Skip to content
Snippets Groups Projects
Commit 4b3080c5 authored by Iris Mestres Pascual's avatar Iris Mestres Pascual
Browse files

chore: remove unused config file

parent b0c39e14
Branches
No related tags found
1 merge request!24chore: remove unused config file
---
#### GLOBAL PARAMETERS #####
# Directories
# Usually there is no need to change these
map_input_dir: "path/to/map_input_directory" # For the mapping worflow
quantify_input_dir: "path/to/quantify_input_directory" # For the quantify worflow
output_dir: "results"
scripts_dir: "../scripts"
local_log: "logs/local"
cluster_log: "logs/cluster"
# Inputs information
sample: ["sample_1", "sample_2"] # put all sample names, separated by comma
#######################################################################################################
####
#### PREPARE PARAMETERS
####
#######################################################################################################
# Isomirs annotation file
# Number of base pairs to add/substract from 5' (start) and 3' (end) coordinates.
bp_5p: [0] # array of numbers, e.g., [-2,-1,0,+1], to include 2 upstream and 1 downstream nts
bp_3p: [0] # array of numbers, e.g., [-2,-1,0,+1], to include 2 upstream and 1 downstream nts
# List of inputs
organism: ["org/pre"] # e.g., ["homo_sapiens/GRCh38.100", "mus_musculus/GRCm37.98"]
# this string specifies a path, and the "/" is important for this
# "pre" specifies the assembly version
#### PARAMETERS SPECIFIC TO INPUTS #####
org/pre: # One section for each list item in "organism"; entry should match precisely what
# is in the "organism" section above, one entry per list item above, omitting the ""
# URLs to genome, gene & miRNA annotations
genome_url: # FTP/HTTP URL to gzipped genome in FASTA format, Ensembl style
# e.g. "ftp://ftp.ensembl.org/pub/release-106/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna_sm.primary_assembly.fa.gz"
gtf_url: # FTP/HTTP URL to gzipped gene annotations in GTF format, Ensembl style
# e.g. "ftp://ftp.ensembl.org/pub/release-106/gtf/homo_sapiens/Homo_sapiens.GRCh38.106.chr.gtf.gz"
mirna_url: # FTP/HTTP URL to unzipped microRNA annotations in GFF format, miRBase style
# e.g. "https://www.mirbase.org/ftp/CURRENT/genomes/hsa.gff3"
# Chromosome name mappings between UCSC <-> Ensembl
# Other organisms available at: https://github.com/dpryan79/ChromosomeMappings
map_chr_url: # FTP/HTTP URL to mapping table
# e.g. "https://raw.githubusercontent.com/dpryan79/ChromosomeMappings/master/GRCh38_UCSC2ensembl.txt"
# Chromosome name mapping parameters:
column: 1 # Column number from input file where to change chromosome name
delimiter: "TAB" # Delimiter of the input file
#######################################################################################################
####
#### MAP PARAMETERS
####
#######################################################################################################
# Resources: genome, transcriptome, genes, miRs
# All of these are produced by the "prepare" workflow
genome: "path/to/genome.processed.fa"
gtf: "path/to/gene_annotations.filtered.gtf"
transcriptome: "path/to/transcriptome_idtrim.fa"
transcriptome_index_segemehl: "path/to/transcriptome_index_segemehl.idx"
genome_index_segemehl: "path/to/genome_index_segemehl.idx"
exons: "path/to/exons.bed"
header_of_collapsed_fasta: "path/to/headerOfCollapsedFasta.sam"
# Tool parameters: quality filter
q_value: 10 # Q (Phred) score; minimum quality score to keep
p_value: 50 # minimum % of bases that must have Q quality
# Tool parameters: adapter removal
error_rate: 0.1 # fraction of allowed errors
minimum_length: 15 # discard processed reads shorter than the indicated length
overlap: 3 # minimum overlap length of adapter and read to trim the bases
max_n: 0 # discard reads containing more than the indicated number of N bases
# Tool parameters: mapping
max_length_reads: 30 # maximum length of processed reads to map with oligomap
nh: 100 # discard reads with more mappings than the indicated number
#### PARAMETERS SPECIFIC TO INPUTS ####
sample_1: # one section per list item in "sample"; names have to match
adapter: "XXXXXXXXXXXXXXXXXXXX" # 3' adapter sequence to trim
format: "fa" # file format; currently supported: "fa"
#######################################################################################################
####
#### QUANTIFY PARAMETERS
####
#######################################################################################################
# Types of miRNAs to quantify
# Remove miRNA types you are not interested in
mir_list: ["miRNA", "miRNA_primary_transcript", "isomirs"]
# Resources: miR annotations, chromosome name mappings
# All of these are produced by the "prepare" workflow
mirnas_anno: "path/to/mirna_filtered.bed"
isomirs_anno: "path/to/isomirs_annotation.bed"
...
\ No newline at end of file
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment