def test_logger():
import pytest
from mspypeline.helpers import get_logger
from logging import Logger
assert isinstance(get_logger("test", "warning"), Logger)
assert isinstance(get_logger(loglevel=10), Logger)
with pytest.warns(RuntimeWarning) as record:
assert isinstance(get_logger(loglevel="asd"), Logger)
assert len(record) == 1
def __init__(self,
input_scale: str = "log2",
output_scale: str = "normal",
col_name_prefix: Optional[str] = None,
loglevel: int = logging.DEBUG,
**kwargs):
"""
Abstract base class for Normalizers. Derived normalizers should implement the :meth:`fit` and :meth:`transform`.
Parameters
----------
input_scale
Scale of the input data. Either normal or log2
output_scale
Scale of the output data. Either normal or log2
col_name_prefix
If not None the prefix is added to each column name
loglevel
loglevel of the logger
kwargs
accepts kwargs
"""
self.loglevel = loglevel
self.logger = get_logger(self.__class__.__name__, self.loglevel)
allowed_scales = ("log2", "normal")
if input_scale not in allowed_scales:
raise ValueError("input_scale should be one of: " +
", ".join(allowed_scales))
if output_scale not in allowed_scales:
raise ValueError("out_scale should be one of: " +
", ".join(allowed_scales))
self.input_scale = input_scale
self.output_scale = output_scale
self.col_name_prefix = col_name_prefix
def __init__(self,
dir_: str,
file_path_yml: Optional[str] = None,
loglevel=logging.DEBUG):
self.logger = get_logger(self.__class__.__name__, loglevel=loglevel)
# create a yaml file reader
self.yaml = YAML()
# self.yaml.indent(mapping=2, sequence=4, offset=2)
self.yaml.indent(offset=2)
self.yaml.default_flow_style = False
self.yaml.width = 4096
# attributes that change upon changing the starting dir
self.configs = {}
self.reader_data = {}
self.interesting_proteins, self.go_analysis_gene_names = None, None
# properties
self._start_dir = None
self._file_path_yaml = None
# set the specified dirs
self.start_dir = dir_
if file_path_yml is not None:
self.file_path_yaml = file_path_yml
def __init__(self, start_dir: str, reader_config: dict, loglevel: int = logging.DEBUG):
"""
Parameters
----------
start_dir
location where the directory/txt folder to the data can be found.
reader_config
mapping of the file reader configuration (as e.g. given in the config.yml file)
loglevel
level of the logger
"""
self.full_data: DataDict = DataDict(data_source=self)
self.start_dir: str = start_dir
self.reader_config: dict = reader_config
self.logger: Logger = get_logger(self.__class__.__name__, loglevel)
# log which files will be read
self.logger.info("Required files: %s", self.required_files)
if not reader_config:
self.logger.warning("Empty configs")
else:
self.logger.debug("Got configs: %s", self.reader_config)
if start_dir is None:
raise ValueError("Invalid starting dir")
def __init__(self,
start_dir: str,
reader_config: dict,
loglevel=logging.DEBUG):
self.full_data = DataDict(data_source=self)
self.start_dir = start_dir
self.reader_config = reader_config
self.logger = get_logger(self.__class__.__name__, loglevel)
# log which files will be read
self.logger.info("Required files: %s", self.required_files)
if not reader_config:
self.logger.warning("Empty configs")
else:
self.logger.debug("Got configs: %s", self.reader_config)
if start_dir is None:
raise ValueError("Invalid starting dir")
def __init__(self,
path: str,
file_path_yml: Optional[str] = None,
loglevel=logging.DEBUG):
"""
Parameters
----------
path
location where the directory/txt folder to the data can be found.
file_path_yml
path to the yaml config file
loglevel
level of the logger
"""
self.logger = get_logger(self.__class__.__name__, loglevel=loglevel)
# create a yaml file reader
self.yaml = YAML()
self.yaml.indent(mapping=2, sequence=4, offset=2)
# self.yaml.indent(offset=2)
self.yaml.default_flow_style = False
self.yaml.width = 4096
# attributes that change upon changing the starting dir
#: configurations for the run. also saved configurations for the reader under the respective reader name
self.configs = {}
self.reader_data = {}
self.interesting_proteins, self.go_analysis_gene_names = None, None
# properties
self._start_dir = None
self._file_path_yaml = None
# list to store all selectable terms; custom and provided
self.list_full_gos = []
self.list_full_pathways = []
# set the specified dirs
self.start_dir = path
if file_path_yml is not None:
self.file_path_yaml = file_path_yml
def __setstate__(self, state):
self.__dict__ = state
self.logger = get_logger(self.__class__.__name__, self.loglevel)
from typing import Optional, Dict, Tuple, Iterator, Union, Iterable, Sized, Callable
import pandas as pd
from collections import defaultdict as ddict
from itertools import combinations
from collections import deque
import numpy as np
from matplotlib.lines import Line2D
import os
from mspypeline.helpers import get_logger
logger = get_logger(str(os.path.basename(__file__).split(".")[0]))
def get_number_rows_cols_for_fig(obj: Union[int, Sized]) -> Tuple[int, int]:
if isinstance(obj, Sized):
obj = len(obj)
n_rows, n_cols = 0, 0
while n_rows * n_cols < obj:
if n_rows <= n_cols:
n_rows += 1
else:
n_cols += 1
return n_rows, n_cols
def fill_dict(d: dict, s: str, s_split=None):
if s_split is None:
s_split = s.split("_")
if len(s_split) > 1:
fill_dict(d[s_split[0]], s, s_split[1:])
else:
def __init__(self,
file_dir,
yml_file=None,
loglevel=logging.DEBUG,
configs: dict = None):
"""
Parameters
----------
file_dir
location where the directory/txt folder to the data can be found.
yml_file
path to the yaml config file
loglevel
level of the logger
configs
mapping containing the configurations
"""
super().__init__()
self.yaml_options = ["default"]
self.reader_options = {
reader.name: reader
for reader in BaseReader.__subclasses__()
}
self.selected_reader = MQReader.MQReader
self.normalize_options = ["None"] + list(default_normalizers.keys())
self.mspinit = MSPInitializer(file_dir, yml_file, loglevel=loglevel)
self.logger = get_logger(self.__class__.__name__, loglevel=loglevel)
self.number_of_plots = 0
self.plot_settings = {}
self.intensity_options = ["lfq_log2", "raw_log2", "ibaq_log2"]
#,"lfq_normalized_log2", "raw_normalized_log2", "ibaq_normalized_log2]
self.title("mspypeline")
path_label = tk.Label(self,
text="Dir to analyze",
font="Helvetica 10 bold").grid(row=0, column=0)
yaml_label = tk.Label(self, text="Yaml file",
font="Helvetica 10 bold").grid(row=0, column=1)
reader_label = tk.Label(self,
text="File reader",
font="Helvetica 10 bold").grid(row=0, column=2)
self.dir_text = tk.StringVar(value=file_dir)
dir_button = tk.Button(
self,
textvariable=self.dir_text,
command=lambda: browsefunc(
filedialog.askdirectory,
self.dir_text,
fn_params={
"title":
"Please select a directory with MaxQuant result files"
}))
dir_button.grid(row=1, column=0)
self.yaml_text = tk.StringVar()
self.yaml_button = tk.OptionMenu(self, self.yaml_text,
*self.yaml_options)
self.yaml_button.grid(row=1, column=1)
self.reader_text = tk.StringVar(value="mqreader")
self.reader_button = tk.OptionMenu(self, self.reader_text,
*self.reader_options.keys())
self.reader_button.grid(row=1, column=2)
self.replicate_var = tk.IntVar(value=1)
replicate_button = tk.Checkbutton(
self,
text="Does the file have technical replicates?",
variable=self.replicate_var).grid(row=2, column=0)
go_proteins_label = tk.Label(self, text="Go analysis proteins").grid(
row=3, column=0)
experiments_label = tk.Label(self,
text="Pathway analysis").grid(row=3,
column=1)
design_label = tk.Label(self, text="Replicate names").grid(row=3,
column=2)
self.go_term_list = tk.Listbox(self,
selectmode="multiple",
height=5,
width=len(
max(self.mspinit.list_full_gos,
key=len)))
self.go_term_list.configure(exportselection=False)
for x in self.mspinit.list_full_gos:
self.go_term_list.insert("end", x)
self.go_term_list.grid(row=4, column=0)
self.pathway_list = tk.Listbox(self,
selectmode="multiple",
height=5,
width=len(
max(self.mspinit.list_full_pathways,
key=len)))
self.pathway_list.configure(exportselection=False)
for x in self.mspinit.list_full_pathways:
self.pathway_list.insert("end", x)
self.pathway_list.grid(row=4, column=1)
self.experiments_list = tk.Listbox(self, height=5)
self.experiments_list.grid(row=4, column=2)
report_button = tk.Button(self,
text="Create Report",
command=lambda: self.report_button())
report_button.grid(row=5, column=0)
plot_label = tk.Label(self, text="Which plots should be created").grid(
row=6, column=0)
intensity_label = tk.Label(self, text="Intensities").grid(row=6,
column=1)
levels_label = tk.Label(self, text="Levels").grid(row=6, column=2)
self.heading_length = 7
tk.Label(self, text="Normalization plots",
font="Helvetica 10 bold").grid(row=self.heading_length +
self.number_of_plots,
column=0)
self.number_of_plots += 1
self.plot_row("Normalization overview",
"normalization_overview_all_normalizers")
self.plot_row("Heatmap overview", "heatmap_overview_all_normalizers")
tk.Label(self,
text="Choose a Normalization Method:",
font="Helvetica 10 bold").grid(row=self.heading_length +
self.number_of_plots,
column=1)
self.number_of_plots += 1
self.plot_intermediate_row("Choose a Normalization Method")
tk.Label(self,
text="Outlier detection / Comparisons",
font="Helvetica 10 bold").grid(row=self.heading_length +
self.number_of_plots,
column=0)
self.number_of_plots += 1
self.plot_row("Detection counts", "detection_counts")
self.plot_row("Number of detected proteins",
"detected_proteins_per_replicate")
self.plot_row("Venn diagrams", "venn_results")
self.plot_row("Group diagrams", "venn_groups")
self.plot_row("PCA overview", "pca_overview")
self.plot_row("Intensity histogram", "intensity_histograms")
self.plot_row("Relative std", "relative_std")
self.plot_row("Scatter replicates", "scatter_replicates")
self.plot_row("Experiment comparison", "experiment_comparison")
self.plot_row("Rank", "rank")
tk.Label(self, text="Statistical inference",
font="Helvetica 10 bold").grid(row=self.heading_length +
self.number_of_plots,
column=0)
self.number_of_plots += 1
self.plot_row("Pathway Analysis", "pathway_analysis")
#self.plot_row("Pathway Timecourse", "pathway_timecourse")
self.plot_row("Go analysis", "go_analysis")
self.plot_row("Volcano plot (R)", "r_volcano")
self.p_val_var = tk.IntVar(value=1)
pval_button = tk.Checkbutton(
self, text="Use adjusted p value", variable=self.p_val_var).grid(
row=self.heading_length + self.number_of_plots, column=1)
total_length = self.heading_length + self.number_of_plots
update_button = tk.Button(self,
text="Update",
command=lambda: self.update_button())
update_button.grid(row=total_length + 1, column=1)
start_button = tk.Button(self,
text="Start",
command=lambda: self.start_button())
start_button.grid(row=total_length + 1, column=2)
self.running_text = tk.StringVar(value="Please press Start")
self.running_label = tk.Label(
self, textvariable=self.running_text).grid(row=total_length + 2,
column=2)
# add all tracing to the variables
self.dir_text.trace("w", self.dir_setter)
self.yaml_text.trace("w", self.yaml_path_setter)
self.reader_text.trace("w", self.reader_setter)
# make the GUI resizable
self.columnconfigure(0, weight=1)
self.rowconfigure(0, weight=1)
self.mspinit.configs.update(configs)
self.update_yaml_options()
self.mainloop()