Skip to content

Instantly share code, notes, and snippets.

@radaniba

radaniba/create_graph.py

Last active August 29, 2015 14:24
Show Gist options
  • Save radaniba/612dce1f57684b4b5989 to your computer and use it in GitHub Desktop.
Save radaniba/612dce1f57684b4b5989 to your computer and use it in GitHub Desktop.
Download ZIP
using networkx to create a simple graph
Raw
create_graph.py
import networkx as nx
import matplotlib.pyplot as plt
def draw_graph(graph, labels=None, graph_layout='shell',
node_size=1600, node_color='blue', node_alpha=0.3,
node_text_size=12,
edge_color='blue', edge_alpha=0.3, edge_tickness=1,
edge_text_pos=0.3,
text_font='sans-serif'):
# create networkx graph
G=nx.Graph()
# add edges
for edge in graph:
G.add_edge(edge[0], edge[1])
# these are different layouts for the network you may try
# shell seems to work best
if graph_layout == 'spring':
graph_pos=nx.spring_layout(G)
elif graph_layout == 'spectral':
graph_pos=nx.spectral_layout(G)
elif graph_layout == 'random':
graph_pos=nx.random_layout(G)
else:
graph_pos=nx.shell_layout(G)
# draw graph
nx.draw_networkx_nodes(G,graph_pos,node_size=node_size,
alpha=node_alpha, node_color=node_color)
nx.draw_networkx_edges(G,graph_pos,width=edge_tickness,
alpha=edge_alpha,edge_color=edge_color)
nx.draw_networkx_labels(G, graph_pos,font_size=node_text_size,
font_family=text_font)
if labels is None:
labels = range(len(graph))
edge_labels = dict(zip(graph, labels))
nx.draw_networkx_edge_labels(G, graph_pos, edge_labels=edge_labels,
label_pos=edge_text_pos)
# show graph
plt.show()
graph = [(0, 1), (1, 5), (1, 7), (4, 5), (4, 8), (1, 6), (3, 7), (5, 9),
(2, 4), (0, 4), (2, 5), (3, 6), (8, 9)]
# you may name your edge labels
labels = map(chr, range(65, 65+len(graph)))
#draw_graph(graph, labels)
# if edge labels is not specified, numeric labels (0, 1, 2...) will be used
draw_graph(graph)
Raw
example_pipeline.yaml
__PIPELINE_INFO__:
name: miseq_discovery_version
version: '1.7'
author: 'Rad'
data_type: null
input_type: 'fastq, tsv'
output_type: 'bam, tsv, vcf'
host_cluster: 'genesis'
date_created: ''
date_last_updated: 'Feb 5, 2015'
factory_version: '1.10.1'
__GENERAL__:
python: 'path to python binary'
java: 'path to java 1.7 binary'
bowtie2: 'path to bowtie2 binary'
gatk: 'path to GATK v 3.1.1 binary'
picard: 'path to picard tool AddOrReplaceReadGroups binary'
R: null
mutationseq: 'path to mutation seq'
__SHARED__:
ref_genome: 'path to the root directory of the reference genome'
ref_genome_fa: 'path to the fasta file of the reference genome'
normal_fastq_file_1: 'path to the normal sample forward fastq file'
normal_fastq_file_2: 'path to the normal sample reverse fastq file'
dbsnp: 'path to the vcf file of dbsnp138'
combined_vcfs: 'path to a file you choose to contain combined vcf calls for all the samples'
combination_log: 'path to a file you choose to contain the logs of combining vcf files'
amplicons_targets: 'path to the amplicon targets file, containing chromosome, start and end of each amplicon'
number_of_samples: 'number of samples to be analyzed'
ld_library_path: 'path to the shared library path'
__SAMPLES__:
sample_name:
fastq_file_1: 'path to the forward fastq file'
fastq_file_2: 'path to the reverse fastq file'
sample_id: 'sample_name'
__TASK_1__:
reserved:
# do not change this section
component_name: 'run_bowtie2'
component_version: '1.0.0'
seed_version: '2.0.0-beta7'
run:
use_cluster: True
memory: '5G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
seq2: ('__SHARED__','normal_fastq_file_2')
seq1: ('__SHARED__','normal_fastq_file_1')
reference: ('__SHARED__','ref_genome')
output_files:
outfile: 'alignment/normal.bam'
parameters:
__TASK_2__:
reserved:
# do not change this section
component_name: 'reheader'
component_version: '1.0.0'
seed_version: '3.1.1'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '5G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate: null
component:
input_files:
infile: ('__TASK_1__','outfile')
output_files:
outfile: 'reheaded/normal_reheaded.bam'
parameters:
__TASK_3__:
reserved:
# do not change this section
component_name: 'run_samtools_sort'
component_version: '1.0.0'
seed_version: '0.1.19'
run:
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_2__']
add_breakpoint: False
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
input: ('__TASK_2__','outfile')
output_files:
output: 'reheaded/normal.sorted.bam'
parameters:
options: '__OPTIONAL__'
__TASK_4__:
reserved:
# do not change this section
component_name: 'run_samtools_index'
component_version: '1.0.0'
seed_version: '0.1.19'
run:
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_3__']
add_breakpoint: False
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
input: ('__TASK_3__','output')
output_files:
parameters:
__TASK_5__:
reserved:
# do not change this section
component_name: 'create_targets'
component_version: '1.0.0'
seed_version: '3.1.1'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_4__']
add_breakpoint: False
env_vars:
boilerplate: null
component:
input_files:
indexed_bam: null
ref_genome: ('__SHARED__','ref_genome_fa')
infile: ('__TASK_3__','output')
output_files:
outfile: 'intervals/normal_positions.intervals'
parameters:
__TASK_6__:
reserved:
# do not change this section
component_name: 'realign'
component_version: '1.0.0'
seed_version: '3.1.1'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_4__']
add_breakpoint: False
env_vars:
boilerplate: null
component:
input_files:
sorted_alignment: ('__TASK_3__','output')
ref_genome: ('__SHARED__','ref_genome_fa')
infile: ('__TASK_5__','outfile')
output_files:
outfile: 'realignment/normal_realigned.bam'
parameters:
__TASK_7__:
reserved:
# do not change this section
component_name: 'base_quality_recalibrator_pre'
component_version: '1.0.0'
seed_version: '3.1.1'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '5G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate: null
component:
input_files:
dbsnp: ('__SHARED__','dbsnp')
ref_genome: ('__SHARED__','ref_genome_fa')
infile: ('__TASK_6__','outfile')
output_files:
outfile: 'realignment/normal_score.grp'
parameters:
__TASK_8__:
reserved:
# do not change this section
component_name: 'base_quality_recalibrator_post'
component_version: '1.0.0'
seed_version: '3.1.1'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '5G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate: null
component:
input_files:
dbsnp: ('__SHARED__','dbsnp')
ref_genome: ('__SHARED__','ref_genome_fa')
bqsr: ('__TASK_7__','outfile')
infile: ('__TASK_6__','outfile')
output_files:
outfile: 'realignment/normal_score.grp2'
parameters:
__TASK_9__:
reserved:
# do not change this section
component_name: 'print_reads'
component_version: '1.0.0'
seed_version: '3.1.1'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '5G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate: null
component:
input_files:
ref_genome: ('__SHARED__','ref_genome_fa')
bqsr: ('__TASK_7__','outfile')
infile: ('__TASK_6__','outfile')
output_files:
outfile: 'realignment/normal_recalibrated.bam'
parameters:
__TASK_10__:
reserved:
# do not change this section
component_name: 'run_samtools_sort'
component_version: '1.0.0'
seed_version: '0.1.19'
run:
use_cluster: True
memory: '5G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
input: ('__TASK_9__','outfile')
output_files:
