<[email protected]>'
# - Application Type: 'RNA-seq'
# - Project Type: '<type>'
# - Sequencing Platform: '<platform>'
# - Sequencing Setup: '<setup>'
## Default output configuration:
title: SeA-SnaP mapping pipeline QC report
subtitle: run at the BIH CUBI
intro_text: The reports summarises results of several QC analyses
custom_logo: documentation/pictures/SeA-SnaP_logo.png