Commit 76ba0d10 authored by aknecht2's avatar aknecht2
Browse files

Small updates to many yaml files. All peak callers now generating...

Small updates to many yaml files.  All peak callers now generating successfully.  Adjusted file_list input loding.  Fixed chip-job-ccat-format-bed to create correct number of columns.
parent 33e7891a
......@@ -26,6 +26,8 @@ align:
param_name: base_genome_file
align.sai:
param_name: input_sai
download_1.fastq:
param_name: base_fastq
ref_genome.amb:
param_name: genome.fna.amb
ref_genome.ann:
......
......@@ -11,7 +11,7 @@ idr:
- sort_awk_sort_peaks:
inputs:
idr.bed:
param_name: peak_results
param_name: result_peaks
outputs:
sorted_idr.bed:
param_name: sorted_peaks
......@@ -51,7 +51,7 @@ peak_call:
param_name: scale_1477.bed
final_result: true
sorted_scale_2216_all.bed:
param_name: scale_2216_all.bed
param_name: scale_2216.bed
final_result: true
- broad[peak_type]:
- music_broad:
......@@ -186,7 +186,7 @@ peak_call:
- sort_awk_sort_peaks:
inputs:
GEM_events.narrowPeak:
param_name: peak_results
param_name: result_peaks
outputs:
results_GEM_sorted.bed:
param_name: sorted_peaks
......@@ -194,7 +194,7 @@ peak_call:
- sort_awk_sort_peaks:
inputs:
GPS_events.narrowPeak:
param_name: peak_results
param_name: result_peaks
outputs:
results_GPS_sorted.bed:
param_name: sorted_peaks
......@@ -223,15 +223,15 @@ peak_call:
param_name: control.tagAlign
outputs:
results.narrowPeak.gz:
param_name: peak_results
param_name: result_peaks
results.pdf:
param_name: plots_df
param_name: plots_pdf
results.ccscore:
param_name: score
- sort_awk_sort_peaks:
inputs:
results.narrowPeak.gz:
param_name: peak_results
param_name: result_peaks
outputs:
results_sorted.bed:
param_name: sorted_peaks
......@@ -245,15 +245,15 @@ peak_call:
param_name: control.tagAlign
outputs:
results.broadPeak.gz:
param_name: peak_results
param_name: result_peaks
results.pdf:
param_name: plots_df
param_name: plots_pdf
results.ccscore:
param_name: score
- sort_awk_sort_peaks:
inputs:
results.broadPeak.gz:
param_name: peak_results
param_name: result_peaks
outputs:
results_sorted.bed:
param_name: sorted_peaks
......@@ -272,7 +272,7 @@ peak_call:
peaks.narrowPeak:
param_name: result_peaks
peaks.xls:
param_name: excel_result
param_name: result_excel
summits.bed:
param_name: result_summit
- sort_awk_sort_peaks:
......@@ -296,7 +296,7 @@ peak_call:
peaks.broadPeak:
param_name: result_peaks
peaks.xls:
param_name: excel_result
param_name: result_excel
summits.bed:
param_name: result_summit
- sort_awk_sort_peaks:
......
......@@ -40,18 +40,18 @@ bwa_sai_to_sam:
changeable: false
required: true
has_value: true
default: $outputs.0
- "$inputs.0":
default: $output_sam
- "$base_genome_file":
type: file
changeable: false
required: true
has_value: false
- "$inputs.1":
- "$input_sai":
type: file
changeable: false
required: true
has_value: false
- "$inputs.2":
- "$base_fastq":
type: file
changeable: false
required: true
......
......@@ -50,7 +50,7 @@ ccat_callpeak:
default: config_TF.txt
path: config
- "$prefix":
type: file
type: string
changeable: false
required: true
has_value: false
......
......@@ -12,7 +12,7 @@ macs2_broad:
result_peaks:
type: file
file_type: bed
excel_result:
result_excel:
type: file
file_type: xls
result_summit:
......
......@@ -12,7 +12,7 @@ macs2_narrow:
result_peaks:
type: file
file_type: bed
excel_result:
result_excel:
type: file
file_type: xls
result_summit:
......
......@@ -17,10 +17,10 @@ peakranger_callpeak:
file_type: bed
details:
type: file
file_type: bed
file_type: any
log:
type: stdout
file_type: bed
file_type: log
command: peakranger
arguments:
- "ranger":
......
sort_awk_sort_peaks:
inputs:
peak_results:
result_peaks:
type: file
file_type: bed
outputs:
......@@ -9,7 +9,7 @@ sort_awk_sort_peaks:
file_type: bed
command: chip-job-sort-peak
arguments:
- "$peak_results":
- "$result_peaks":
type: file
changeable: false
required: true
......
......@@ -7,7 +7,7 @@ spp_nodups_broad:
type: file
file_type: bed
outputs:
peak_results:
result_peaks:
type: file
file_type: bed
plots_pdf:
......@@ -53,7 +53,7 @@ spp_nodups_broad:
changeable: false
required: true
has_value: true
default: $peak_results
default: $result_peaks
- "-savp=":
type: file
changeable: false
......
......@@ -7,7 +7,7 @@ spp_nodups_narrow:
type: file
file_type: bed
outputs:
peak_results:
result_peaks:
type: file
file_type: bed
plots_pdf:
......@@ -53,7 +53,7 @@ spp_nodups_narrow:
changeable: false
required: true
has_value: true
default: $peak_results
default: $result_peaks
- "-savp=":
type: file
changeable: false
......
......@@ -512,7 +512,7 @@ class WorkflowJob(object):
"""
arg_value = self._get_arg_value(arg_name, arg_info)
add_value = arg_value
if isinstance(arg_value, str) and arg_value.startswith("$"):
if (isinstance(arg_value, str) and arg_value.startswith("$")) or arg_info["type"] == "rawfile":
arg_value = arg_value[1:]
if arg_info["type"] == "rawfile":
add_value = self.raw_files[os.path.basename(arg_value)]["file"]
......
......@@ -454,7 +454,7 @@ class WorkflowModule(object):
if wj_param["type"] == "file_list":
sub_list = []
param_dict[param_name] = {
"name": arg_params[logical_name],
"name": param_name,
"value": [{
"name": val,
"file": master_files[val]
......
......@@ -5,13 +5,13 @@ import os
# The ccat output is *mostly* correct, however simply sorting is not enough
# as the fourth column labels are not done in correct chromosome order
# After sorting the output looks like this:
# chr1 3086860 3087035 ccat_131620 4 . 5.483551 0.577000 0.001
# chr1 3318040 3318245 ccat_131610 4 . 5.483551 0.577000 0.001
# chr1 3372210 3372465 ccat_87299 5 . 6.854439 0.462000 0.001
# chr1 3086860 3087035 ccat_131620 4 0 5.483551 0.577000
# chr1 3318040 3318245 ccat_131610 4 0 5.483551 0.577000
# chr1 3372210 3372465 ccat_87299 5 0 6.854439 0.462000
# When it should look like this:
# chr1 3086860 3087035 ccat_0 4 . 5.483551 0.577000 0.001
# chr1 3318040 3318245 ccat_1 4 . 5.483551 0.577000 0.001
# chr1 3372210 3372465 ccat_2 5 . 6.854439 0.462000 0.001
# chr1 3086860 3087035 ccat_0 4 0 5.483551 0.577000 -1
# chr1 3318040 3318245 ccat_1 4 0 5.483551 0.577000 -1
# chr1 3372210 3372465 ccat_2 5 0 6.854439 0.462000 -1
parser = argparse.ArgumentParser(description = "Format ccat result files.")
parser.add_argument("--input", "-i", dest="input", required=True, help="Path to input ccat file.")
......@@ -34,4 +34,4 @@ with open(args.output, "w") as wh:
for i, line in enumerate(sorted_data):
# Fix the peak numbers
line[3] = "ccat_%s" % (i,)
wh.write("\t".join(line) + "\n")
wh.write("\t".join(line) + "\t-1\n")
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment