-
Notifications
You must be signed in to change notification settings - Fork 6
Expand file tree
/
Copy pathsnakemake_config.yaml
More file actions
134 lines (134 loc) · 4.7 KB
/
Copy pathsnakemake_config.yaml
File metadata and controls
134 lines (134 loc) · 4.7 KB
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
134
# Resource allocation
add_novel_transcripts_to_gtf_mem_gb: 2
add_novel_transcripts_to_gtf_time_hr: 6
check_asm_coupling_py_mem_gb: 2
check_asm_coupling_py_time_hr: 6
check_asm_coupling_r_mem_gb: 2
check_asm_coupling_r_time_hr: 6
check_transcript_to_asm_compatibility_mem_gb: 12
check_transcript_to_asm_compatibility_threads: 4
check_transcript_to_asm_compatibility_time_hr: 12
clean_espresso_gtf_mem_gb: 2
clean_espresso_gtf_time_hr: 6
count_reads_for_asms_mem_gb: 40
count_reads_for_asms_threads: 16
count_reads_for_asms_time_hr: 12
count_transcripts_for_asms_mem_gb: 4
count_transcripts_for_asms_time_hr: 6
create_alignments_from_events_mem_gb: 4
create_alignments_from_events_time_hr: 6
create_gtf_from_asm_definitions_mem_gb: 2
create_gtf_from_asm_definitions_time_hr: 6
detect_splicing_events_mem_gb: 12
detect_splicing_events_threads: 12
detect_splicing_events_time_hr: 12
filter_isoforms_with_counts_mem_gb: 8
filter_isoforms_with_counts_threads: 4
filter_isoforms_with_counts_time_hr: 12
organize_alignment_info_mem_gb: 12
organize_alignment_info_threads: 4
organize_alignment_info_time_hr: 12
organize_gene_info_mem_gb: 4
organize_gene_info_time_hr: 12
plot_gene_sets_mem_gb: 4
plot_gene_sets_time_hr: 1
rmats_long_mem_gb: 24
rmats_long_threads: 16
rmats_long_time_hr: 24
rmats_long_plots_mem_gb: 32
rmats_long_plots_threads: 16
rmats_long_plots_time_hr: 24
simplify_alignment_info_mem_gb: 4
simplify_alignment_info_time_hr: 12
# Command options
adj_pvalue: 0.05
delta_proportion: 0.05
average_reads_per_group: 10
average_cpm_per_group: 0
min_cpm_per_group: 0
asm_proportion_of_gene: 0.05
min_cpm_per_asm: 0
min_isoform_reads: 1
full_length_min_all_sjs_count: 0
asms_min_all_sjs_count: 1
basic_min_all_sjs_count: 1
limit_asm_to_top_n_isoforms: 50
min_reads_per_edge: 5
max_nodes_in_event: 50
max_paths_in_event: 50
plot_file_type: '.png'
intron_scaling: 1
max_transcripts: 7
coupling_min_reads_per_group: 10
simplify_gene_isoform_endpoints: false
filter_gene_isoforms_by_edge: false
quantify_full_length_transcripts: true
quantify_asms: true
quantify_basic_events: true
require_asms_to_be_strict: true
use_novel_junctions: false
count_compatible_transcripts_by_asm: false
# Reference files:
# The snakemake can automatically download and gunzip files if
# a matching url entry is given in the reference_files section below.
# If the entry in the reference_files section ends with .gz then the
# snakemake will gunzip the file.
# **The gtf_name should not end with .gz**
gtf_name: 'gencode.v47.primary_assembly.annotation.gtf'
# The entries under reference_files should be
# file_name.with.extension:
# url: 'url_path/to_the/file_name.with.extension'
#
# The 'url:' will be used to download the file and it will be put in
# references/ with the name given on the line above the 'url:'.
# The file will be gunzipped and the .gz removed if needed.
reference_files:
gencode.v47.primary_assembly.annotation.gtf.gz:
url: 'https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_47/gencode.v47.primary_assembly.annotation.gtf.gz'
# Input files:
# optional /path/to/updated.gtf to add novel ESPRESSO isoforms to the main gtf
espresso_gtf: ''
# The path to an existing annotation/ directory produced by
# organize_gene_info_by_chr.py can be used as annotation_dir.
# The .gtf used to create that directory should be given as gtf_name.
annotation_dir: ''
# The path to existing event directories from
# detect_splicing_events.py can be used.
# The configured annotation_dir above should be the same as the one
# used to detect the events.
# Using an existing event directory allows detecting events using
# all available samples and then using those events for a two group
# comparison using a subset of samples.
predefined_asm_events: ''
predefined_basic_events: ''
predefined_full_length_events: ''
# An optional .tsv with 1 line per sample.
# The first line has the column names.
# The first column is sample_id.
# Each additional column is a covariate.
covar_tsv: ''
# group_1_samples is required.
# group_2_samples can be set to {}
# For each sample, one of sam, bam, or simplified should be set.
# * sam: path to a .sam file
# * bam: path to a .bam file
# * simplified: path to a .tsv file created by simplify_alignment_info.py
group_1_name: 'PC3E'
group_1_samples:
pc3e_1:
- sam: '/path/to/example/pc3e_1_filtered.sam'
pc3e_2:
- sam: '/path/to/example/pc3e_2_filtered.sam'
pc3e_3:
- sam: '/path/to/example/pc3e_3_filtered.sam'
group_2_name: 'GS689'
group_2_samples:
gs689_1:
- sam: '/path/to/example/gs689_1_filtered.sam'
gs689_2:
- sam: '/path/to/example/gs689_2_filtered.sam'
gs689_3:
- sam: '/path/to/example/gs689_3_filtered.sam'
# Additional configuration
run_name: 'example'
# conda_wrapper: '/path/to/conda_wrapper' # will be written by ./install