Skip to content

Instantly share code, notes, and snippets.

@Phlya
Last active February 21, 2022 15:03
Show Gist options
  • Save Phlya/3dc64b6152bbcd9d7a2f52ccf22ad35f to your computer and use it in GitHub Desktop.
Save Phlya/3dc64b6152bbcd9d7a2f52ccf22ad35f to your computer and use it in GitHub Desktop.
distiller-nf project file used to analyse the bulk Hi-C and micro-C data for MCM-AID HCT116 cell line
# Fastqs can be provided as:
# -- a pairs of relative/absolute paths
# -- sra:<SRA_NUMBER>, optionally followed by the indices of the first and
# the last entry in the SRA in the form of "?start=<first>&end=<last>
# [to implement] -- as a path to a folder with fastqs '<base_folder>', with the structure
# <base_folder>/<library_name>/<run_name>/, with each folder containing only
# two fastq.gz files
input:
raw_reads_paths:
# Hi-C
MCM2-AID_-Aux_87322:
lane1:
- project/fastq/87322.1.1.dwnsmpl.fastq.gz
- project/fastq/87322.1.2.dwnsmpl.fastq.gz
lane2:
- project/fastq/87322.2.1.dwnsmpl.fastq.gz
- project/fastq/87322.2.2.dwnsmpl.fastq.gz
MCM2-AID_+Aux_87320:
lane1:
- project/fastq/87320.1.1.fastq.gz
- project/fastq/87320.1.2.fastq.gz
lane2:
- project/fastq/87320.2.1.fastq.gz
- project/fastq/87320.2.2.fastq.gz
# MicroC
G1_DMSO_1:
lane1:
- ./project/fastq/G1/rep1/dmso_lib1.R1.fastq.gz
- ./project/fastq/G1/rep1/dmso_lib1.R2.fastq.gz
G1_DMSO_2:
lane1:
- ./project/fastq/G1/rep1/dmso_lib2.R1.fastq.gz
- ./project/fastq/G1/rep1/dmso_lib2.R2.fastq.gz
G1_DMSO_3:
lane1:
- ./project/fastq/G1/rep1/dmso_lib3.R1.fastq.gz
- ./project/fastq/G1/rep1/dmso_lib3.R2.fastq.gz
G1_DMSO_4:
lane1:
- ./project/fastq/G1/rep1/dmso_lib4.R1.fastq.gz
- ./project/fastq/G1/rep1/dmso_lib4.R2.fastq.gz
G1_AUX_1:
lane1:
- ./project/fastq/G1/rep1/aux_lib1.R1.fastq.gz
- ./project/fastq/G1/rep1/aux_lib1.R2.fastq.gz
G1_AUX_2:
lane1:
- ./project/fastq/G1/rep1/aux_lib2.R1.fastq.gz
- ./project/fastq/G1/rep1/aux_lib2.R2.fastq.gz
G1_AUX_3:
lane1:
- ./project/fastq/G1/rep1/aux_lib3.R1.fastq.gz
- ./project/fastq/G1/rep1/aux_lib3.R2.fastq.gz
G1_AUX_4:
lane1:
- ./project/fastq/G1/rep1/aux_lib4.R1.fastq.gz
- ./project/fastq/G1/rep1/aux_lib4.R2.fastq.gz
G1_DMSO_r2_1:
lane1:
- ./project/fastq/G1/rep2/microC5_dmso_lib1.R1.fastq.gz
- ./project/fastq/G1/rep2/microC5_dmso_lib1.R2.fastq.gz
G1_DMSO_r2_2:
lane1:
- ./project/fastq/G1/rep2/microC5_dmso_lib2.R1.fastq.gz
- ./project/fastq/G1/rep2/microC5_dmso_lib2.R2.fastq.gz
G1_DMSO_r2_3:
lane1:
- ./project/fastq/G1/rep2/microC5_dmso_lib3.R1.fastq.gz
- ./project/fastq/G1/rep2/microC5_dmso_lib3.R2.fastq.gz
G1_AUX_r2_1:
lane1:
- ./project/fastq/G1/rep2/microC5_aux_lib1.R1.fastq.gz
- ./project/fastq/G1/rep2/microC5_aux_lib1.R2.fastq.gz
G1_AUX_r2_2:
lane1:
- ./project/fastq/G1/rep2/microC5_aux_lib2.R1.fastq.gz
- ./project/fastq/G1/rep2/microC5_aux_lib2.R2.fastq.gz
G1_AUX_r2_3:
lane1:
- ./project/fastq/G1/rep2/microC5_aux_lib3.R1.fastq.gz
- ./project/fastq/G1/rep2/microC5_aux_lib3.R2.fastq.gz
AUX_TRP_1:
lane1:
- ./project/fastq/trp/microC6_aux.trp_lib1.R1.fastq.gz
- ./project/fastq/trp/microC6_aux.trp_lib1.R2.fastq.gz
AUX_TRP_2:
lane1:
- ./project/fastq/trp/microC6_aux.trp_lib2.R1.fastq.gz
- ./project/fastq/trp/microC6_aux.trp_lib2.R2.fastq.gz
AUX_TRP_3:
lane1:
- ./project/fastq/trp/microC6_aux.trp_lib3.R1.fastq.gz
- ./project/fastq/trp/microC6_aux.trp_lib3.R2.fastq.gz
DMSO_TRP_1:
lane1:
- ./project/fastq/trp/microC6_dmso.trp_lib1.R1.fastq.gz
- ./project/fastq/trp/microC6_dmso.trp_lib1.R2.fastq.gz
DMSO_TRP_2:
lane1:
- ./project/fastq/trp/microC6_dmso.trp_lib2.R1.fastq.gz
- ./project/fastq/trp/microC6_dmso.trp_lib2.R2.fastq.gz
DMSO_TRP_3:
lane1:
- ./project/fastq/trp/microC6_dmso.trp_lib3.R1.fastq.gz
- ./project/fastq/trp/microC6_dmso.trp_lib3.R2.fastq.gz
library_groups:
# Micro-C
G1_DMSO_rep1:
- G1_DMSO_1
- G1_DMSO_2
- G1_DMSO_3
- G1_DMSO_4
G1_AUX_rep1:
- G1_AUX_1
- G1_AUX_2
- G1_AUX_3
- G1_AUX_4
G1_DMSO_rep2:
- G1_DMSO_r2_1
- G1_DMSO_r2_2
- G1_DMSO_r2_3
- G1_DMSO_r2_4
G1_AUX_rep2:
- G1_AUX_r2_1
- G1_AUX_r2_2
- G1_AUX_r2_3
- G1_AUX_r2_4
G1_DMSO_merged:
- G1_DMSO_1
- G1_DMSO_2
- G1_DMSO_3
- G1_DMSO_4
- G1_DMSO_r2_1
- G1_DMSO_r2_2
- G1_DMSO_r2_3
- G1_DMSO_r2_4
G1_AUX_merged:
- G1_AUX_1
- G1_AUX_2
- G1_AUX_3
- G1_AUX_4
- G1_AUX_r2_1
- G1_AUX_r2_2
- G1_AUX_r2_3
- G1_AUX_r2_4
AUX_TRP:
- AUX_TRP_1
- AUX_TRP_2
- AUX_TRP_3
DMSO_TRP:
- DMSO_TRP_1
- DMSO_TRP_2
- DMSO_TRP_3
truncate_fastq_reads: 0
genome:
assembly_name: 'hg38'
bwa_index_wildcard_path: '/exports/igmm/eddie/wendy-lab/ilia/genomes/hg38/bwaindex/hg38.fa*'
chrom_sizes_path: '/exports/igmm/eddie/wendy-lab/ilia/genomes/hg38/chrfile.txt'
do_fastqc: False
map:
chunksize: 10000000
mapping_options: ''
long_reads: False
parse:
make_pairsam: False
drop_readid: False
drop_seq: True
keep_unparsed_bams: False
parsing_options: '--add-columns mapq'
dedup:
max_mismatch_bp: 0
bin:
resolutions:
- 10000000
- 5000000
- 2500000
- 1000000
- 500000
- 250000
- 100000
- 50000
- 25000
- 10000
- 5000
- 2000
- 1000
- 5000
- 200
- 100
balance: True
# balance_options: '--cis-only'
filters:
no_filter: ''
mapq_30: '(mapq1>=30) and (mapq2>=30)'
# Control the stats output
stats:
# This option will produce separate stats for filters (listed in bins):
use_filters: True
output:
dirs:
processed_fastqs: './project/output/processed_fastqs/'
mapped_parsed_sorted_chunks: './project/output/mapped_parsed_sorted_chunks'
fastqc: './project/output/fastqc/'
pairs_library: './project/output/pairs_library'
coolers_library: './project/output/coolers_library/'
coolers_library_group: './project/output/coolers_library_group/'
stats_library: './project/output/stats_library/'
stats_library_group: './project/output/stats_library_group/'
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment