-
Notifications
You must be signed in to change notification settings - Fork 2
/
configuration_file.txt
103 lines (90 loc) · 3.93 KB
/
configuration_file.txt
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
############################################################################################################
### scRNApipe configuration file ### ##
##
## * General_Info - Input general parameters
## threads: # of threads to be used in the analysis in the whole analysis
##
## * Quality_Control - activation/deactivation parameters
## no_QualityControl: if set True, no Quality Control will be performed
##
## * Preprocessing
## no_PreProcessing: if set True, no PreProcessing will be performed
## transformation_file: .json pointing out the information position of R1 and R2
## cell_barcodes: .txt file listing all cellular barcodes contained in the reads
## cell_barcode_mm: number of allowed mismatches in the cell barcodes (default: 1)
## sample_barcodes: .txt file listing all sample barcodes used in the data
## sample_barcode_mm: number of allowed mismatches in the sample barcodes (default: 1)
##
## ### For further details about the above files, please visit umis on GitHub ###
##
## * Ref.Genome_Aligning
## no_ALignment: if set True, no aligning against the reference genome will be performed
## ### Refers to the default aligner - STAR ###
## reference_genome_idx: path to the reference genome indexes of STAR
##
## * Analysis - regulation parameters
## no_CounTing: if set True, no main analysis will be performed
## no_dedup: if set True, no PCR deduplication step will be performed
## skip_unassigned: if set True, unassigned reads will not be included in further analysis. This
## option is valid only in combination with "gene" implementation!
## implementation: "gene" (options: gene, feature, default)
## annotation_file: path to annotation file (.gtf file contain mRNA and ERCC annotation)
##
## * Expression_Matrix - regulation parameters
## no_ExMat: if set True, no Expression Matrix will be generated
## skip_genes: if set True, genes not found in the analysis will be skipped from the final
## Expression Matrix
## gene_list: path to mRNA ID list file (.csv file contain mRNA and ERCC IDs as a list)
##
## * IO_Info - Input/Output options
## input_dir: path to input Data folder (e.g home/Data)
## input_files: paths to input pair-end files (e.g home/XX_R1.fq.gz home/XX_R2.fq.gz)
## OR wildcard option (e.g home/*fastq.gz)
## output_dir: path of the output directory that all files of the analysis will be stored
## (default: current directory)
##
## This file contains the necessary input information (options/paths) for the correct analysis approach
## according to the dataset demands. The pipeline's sub-sessions contained can be optionally skipped
## by changing the boolean values from False to True. The input directory path (that contains the data)
## OR the input pair-end file OR input wildcard path is mandatory. If output_dir or input option won't
## be used, SHOULD BE MARKED with "-". The whole pipeline was designed to run fast and accurate with
## compressed data. Supported files: .fastq.gz/.fq.gz
##
## For further information concerning each option:
##
## scRNApipe --help
##
##
## Running the pipeline:
##
## scRNApipe <configuration_file.txt>
### ###
############################################################################################################
[General_Info]
threads = 1
[Quality_Control]
no_QualityControl = False
[Preprocessing]
no_PreProcessing = False
transformation_file = /transform.json
cell_barcodes = /cell_barcodes.txt
cell_barcode_mm = 1
sample_barcodes = /sample_barcodes.txt
sample_barcode_mm = 1
[RefGenome_Aligning]
no_ALignment = False
reference_genome_idx = /Star_overhang69
[MainAnalysis]
no_CounTing = False
no_dedup = False
skip_unassigned = True
implementation = gene
annotation_file = /GCv25_prim_assem_ERCC.gtf
[Expression_Matrix]
no_ExMat = False
skip_genes = False
gene_list = /GeneID.csv
[IO_Info]
input_dir = -
input_files = -
output_dir = -