def fastqc_detailed_figure(input={
"template": "",
"dbaccessor": "",
"json": ""
},
output={
"R": "",
"pdf": ""
},
param={"ids": ""}):
quality_medians = []
stat = json_load(input["json"])['stat']
for s in param['ids']:
quality_medians.append(stat[s]['median'])
## from dbaccessor module
historic_data = db_fastqc(input["dbaccessor"])
# The table of fastqc_summary that will be used for rendering
# Col 1: sample ID
# Col 2: sequence length
# Col 3: median of sequence quality
fastqc_dist_r = JinjaTemplateCommand(
template=input["template"],
param={
'historic_data': historic_data,
'current_data': quality_medians,
'ids': [underline_to_space(i) for i in param["ids"]],
'cutoff': 25,
"need_smooth_curve": True,
"section": "FastQC score distribution",
"pdf": output["pdf"],
"render_dump": output["R"]
})
template_dump(fastqc_dist_r)
r_exec(fastqc_dist_r)
def long_tex(input, output, param):
latex = JinjaTemplateCommand(
name="mapping quality",
template=input["template"],
param={"phan": input["figure"],
"render_dump": output["latex"]})
template_dump(latex)
def latex_contamination(input, output, param):
"""
input bowtie json files generated from mapping to different species
:param input:
:param output:
:param param:
:return:
"""
json_dict = json_load(input["json"])
if len(json_dict["stat"]["meta"]["species"]) < 1:
section_name = ""
else:
section_name = "library_contamination"
contam_values = json_dict["stat"]["value"]
for sample in contam_values:
for species in contam_values[sample]:
contam_values[sample][species] = decimal_to_latex_percent(contam_values[sample][species])
library_quality_latex = JinjaTemplateCommand(
name="library contamination",
template=input["template"],
param={"section_name": section_name,
"library_contamination": json_dict["stat"],
'prefix_dataset_id': json_dict["param"]['id'],
'layout': param['layout'],
"render_dump": output["latex"]})
template_dump(library_quality_latex)
def fastqc_detailed_figure(input = {"template": "", "dbaccessor": "", "json": ""},output = {"R":"", "pdf":""},
param={"ids": ""}):
quality_medians = []
stat = json_load(input["json"])['stat']
for s in param['ids']:
quality_medians.append(stat[s]['median'])
## from dbaccessor module
historic_data = db_fastqc(input["dbaccessor"])
# The table of fastqc_summary that will be used for rendering
# Col 1: sample ID
# Col 2: sequence length
# Col 3: median of sequence quality
fastqc_dist_r = JinjaTemplateCommand(
template=input["template"],
param={'historic_data': historic_data,
'current_data': quality_medians,
'ids': [underline_to_space(i) for i in param["ids"]],
'cutoff': 25,
"need_smooth_curve": True,
"section": "FastQC score distribution",
"pdf": output["pdf"],
"render_dump": output["R"]})
template_dump(fastqc_dist_r)
r_exec(fastqc_dist_r)
def long_tex(input, output, param):
latex = JinjaTemplateCommand(name="mapping quality",
template=input["template"],
param={
"phan": input["figure"],
"render_dump": output["latex"]
})
template_dump(latex)
def latex_conservation(input, output, param):
latex = JinjaTemplateCommand(
name = "conservation",
template = input["template"],
param={"conservation_compare_graph": param["prefix"] + "_conserv_compare.pdf",
"conservation_graph": param["prefix"] + "_conserv.pdf",
"render_dump": output["latex"]})
template_dump(latex)
def load_gc_latex(input, output, param):
latex = JinjaTemplateCommand(template=input["template"],
param={
"gccontent_graphs":
input["gccontent_graphs"],
"render_dump": output["latex"]
})
template_dump(latex)
def latex_summary_table(input, output, param):
summary = summary_table(param["conf"])
latex = JinjaTemplateCommand(
template=input["template"],
param={"summary_table": summary,
"layout": param["layout"],
"render_dump": output["latex"]})
template_dump(latex)
def latex_summary_table(input, output, param):
summary = summary_table(param["conf"])
latex = JinjaTemplateCommand(template=input["template"],
param={
"summary_table": summary,
"layout": param["layout"],
"render_dump": output["latex"]
})
template_dump(latex)
def latex_seqpos(input, output, param):
json_dict = json_load(input["json"])
latex = JinjaTemplateCommand(
name="motif finding",
template=input["template"],
param={
"motif_table":
json_dict["stat"]["satisfied_motifs"][:5], ## use top 5 motif
"render_dump": output["tex"]
})
template_dump(latex)
def load_latex(input, output, param):
json_dict = json_load(input["json"])
frip_table = []
stat = json_dict["stat"]
for sample in stat: #sample is the keys in the stat dictionary
frip_table.append([underline_to_space(str(sample)), stat[sample]["info_tag"], stat[sample]["total_tag"], decimal_to_latex_percent(stat[sample]["frip"])])
latex = JinjaTemplateCommand(
template=input["template"],
param={"frip_table": frip_table,
"render_dump": output["latex"]})
template_dump(latex)
def latex_conservation(input, output, param):
if os.path.exists(param["prefix"] + "_conserv_compare.pdf"):
latex = JinjaTemplateCommand(name="conservation",
template=input["template"],
param={
"conservation_compare_graph":
param["prefix"] +
"_conserv_compare.pdf",
"conservation_graph":
param["prefix"] + "_conserv_img.png",
"render_dump":
output["latex"]
})
template_dump(latex)
def bwa_figures(input={"dbaccessor": "", "json": ""}, output = {"figure": ""}, param = {}):
historyData = db_bwa(input["dbaccessor"])
json_dict = json_load(input["json"])
mappable_rates = [float(json_dict["stat"][i]["mapped"])/json_dict["stat"][i]['total'] for i in param["sample"]]
mappable_rate_R = JinjaTemplateCommand(template=input["template"],
param={'historic_data': historyData,
'current_data': mappable_rates,
'ids': param['sample'],
'cutoff': 0.5,
'section': 'Unique mapped rate',
"need_smooth_curve": True,
"render_dump": output["R"],
"pdf": output["pdf"]})
template_dump(mappable_rate_R)
r_exec(mappable_rate_R)
def bwa_figures(input={"dbaccessor": "", "json": ""}, output = {"figure": ""}, param = {}):
historyData = db_bwa(input["dbaccessor"])
json_dict = json_load(input["json"])
mappable_rates = [float(json_dict["stat"][i]["mapped"])/json_dict["stat"][i]['total'] for i in param["sample"]]
mappable_rate_R = JinjaTemplateCommand(template=input["template"],
param={'historic_data': historyData,
'current_data': mappable_rates,
'ids': param['sample'],
'cutoff': 0.5,
'section': 'Unique mapped rate',
"need_smooth_curve": True,
"render_dump": output["R"],
"pdf": output["pdf"]})
template_dump(mappable_rate_R)
r_exec(mappable_rate_R)
def load_latex(input, output, param):
json_dict = json_load(input["json"])
fastqc_summary = []
stat = json_dict["stat"]
for sample in stat:
fastqc_summary.append([underline_to_space(sample), stat[sample]["sequence_length"], stat[sample]["median"]])
latex = JinjaTemplateCommand(
template=input["template"],
param={"section_name": "sequence_quality",
"path": input["pdf"],
"fastqc_table": fastqc_summary,
"fastqc_graph": input["pdf"],
'prefix_dataset_id': [ underline_to_space(i) for i in stat.keys() ],
"render_dump": output["latex"]})
template_dump(latex)
def load_latex(input, output, param):
json_dict = json_load(input["json"])
frip_table = []
stat = json_dict["stat"]
for sample in stat: #sample is the keys in the stat dictionary
frip_table.append([
underline_to_space(str(sample)), stat[sample]["info_tag"],
stat[sample]["total_tag"],
decimal_to_latex_percent(stat[sample]["frip"])
])
latex = JinjaTemplateCommand(template=input["template"],
param={
"frip_table": frip_table,
"render_dump": output["latex"]
})
template_dump(latex)
def load_latex(input, output, param):
json_dict = json_load(input["json"])
fastqc_summary = []
stat = json_dict["stat"]
for sample in stat:
fastqc_summary.append([
underline_to_space(sample), stat[sample]["sequence_length"],
stat[sample]["median"]
])
latex = JinjaTemplateCommand(
template=input["template"],
param={
"section_name": "sequence_quality",
"path": input["pdf"],
"fastqc_table": fastqc_summary,
"fastqc_graph": input["pdf"],
'prefix_dataset_id': [underline_to_space(i) for i in stat.keys()],
"render_dump": output["latex"]
})
template_dump(latex)
def latex_contamination(input, output, param):
"""
input bowtie json files generated from mapping to different species
:param input:
:param output:
:param param:
:return:
"""
json_dict = json_load(input["json"])
if len(json_dict["stat"]["meta"]["species"]) < 1:
section_name = ""
else:
section_name = "library_contamination"
contam_values = json_dict["stat"]["value"]
for sample in contam_values:
for species in contam_values[sample]:
contam_values[sample][species] = decimal_to_latex_percent(
contam_values[sample][species])
library_quality_latex = JinjaTemplateCommand(name="library contamination",
template=input["template"],
param={
"section_name":
section_name,
"library_contamination":
json_dict["stat"],
'prefix_dataset_id':
json_dict["param"]['id'],
'layout':
param['layout'],
"render_dump":
output["latex"]
})
template_dump(library_quality_latex)
def load_gc_latex(input, output, param):
latex = JinjaTemplateCommand(
template=input["template"],
param={"gccontent_graphs": input["gccontent_graphs"],
"render_dump": output["latex"]})
template_dump(latex)