output: 'realignment/normal_recalibrated.sorted.bam'
parameters:
options: null
__TASK_11__:
reserved:
# do not change this section
component_name: 'run_samtools_index'
component_version: '1.0.0'
seed_version: '0.1.19'
run:
use_cluster: True
memory: '5G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
input: ('__TASK_10__','output')
output_files:
parameters:
__TASK_12__:
reserved:
# do not change this section
component_name: 'run_bowtie2'
component_version: '1.0.0'
seed_version: '2.0.0-beta7'
run:
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_11__']
add_breakpoint: False
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
seq2: ('__SAMPLES__','fastq_file_2')
seq1: ('__SAMPLES__','fastq_file_1')
reference: ('__SHARED__','ref_genome')
output_files:
outfile: 'alignment/${sample_id}.bam'
parameters:
__TASK_13__:
reserved:
# do not change this section
component_name: 'reheader'
component_version: '1.0.0'
seed_version: '3.1.1'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '5G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate: null
component:
input_files:
infile: ('__TASK_12__','outfile')
output_files:
outfile: 'reheaded/${sample_id}_reheaded.bam'
parameters:
__TASK_14__:
reserved:
# do not change this section
component_name: 'run_samtools_sort'
component_version: '1.0.0'
seed_version: '0.1.19'
run:
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_13__']
add_breakpoint: False
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
input: ('__TASK_13__','outfile')
output_files:
output: 'reheaded/${sample_id}.sorted.bam'
parameters:
options: '__OPTIONAL__'
__TASK_15__:
reserved:
# do not change this section
component_name: 'run_samtools_index'
component_version: '1.0.0'
seed_version: '0.1.19'
run:
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_14__']
add_breakpoint: False
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
input: ('__TASK_14__','output')
output_files:
parameters:
__TASK_16__:
reserved:
# do not change this section
component_name: 'create_targets'
component_version: '1.0.0'
seed_version: '3.1.1'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_15__']
add_breakpoint: False
env_vars:
boilerplate: null
component:
input_files:
indexed_bam: null
ref_genome: ('__SHARED__','ref_genome_fa')
infile: ('__TASK_14__','output')
output_files:
outfile: 'intervals/${sample_id}_positions.intervals'
parameters:
__TASK_17__:
reserved:
# do not change this section
component_name: 'realign'
component_version: '1.0.0'
seed_version: '3.1.1'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_14__']
add_breakpoint: False
env_vars:
boilerplate: null
component:
input_files:
sorted_alignment: ('__TASK_14__','output')
ref_genome: ('__SHARED__','ref_genome_fa')
infile: ('__TASK_16__','outfile')
output_files:
outfile: 'realignment/${sample_id}_realigned.bam'
parameters:
__TASK_18__:
reserved:
# do not change this section
component_name: 'base_quality_recalibrator_pre'
component_version: '1.0.0'
seed_version: '3.1.1'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '5G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate: null
component:
input_files:
dbsnp: ('__SHARED__','dbsnp')
ref_genome: ('__SHARED__','ref_genome_fa')
infile: ('__TASK_17__','outfile')
output_files:
outfile: 'realignment/${sample_id}_score.grp'
parameters:
__TASK_19__:
reserved:
# do not change this section
component_name: 'base_quality_recalibrator_post'
component_version: '1.0.0'
seed_version: '3.1.1'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '5G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate: null
component:
input_files:
dbsnp: ('__SHARED__','dbsnp')
ref_genome: ('__SHARED__','ref_genome_fa')
bqsr: ('__TASK_18__','outfile')
infile: ('__TASK_17__','outfile')
output_files:
outfile: 'realignment/${sample_id}_score.grp2'
parameters:
__TASK_20__:
reserved:
# do not change this section
component_name: 'print_reads'
component_version: '1.0.0'
seed_version: '3.1.1'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '5G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate: null
component:
input_files:
ref_genome: ('__SHARED__','ref_genome_fa')
bqsr: ('__TASK_18__','outfile')
infile: ('__TASK_17__','outfile')
output_files:
outfile: 'realignment/${sample_id}_recalibrated.bam'
parameters:
__TASK_21__:
reserved:
# do not change this section
component_name: 'run_samtools_sort'
component_version: '1.0.0'
seed_version: '0.1.19'
run:
use_cluster: True
memory: '5G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
input: ('__TASK_20__','outfile')
output_files:
output: 'realignment/${sample_id}_recalibrated.sorted.bam'
parameters:
options: '__OPTIONAL__'
__TASK_22__:
reserved:
# do not change this section
component_name: 'run_samtools_index'
component_version: '1.0.0'
seed_version: '0.1.19'
run:
use_cluster: True
memory: '5G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
input: ('__TASK_21__','output')
output_files:
parameters:
__TASK_23__:
reserved:
# do not change this section
component_name: 'run_mutationseq'
component_version: '1.0.3'
seed_version: '4.3.3'
run:
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_22__']
add_breakpoint: False
env_vars:
PATH: '/genesis/extscratch/shahlab/raniba/pipelines/miseq_pipeline/miseq_analysis_pipeline/miseq-pipeline/software/samtools-0.1.19/'
LD_LIBRARY_PATH: ['/genesis/extscratch/shahlab/raniba/pipelines/miseq_pipeline/miseq_analysis_pipeline/miseq-pipeline/software/Python-2.7.6/lib']
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
tumour: ('__TASK_21__','output')
reference: ('__SHARED__','ref_genome_fa')
positions_file: null
normal: ('__TASK_10__','output')
model: 'model_deep_v0.2.npz'
config: 'metadata.config'
output_files:
export_features: null
out: 'calls/${sample_id}_mutationseq.vcf'
log_file: '../logs/mutationSeq_run.log'
parameters:
all: '__FLAG__'
features_only: '__FLAG__'
verbose: '__FLAG__'
normal_variant: 25
interval: null
titan_mode: '__FLAG__'
deep: True
no_filter: '__FLAG__'
manifest: ('__SHARED__','amplicons_targets')
tumour_variant: 2
single: False
normalized: '__FLAG__'
coverage: 4
return_cov: '__FLAG__'
threshold: 0.5
buffer_size: '2G'
baseq_threshold: 10
mapq_threshold: 20
purity: 70
__TASK_24__:
reserved:
# do not change this section
component_name: 'combine_vcfs'
component_version: '1.0.0'
seed_version: '1.0.0'
run:
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_23__']
add_breakpoint: True
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
input_vcf: ('__TASK_23__','out')
sample_id: ('__SAMPLES__','sample_id')
combined_vcfs: ('__SHARED__','combined_vcfs')
combination_log: ('__SHARED__','combination_log')
output_files:
outfile: '__OPTIONAL__'
parameters:
__TASK_25__:
reserved:
# do not change this section
component_name: 'create_positions'
component_version: '1.0.0'
seed_version: '1.0.0'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_24__']
add_breakpoint: False
env_vars:
boilerplate: null
component:
input_files:
amplicons_targets: ('__SHARED__','amplicons_targets')
infile: ('__SHARED__','combined_vcfs')
output_files:
outfile: 'positions/${sample_id}_positions.tsv'
parameters:
log_dump: ('__SHARED__','combination_log')
number_of_samples: ('__SHARED__','number_of_samples')
__TASK_26__:
reserved:
# do not change this section
component_name: 'build_amplicon_positions'
component_version: '1.0.0'
seed_version: '1.0.0'
run:
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_25__']
add_breakpoint: False
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
variant_positions: ('__TASK_25__','outfile')
output_files:
amplicon_positions: 'positions/${sample_id}_amplicons_positions.tsv'
parameters:
__TASK_27__:
reserved:
# do not change this section
component_name: 'build_count_files'
component_version: '1.0.0'
seed_version: '1.0.0'
run:
use_cluster: True
memory: '10G'
forced_dependencies: ['__TASK_26__', '__TASK_22__']
add_breakpoint: False
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
sorted_bam: ('__TASK_21__','output')
ref_genome: ('__SHARED__', 'ref_genome_fa')
amplicon_positions: ('__TASK_26__','amplicon_positions')
indexed_bam: null
output_files:
counts_file: 'counts/${sample_id}_counts.tsv'
parameters:
min_mqual: 10
min_bqual: 20
__TASK_28__:
reserved:
# do not change this section
component_name: 'do_binomial_exact_test'
component_version: '1.0.0'
seed_version: '1.0.0'
run:
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_27__']
add_breakpoint: False
env_vars:
boilerplate: null
parallel_run: False
parallel_params: []
interval_file: null
component:
input_files:
counts_file: ('__TASK_27__','counts_file')
variant_positions: ('__TASK_25__','outfile')
output_files:
variant_status: 'variant_status/${sample_id}_variant_status.tsv'
parameters:
low_coverage_threshold: 50
family_wise_error_rate: 0.001
variant_call_files_log: ('__SHARED__', 'snv_calls')
sample_ids_log: ('__SHARED__', 'snv_calls_ids')
__TASK_29__:
reserved:
# do not change this section.
component_name: 'run_strelka'
component_version: '1.2.0'
seed_version: '1.0.13'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '10G'
forced_dependencies: []
add_breakpoint: False
env_vars:
boilerplate:
component:
input_files:
tumor: ('__TASK_21__', 'output')
config: '__OPTIONAL__'
ref: ('__SHARED__','strelka_ref')
normal: ('__TASK_10__', 'output')
output_files:
output_dir: strelka_output
parameters:
num_procs: 8
isSkipDepthFilters: ('__SHARED__','isSkipDepthFilters')
__TASK_30__:
reserved:
# do not change this section.
component_name: 'run_snpeff'
component_version: '1.0.2'
seed_version: 'SnpEff 3.6b (build 2014-05-01)'
run:
use_cluster: True
memory: '4G'
forced_dependencies: ['__TASK_29__']
add_breakpoint: False
env_vars:
boilerplate:
parallel_run: False
parallel_params: []
interval_file:
component:
input_files:
variants_file: passed.somatic.snvs.vcf
config: 'snpEff_3_6/snpEff.config'
output_files:
stats: 'snpEff_summary.html'
out: 'strelka.passed.somatic.snvs.annotSnpEff.vcf'
parameters:
upDownStreamLen: '__OPTIONAL__'
verbose: '__FLAG__'
cancer: '__FLAG__'
treatAllAsProteinCoding: '__OPTIONAL__'
one: '__FLAG__'
dataDir: '__OPTIONAL__'
'no': '__OPTIONAL__'
outOffset: '__FLAG__'
help: '__FLAG__'
het: '__FLAG__'
oicr: '__FLAG__'
lof: '__FLAG__'
no_utr: '__FLAG__'
minC: '__OPTIONAL__'
sequenceOntology: '__FLAG__'
chr: '__OPTIONAL__'
around: '__FLAG__'
output_format: 'vcf'
cvsStats: '__FLAG__'
no_intergenic: '__FLAG__'
noLog: '__FLAG__'
noStats: True
del: '__FLAG__'
debug: '__FLAG__'
motif: '__FLAG__'
input_format: 'vcf'
maxQ: '__OPTIONAL__'
canon: '__FLAG__'
ins: '__FLAG__'
zero: '__FLAG__'
genome_version: 'GRCh37.66'
no_intron: '__FLAG__'
download: '__FLAG__'
maxC: '__OPTIONAL__'
cancerSamples: '__OPTIONAL__'
hom: '__FLAG__'
no_downstream: '__FLAG__'
hgvs: '__FLAG__'
minQ: '__OPTIONAL__'
reg: '__OPTIONAL__'
geneId: '__FLAG__'
onlyReg: '__FLAG__'
nmp: '__FLAG__'
threads: '__OPTIONAL__'
snp: '__FLAG__'
no_upstream: '__FLAG__'
interval: '__OPTIONAL__'
quiet: '__FLAG__'
filterInterval: '__OPTIONAL__'
inOffset: '__FLAG__'
__TASK_30a__:
reserved:
# do not change this section.
component_name: 'annot_mutationassessor_vcf'
component_version: '1.0.0'
seed_version: '1.0.0'
run:
use_cluster: True
memory: '10G'
forced_dependencies: []
add_breakpoint: False
env_vars:
LD_LIBRARY_PATH: ('__SHARED__', 'ld_library_path')
boilerplate:
parallel_run: False
parallel_params: ['vcf']
interval_file:
component:
input_files:
db: ('__SHARED__', 'mutation_assessor_db')
vcf: ('__TASK_30__', 'out')
output_files:
output: strelka.passed.somatic.snvs.annotSnpEff.annotMA.vcf
parameters:
__TASK_31__:
reserved:
# do not change this section.
component_name: 'flag_positions_vcf'
component_version: '1.0.3'
seed_version: '1.2.0'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '10G'
forced_dependencies: []
add_breakpoint: False
env_vars:
LD_LIBRARY_PATH: ('__SHARED__', 'ld_library_path')
boilerplate:
component:
input_files:
db: ('__SHARED__', 'dbsnp')
infile: ('__TASK_30a__', 'output')
output_files:
out: strelka.passed.somatic.snvs.annotSnpEff.annotMA.flagDBsnp.vcf
parameters:
label: DBSNP
flag_with_id: True
input_type: 'snv'
__TASK_32__:
reserved:
# do not change this section.
component_name: 'flag_positions_vcf'
component_version: '1.0.3'
seed_version: '1.2.0'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '10G'
forced_dependencies: []
add_breakpoint: False
env_vars:
LD_LIBRARY_PATH: ('__SHARED__', 'ld_library_path')
boilerplate:
component:
input_files:
db: ('__SHARED__', 'thousand_genomes')
infile: ('__TASK_31__', 'out')
output_files:
out: 'strelka.passed.somatic.snvs.annotSnpEff.annotMA.flagDBsnp.flag1000gen.vcf'
parameters:
label: 1000Gen
flag_with_id: '__FLAG__'
input_type: 'snv'
__TASK_32a__:
reserved:
# do not change this section.
component_name: 'flag_positions_vcf'
component_version: '1.0.3'
seed_version: '1.2.0'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '10G'
forced_dependencies: []
add_breakpoint: False
env_vars:
LD_LIBRARY_PATH: ('__SHARED__', 'ld_library_path')
boilerplate:
component:
input_files:
db: ('__SHARED__', 'cosmic_db')
infile: ('__TASK_32__', 'out')
output_files:
out: 'results/${sample_id}_strelka.passed.somatic.snvs.annotSnpEff.annotMA.flagDBsnp.flag1000gen.flagCosmic.vcf'
parameters:
label: Cosmic
flag_with_id: True
input_type: 'snv'
__TASK_33__:
reserved:
# do not change this section.
component_name: 'run_snpeff'
component_version: '1.0.2'
seed_version: 'SnpEff 3.6b (build 2014-05-01)'
run:
use_cluster: True
memory: '5G'
forced_dependencies: ['__TASK_29__']
add_breakpoint: False
env_vars:
boilerplate:
parallel_run: False
parallel_params: []
interval_file:
component:
input_files:
variants_file: passed.somatic.indels.vcf
config: 'snpEff_3_6/snpEff.config'
output_files:
stats: 'snpEff_summary.html'
out: 'strelka.passed.somatic.indels.annotSnpEff.vcf'
parameters:
upDownStreamLen: '__OPTIONAL__'
verbose: '__FLAG__'
cancer: '__FLAG__'
treatAllAsProteinCoding: '__OPTIONAL__'
one: '__FLAG__'
dataDir: '__OPTIONAL__'
'no': '__OPTIONAL__'
outOffset: '__FLAG__'
help: '__FLAG__'
het: '__FLAG__'
oicr: '__FLAG__'
lof: '__FLAG__'
no_utr: '__FLAG__'
minC: '__OPTIONAL__'
sequenceOntology: '__FLAG__'
chr: '__OPTIONAL__'
around: '__FLAG__'
output_format: 'vcf'
cvsStats: '__FLAG__'
no_intergenic: '__FLAG__'
noLog: '__FLAG__'
noStats: True
del: '__FLAG__'
debug: '__FLAG__'
motif: '__FLAG__'
input_format: 'vcf'
maxQ: '__OPTIONAL__'
canon: '__FLAG__'
ins: '__FLAG__'
zero: '__FLAG__'
genome_version: 'GRCh37.66'
no_intron: '__FLAG__'
download: '__FLAG__'
maxC: '__OPTIONAL__'
cancerSamples: '__OPTIONAL__'
hom: '__FLAG__'
no_downstream: '__FLAG__'
hgvs: '__FLAG__'
minQ: '__OPTIONAL__'
reg: '__OPTIONAL__'
geneId: '__FLAG__'
onlyReg: '__FLAG__'
nmp: '__FLAG__'
threads: '__OPTIONAL__'
snp: '__FLAG__'
no_upstream: '__FLAG__'
interval: '__OPTIONAL__'
quiet: '__FLAG__'
filterInterval: '__OPTIONAL__'
inOffset: '__FLAG__'
__TASK_34__:
reserved:
# do not change this section.
component_name: 'flag_positions_vcf'
component_version: '1.0.3'
seed_version: '1.2.0'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '10G'
forced_dependencies: []
add_breakpoint: False
env_vars:
LD_LIBRARY_PATH: ('__SHARED__', 'ld_library_path')
boilerplate:
component:
input_files:
db: ('__SHARED__', 'dbsnp')
infile: ('__TASK_33__', 'out')
output_files:
out: strelka.passed.somatic.indels.annotSnpEff.annotMA.flagDBsnp.vcf
parameters:
label: DBSNP
flag_with_id: True
input_type: 'indel'
__TASK_35__:
reserved:
# do not change this section.
component_name: 'flag_positions_vcf'
component_version: '1.0.3'
seed_version: '1.2.0'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '10G'
forced_dependencies: []
add_breakpoint: False
env_vars:
LD_LIBRARY_PATH: ('__SHARED__', 'ld_library_path')
boilerplate:
component:
input_files:
db: ('__SHARED__', 'thousand_genomes')
infile: ('__TASK_34__', 'out')
output_files:
out: 'strelka.passed.somatic.indels.annotSnpEff.annotMA.flagDBsnp.flag1000gen.vcf'
parameters:
label: 1000Gen
flag_with_id: '__FLAG__'
input_type: 'indel'
__TASK_35a__:
reserved:
# do not change this section.
component_name: 'flag_positions_vcf'
component_version: '1.0.3'
seed_version: '1.2.0'
run:
# NOTE: component cannot run in parallel mode.
use_cluster: True
memory: '10G'
forced_dependencies: []
add_breakpoint: False
env_vars:
LD_LIBRARY_PATH: ('__SHARED__', 'ld_library_path')
boilerplate:
component:
input_files:
db: ('__SHARED__', 'cosmic_db')
infile: ('__TASK_35__', 'out')
output_files:
out: 'results/${sample_id}_strelka.passed.somatic.indels.annotSnpEff.annotMA.flagDBsnp.flag1000gen.flagCosmic.vcf'
parameters:
label: Cosmic
flag_with_id: True
input_type: 'indel'
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment