def latex_bowtie(input, output, param):
json_dict = json_load(input["json"])
basic_map_table = []
for sam in json_dict["stat"]:
basic_map_table.append(
[
underline_to_space(sam),
json_dict["stat"][sam]["total_reads"],
json_dict["stat"][sam]["mappable_reads"],
json_dict["stat"][sam]["mappable_rate"],
]
)
latex = JinjaTemplateCommand(
name="mapping quality",
template=input["template"],
param={
"section_name": "bowtie",
"basic_map_table": basic_map_table,
"mappable_ratio_graph": json_dict["output"]["pdf"],
"render_dump": output["latex"],
},
)
template_dump(latex)
def latex_fastqc(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": json_dict["output"]["pdf"],
"fastqc_table": fastqc_summary,
"fastqc_graph": json_dict["output"]["pdf"],
'prefix_dataset_id': [ underline_to_space(i) for i in stat.keys() ],
"render_dump": output["latex"]})
template_dump(latex)
def stat_fastqc(input={"db": "", "fastqc_summaries": [], "template": ""},
output={"R": "", "json": "", "pdf": ""},
param={"ids": [], "id": ""}):
json_dict = {"stat": {}, "input": input, "output": output, "param": param}
stat = json_dict["stat"]
quality_medians = []
for a_summary, a_id in zip(input["fastqc_summaries"], param["ids"]):
parsed = _python_fastqc_parse(input=a_summary)
stat[a_id] = {}
stat[a_id]["median"] = parsed["median"]
stat[a_id]["cutoff"] = 25
stat[a_id]['judge'] = "Pass" if parsed["median"] > 25 else "Fail"
stat[a_id]["sequence_length"] = parsed["sequence_length"]
quality_medians.append(parsed["median"])
# 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
qc_db = sqlite3.connect(input["db"]).cursor()
qc_db.execute("SELECT median_quality FROM fastqc_info")
history_data = [float(i[0]) for i in qc_db.fetchall()]
fastqc_dist_r = JinjaTemplateCommand(
template=input["template"],
param={'historic_data': history_data,
'current_data': quality_medians,
'ids': [underline_to_space(i) for i in param["ids"]],
'cutoff': 25,
'main': 'Sequence Quality Score Cumulative Percentage',
'xlab': 'sequence quality score',
'ylab': 'fn(sequence quality score)',
"need_smooth_curve": True,
"pdf": output["pdf"],
"render_dump": output["R"]})
template_dump(fastqc_dist_r)
r_exec(fastqc_dist_r)
json_dump(json_dict)
def latex_macs2(input, output, param):
# TODO: qian work out the peaks_summary_result part
json_dict = json_load(input["json"])
summary = [underline_to_space(json_dict["param"]["id"]),
json_dict["stat"]["qvalue"],
json_dict["stat"]["totalpeak"],
json_dict["stat"]["peaksge10"],
json_dict["stat"]["shiftsize"]]
high_confident_latex = JinjaTemplateCommand(
name = "high confident latex",
template = input["template"],
param = {"section_name": "high_confident_peaks",
"peak_summary_table": summary,
"high_confident_peak_graph": json_dict["output"]["pdf"],
"render_dump": output["latex"]})
template_dump(high_confident_latex)
def _2space(id):
return underline_to_space(id)
