ms_to_peakforest_it: server.py comparison

comparison server.py @ 1:7e3085fc60c1 draft default tip

master branch Updating

author	lain
date	Wed, 30 Aug 2023 14:21:18 +0000
parents	b58b229c4cbf
children

comparison

equal deleted inserted replaced

-:b58b229c4cbf
+:7e3085fc60c1
 "absolute_intensity": "abs_intensity",
 "relative_intensity": "rel_intensity",
 "theo_mass": "",
 "delta_ppm": "ppm",
 "rdbequiv": "",
-"composition": "",
+"composition": "fragment",
-"attribution": "fragment",
+"attribution": "composition",
 }
 MS_2_SNOOP_HEADER = {
 "name": str,
 "inchikey": str,
-"composition": str,
+# "composition": str,
+"composition": lambda *args:"",
 "fragment": str,
 "fragment_mz": str,
 "ppm": str,
 "fileid": str,
 "correlation": str,
-"abs_intensity": lambda x:float(x) * 100,
+"abs_intensity": lambda x:float(x), # * 100,
-"rel_intensity": lambda x:float(x) * 100,
+"rel_intensity": lambda x:float(x) * 100 if x != "" else "",
 "valid_corelation": str
 }
 class ConfigException(ValueError):
 help: Show this help
 optional:
 method: "default is {{ defaults.method }}"
 meta:
 author: Lain Pavot
-version: 1.1.0
+version: 1.2.0
 shortcuts:
 help: h
 ## will autogenerate -i for input and -m for method
 ---
 default parameters are searched in the "default" root section.
 config.placeholders[TAB_INDEX_PLACEHOLDER] = "1"
 config.placeholders[ACTIVE_TAB_PLACEHOLDER] = "active"
 config.placeholders[ADD_SPECTRUM_FORM] = ""
 config.placeholders[EMBED_JS_PLACEHOLDER] = ""
 config.placeholders[TAB_LIST_PLACEHOLDER] = ""
-config.placeholders["DEFAULT_MIN_MZ"] = "50"
+# config.placeholders["DEFAULT_MIN_MZ"] = "50"
-config.placeholders["DEFAULT_MAX_MZ"] = "500"
+# config.placeholders["DEFAULT_MAX_MZ"] = "500"
 config.placeholders["DEFAULT_RESOLUTION_LOW"] = ""
 config.placeholders["DEFAULT_RESOLUTION_HIGH"] = "selected=\"selected\""
 config.placeholders["DEFAULT_RESOLUTION_UNSET"] = ""
-config.placeholders["DEFAULT_MIN_RT"] = "0.9"
-config.placeholders["DEFAULT_MAX_RT"] = "1.4"
 return config
 def parse_parameters(config):
 """
 parses command line and checks provided values are acceptable/usable.
 raise ValueError(
 "Some errors occured during parameters extraction: \n"
 + '\n'.join(parameters.errors)
 )
+parameters.placeholders["DEFAULT_MIN_RT"] = str(arguments.rt_min)
+parameters.placeholders["DEFAULT_MAX_RT"] = str(arguments.rt_max)
 if arguments.sample_type == COMPOUND_MIX:
 parameters["form_template"] = os.path.join(
 parameters["root_dir"],
 parameters.templates.form_mix
 )
 parameters["meta_template"] = os.path.join(
 parameters["root_dir"],
 parameters.templates.main_mix
 )
-elif arguments.sample_type == COMPOUND_REF:
+else: # elif arguments.sample_type == COMPOUND_REF:
 parameters["form_template"] = os.path.join(
 parameters["root_dir"],
 parameters.templates.form_ref
 )
 parameters["meta_template"] = os.path.join(
 if arguments.method == "test":
 if arguments.spectrum_type == "LC_MS":
 arguments["method"] = "cf_pfem_urine_qtof"
 else:
 arguments["method"] = "cf_pfem_urine_method1_qtof-msms"
+arguments["method"] = "toulouse-metatoul-agromix__ft-esi__msms"
 if arguments["sample_type"] == COMPOUND_MIX:
 check_mix_compound_files(parameters)
 more_info_in_logs(parameters)
 return parameters
 numbarz = [
 list(map(int, os.path.basename(metadata).split("_", 1)[0].split("-")))
 for metadata in arguments.raw_metadata
 ]
 except ValueError:
-parameters.logger.error(
+## file does not start with `[0-9]+-[0-9]+_.*`: probably
-"Metadata/file names does not start with `[0-9]+-[0-9]+_.*` . "
+## a ms2snoop file.
-"This is necessary in the case of compounds mix."
+return
-)
+# parameters.logger.error(
-sys.exit(-1)
+#   "Metadata/file names does not start with `[0-9]+-[0-9]+_.*` . "
+#   "This is necessary in the case of compounds mix."
+# )
+# sys.exit(-1)
 runs, samples = zip(*numbarz)
 if not all(runs[0] == i for i in runs[1:]):
 parameters.logger.error(
 "Run numbers in metadata/file names are not identical. "
 "You mixed some files."
 for value in (
 ms_data["fragment_mz"],
 ms_data["abs_intensity"],
 ms_data["rel_intensity"],
 ms_data["ppm"],
+ms_data["fragment"],
 ms_data["composition"],
-ms_data["fragment"],
 str(ms_data["valid_corelation"] == "TRUE").lower(),
 "true" if ms_data.get("correlation") == "1" else "false"
 )
 )
 )
 """
 aggregates informations to form the peak table,
 adds the compound to the tab list,
 creates the js file for this tab
 """
-if len([x for x in ms_peak_table if x.split(", ")[7] == "\"true\""]) > 1:
+ignore_multiple_parent_ion(ms_peak_table)
-for i in range(len(ms_peak_table)):
+determine_min_max_mz(ms_peak_table)
-ms_peak_table[i] = ", ".join(
+guess_relative_intensities(ms_peak_table)
-ms_peak_table[i].split(", ")[:-1] + [", \"false\""]
+accept_all_fragments_if_all_false(ms_peak_table)
-)
 config.placeholders[MS_PEAK_VALUES_PLACEHOLDER] = f"""[
 {','.join('['+line+']' for line in ms_peak_table)}
 ]"""
 tab_list = fill_template(
 "tab_list_template",
 {TAB_INDEX_PLACEHOLDER: str(index)},
 )
 if index == 1:
 config.placeholders[ACTIVE_TAB_PLACEHOLDER] = ""
+def determine_min_max_mz(ms_peak_table):
+mz_list = [
+float(ms_peak_table[i].split(", ")[0].strip("\""))
+for i in range(len(ms_peak_table))
+]
+config.placeholders["DEFAULT_MIN_MZ"] = str(min(mz_list))
+config.placeholders["DEFAULT_MAX_MZ"] = str(max(mz_list))
+def guess_relative_intensities(ms_peak_table):
+if all(
+ms_peak_table[i].split(", ")[2].strip("\"") == ""
+for i in range(len(ms_peak_table))
+):
+absolute_intensities = [
+float(ms_peak_table[i].split(", ")[1].strip("\""))
+for i in range(len(ms_peak_table))
+]
+greatest = float(max(absolute_intensities))
+relative_intensities = [
+intensity / greatest * 100
+for intensity in absolute_intensities
+]
+replace_ms_table_value(ms_peak_table, 2, relative_intensities)
+def ignore_multiple_parent_ion(ms_peak_table):
+if len([
+None for x in ms_peak_table
+if x.split(", ")[7].strip("\"") == "true"
+]) > 1:
+## if more than one is the precursor, then none is the precursor
+replace_ms_table_value(ms_peak_table, 7, "\"false\"")
+def accept_all_fragments_if_all_false(ms_peak_table):
+if all(
+ms_peak_table[i].split(", ")[6].strip("\"") == "false"
+for i in range(len(ms_peak_table))
+):
+replace_ms_table_value(ms_peak_table, 6, "true")
+def replace_ms_table_value(ms_peak_table, index, value, sep=", "):
+length = len(ms_peak_table)
+if not isinstance(value, list):
+if isinstance(value, str):
+value = [value.join('""')] * length
+else:
+value = [str(value)] * length
+if not isinstance(value[0], str):
+value = [str(x) for x in value]
+count = ms_peak_table[0].count(sep)
+endindex = count - index
+neg_endindex = -endindex
+for i in range(length):
+ms_peak_table[i] = sep.join((
+*ms_peak_table[i].split(sep, index)[:index],
+value[i],
+*ms_peak_table[i].rsplit(sep, endindex)[neg_endindex:]
+))
 def fragnot_extractor(config, *line):
 """
 Fragnot processor - extracts one fragnot line of content and
 produces a uniformised output.
 """
 fragnot_data = {
 FRAGNOT_HEADER[header]: line[i].strip()
 for i, header in enumerate(FRAGNOT_HEADER)
 }
-fragnot_data["composition"] = "unknown"
+# fragnot_data["composition"] = "unknown"
 fragnot_data["valid_corelation"] = config.arguments.validation
 return fragnot_data
 def ms2snoop_extractor(config, *line):
 """
 if config.workdir.generate_in_tmp:
 gen_dir = config.workdir.tmp_dir
 else:
 gen_dir = tempfile.gettempdir()
 config.workdir.tmp_dir = gen_dir
-shutil.copy(os.path.join(config["root_dir"], "common.js"), gen_dir)
+shutil.copy(os.path.join(config["root_dir"], "src", "common.js"), gen_dir)
 config.logger.info(f"Outputs will be generated in {config.workdir.tmp_dir}")
 return gen_dir
 def get_hander_for(directory, config):
 """
 super().__init__(*args, **kwargs, directory=directory)
 def do_POST(self):
 content_length = int(self.headers.get("Content-Length"))
 json_bytes = self.rfile.read(content_length).decode("utf-8")
-json_list = json.loads(json_bytes)
+# json_list = json.loads(json_bytes)
-for i, obj in enumerate(json_list):
+# for i, obj in enumerate(json_list):
-print(obj)
+#   print(obj)
-if obj:
+#   if obj:
-config["json_result"][i] = obj
+#     config["json_result"][i] = obj
+json_obj = json.loads(json_bytes)
+config["json_result"][json_obj["index"]] = json_obj["object"]
 save_json(config)
 self.send_head()
 self.wfile.write(json_bytes.encode("utf-8"))
 return
 def run_server(config):
 """
 prepare and runs the server, with the handler for the given directory
 """
-ip, port = config.network.ip, config.network.port
+ip, port = config.arguments.ip, int(config.arguments.port)
 config.logger.debug(f"IP and port: {ip}:{port}")
 socketserver.TCPServer.allow_reuse_address = True
 config.logger.debug(f"Allow reuse adress.")
 handler = get_hander_for(config.workdir.tmp_dir, config)
 config.logger.debug(f"Created server handler for {config.workdir.tmp_dir}")
 logger.info("*bip* *bop*")
 logger.info("shutdown")
 logger.info("...")
 if __name__ == "__main__":
+print(os.listdir("test-data"))
+if not os.path.exists("config.yml"):
+shutil.copy("config.default.yml", "config.yml")
 base_config = parse_config()
 config = parse_parameters(base_config)
 """
 The config contains result of the parsed config file.
 """
 arguments = config.arguments
+if arguments.pid:
+print(arguments.pid)
+with open(arguments.pid, "w") as pid_file:
+pid_file.write(str(os.getpid()))
+atexit.register(lambda:os.unlink(arguments.pid))
 config.logger.info(f"Starting MS2PF from {os.getcwd()}")
 gen_dir = prepare_workplace(config)

Mercurial > repos > lain > ms_to_peakforest_it

comparison server.py @ 1:7e3085fc60c1 draft default tip