Merge pull request #80 from michaelmarty/v3

V3

PublicScripts/DIA-PTCR/IL22/glycan_assigner_brute_force.py

@@ -6,23 +6,24 @@
 import pandas as pd
 from unidec.modules.matchtools import *
 
+# Idea do this same thing with other omics data (lipidomics, metabolomics, etc.)
 
 # Set the directory and engine
 os.chdir("D:\\Data\\Luis Genentech")
 eng = engine.UniDec()
 
 # Set and load the peak file
 pfile = "20220113162114FcFusionProtein_SA15_20uScans_5500_7000mz_peaks.txt"
-#pfile = "20220113144226FcFusionProtein_SA8_20uScans_peaks.txt"
-#pfile = "211029_Wendy_Isle22FC_4_warmup_PTR2_peaks.txt"
+# pfile = "20220113144226FcFusionProtein_SA8_20uScans_peaks.txt"
+# pfile = "211029_Wendy_Isle22FC_4_warmup_PTR2_peaks.txt"
 eng.load_peaks(pfile)
 
 # Set and load the glycan file
-#gfile = "SA15_Trypsin_glycan_list_abridged.csv"
-#gfile = "IL22_SA8_tryp_glycan_list_abridged.csv"
-#gfile = "IL22_SA4_tryp_glycan_list_abridged.csv"
-#gfile = "IL22_Tryp\\IL22_SA4_tryp_glycan_list_4thsite.csv"
-#gfile = "IL22_Tryp\\IL22_SA8_tryp_glycan_list_4thsite.csv"
+# gfile = "SA15_Trypsin_glycan_list_abridged.csv"
+# gfile = "IL22_SA8_tryp_glycan_list_abridged.csv"
+# gfile = "IL22_SA4_tryp_glycan_list_abridged.csv"
+# gfile = "IL22_Tryp\\IL22_SA4_tryp_glycan_list_4thsite.csv"
+# gfile = "IL22_Tryp\\IL22_SA8_tryp_glycan_list_4thsite.csv"
 gfile = "IL22_Tryp\\IL22_SA15_tryp_glycan_list_4thsite.csv"
 gdf = pd.read_csv(gfile)
 print(gdf.keys())
@@ -35,7 +36,7 @@
 sites = ["S1", "S1", "S2", "S2", "S3", "S3", "S4", "S4"]
 
 st = time.perf_counter()
-probs_cutoff=1
+probs_cutoff = 1
 # Brute force calculate all possible combinations of glycans in the list
 indexes, masses, probs, glycans = get_sitematch_list(gdf, sites=sites, probs_cutoff=probs_cutoff)
 
@@ -50,9 +51,8 @@
 plt.savefig(gfile[:-4]+"TheoreticalMassBruteForce"+str(probs_cutoff)+".pdf")
 plt.show()'''
 
-
 # Open the output file
-outfile = gfile[:-4] + "_matches_brute_force"+str(probs_cutoff)+".xlsx"
+outfile = gfile[:-4] + "_matches_brute_force" + str(probs_cutoff) + ".xlsx"
 with pd.ExcelWriter(outfile) as writer:
     # Loop through all peaks
     for mass in eng.pks.masses:

build.bat

@@ -6,7 +6,7 @@ rem build docker and commit
 rem build wheel, test, and commit
 rem python -m build -o .\distpypi
 rem python -m twine upload --repository testpypi .\distpypi\* --config-file .pypirc (check that old wheels are deleted)
-rem update docs with .\unidec_docs\make.bat html
+rem update docs with .\unidec_doc\make.bat html
 rem paste docs into UniDecDocumentation and push to git
 
 echo "Building"

readme.md

@@ -191,9 +191,27 @@ Of course, using the pre-compiled version means you don't need to know Python at
 
 ## Change Log
 
+v.6.0.1
+
+*Added Noise Removal Tool* to UniDec and UniDecCD. This allows you to select specific noise regions (common in UHMR data) and set them to 0. Try Tools > Select Noise Peaks and the checking "Remove Noise Peaks" in the Advanced Data Processing Parameters.
+
+UPP Changes: 
+* Added "Config m/z Peak FWHM", "Config m/z Peak Shape", and "Config Sample Mass Every" parameters. If "Config m/z Peak FWHM" is specified as a float or integer, it will use that and skip the automatic peak width determination.
+* Enabled relative paths. 
+* Added "All" or "None" keywords on "Apply Fixed Mods" and "Disulfides Oxidized." 
+* Added "Config File" keyword to load a specific config file.
+* More tolerant of nans and different file extensions
+* Added ability to select files to load to UPP.
+* Added "Global Fixed Mod" to apply the same float value to each pair.
+* Special Bispecific Antibody Pairing Calculations (see Help File)
+* Fixex issues bugs with use_converted, clear all, and resetting the config.
+
+Fixed major bugs with 2D zooming and plotting. 
+
 v.6.0.0
 
-Major changes to code structure to enable PyPI distribution. Changed to more conventional Python package structure with unidec top directory. Renamed unidec_modules to modeuls, unidec_src to src, and unidec_bin to bin. Renamed some top level windows and moved all to main folder. For example, unidectools.py has been moved from modules to the top level and renamed as tools.py, and unidec.py has been renamed as engine.py. 
+Major changes to code structure to enable PyPI distribution. Changed to more conventional Python package structure with unidec top directory. Renamed unidec_modules to modules, unidec_src to src, and unidec_bin to bin. Renamed some top level windows and moved all to main folder. For example, unidectools.py has been moved from modules to the top level and renamed as tools.py, and unidec.py has been renamed as engine.py. The good news is that you can now do `pip install unidec` and `python -m unidec.Launcher` to run UniDec from the command line.
+
 
 Improved command line tools. Added -o option for file output in unidec. Included new entry points and smoothed out command line interface. Now you can use unidec to lanuch python -m unidec in the scripts folder. Similarly, gunidec will launch python -m unidec.Launcher. If you have Python and the scripts folder configured in your system path, command line tools will be much easier to use. 
 

unidec/Launcher.py

@@ -100,7 +100,7 @@ def __init__(self, parent):
         button7 = wx.Button(panel, -1, "UltraMeta Data Collector\n\nVisualize Multiple HDF5 Data Sets\nFit Trends")
         button8 = wx.Button(panel, -1, "UniChrom\n\nDeconvolution of Chromatograms\nUniDec for LC/MS Data")
         button9 = wx.Button(panel, -1, "UniDecCD\n\nDeconvolution of Charge Detection MS\nUniDec for CD-MS Data")
-        button10 = wx.Button(panel, -1, "UPP\n\nUniDec Pharama Pipeline\nBatch Processing Workflow")
+        button10 = wx.Button(panel, -1, "UPP\n\nUniDec Processing Pipeline\nBatch Processing Workflow")
         html = wx.html.HtmlWindow(panel, -1, size=(390, 310))
         pathtofile = os.path.dirname(os.path.abspath(__file__))
         self.imagepath = self.eng.config.toplogofile

unidec/UPP.py

@@ -165,6 +165,15 @@ def __init__(self, nrows=2, ncolumns=2, title="UniDec Processing Pipeline"):
         # Save File Menu
         save_file_menu_item = menu.Append(wx.ID_ANY, "Save File", "Save a CSV or Excel file")
         self.Bind(wx.EVT_MENU, self.on_save_file, save_file_menu_item)
+        menu.AppendSeparator()
+
+        # Add Files Menu
+        add_files_menu_item = menu.Append(wx.ID_ANY, "Add Data Files", "Add Data Files")
+        self.Bind(wx.EVT_MENU, self.on_add_files, add_files_menu_item)
+
+        # Clear everything on the panel
+        clear_everything_menu_item = menu.Append(wx.ID_ANY, "Clear All", "Clear Everything")
+        self.Bind(wx.EVT_MENU, self.clear_all, clear_everything_menu_item)
 
         help_menu = wx.Menu()
         # Open File Menu
@@ -315,9 +324,16 @@ def on_run_selected(self, event=None, rows=None):
         if not self.hide_col_flag:
             self.on_hide_columns()
 
+    def clear_all(self, event=None):
+        self.ss.delete_all()
+        self.ss.set_col_headers(["Sample name", "Data Directory"])
+
     def load_file(self, filename):
         print("Loading File:", filename)
-        self.ss.delete_all()
+        try:
+            self.ss.delete_all()
+        except Exception:
+            pass
         self.bpeng.top_dir = os.path.dirname(filename)
         df = file_to_df(filename)
         self.ss.set_df(df)
@@ -405,6 +421,46 @@ def open_unidec(self, row):
                 app.after_pick_peaks()
             app.start()
 
+    def on_add_files(self, event=None):
+
+        wildcard = "CSV or Excel files (*.csv; *.xlsx; *.xls)|*.csv; *.xlsx; *.xls|CSV files (*.csv)|*.csv|Excel files (*.xlsx; *.xls)|*.xlsx; *.xls"
+        wildcard = "Any files (*.*) |*.*| " \
+                   "Known file types (*.raw; *.d; *.mzML; *.mzXML; *.txt; *.csv; *.dat; *.npz)|" \
+                   "*.raw; *.d; *.mzML; *.mzXML; *.txt; *.csv; *.dat; *.npz|" \
+                   "Thermo RAW files (*.raw)|*.raw|" \
+                   "Agilent D files (*.d)|*.d|" \
+                   "mzML files (*.mzML)|*.mzML|" \
+                   "mzXML files (*.mzXML)|*.mzXML|" \
+                   "Text files (*.txt)|*.txt|" \
+                   "CSV files (*.csv)|*.csv|" \
+                   "Dat files (*.dat)|*.dat|" \
+                   "NPZ files (*.npz)|*.npz"
+
+        # Create a file selection dialog
+        with wx.FileDialog(self, "Select Files to Add",
+                           wildcard=wildcard,
+                           style=wx.FD_OPEN | wx.FD_FILE_MUST_EXIST | wx.FD_MULTIPLE) as fileDialog:
+            # Show the dialog and retrieve the user response. If it is the OK response,
+            # process the data.
+
+            if fileDialog.ShowModal() == wx.ID_CANCEL:
+                return
+            # Proceed loading the file chosen by the user
+            paths = fileDialog.GetPaths()
+            self.add_files(paths)
+
+    def add_files(self, paths):
+        print("Adding Files:", paths)
+        self.get_from_gui()
+        # Add paths list to the datafram in the "Sample name" column
+        sample_names = [os.path.basename(path) for path in paths]
+        data_dir = [os.path.dirname(path) for path in paths]
+        newdf = pd.DataFrame({"Sample name": sample_names, "Data Directory": data_dir})
+        self.bpeng.rundf = pd.concat([self.bpeng.rundf, newdf], ignore_index=True)
+
+        self.ss.set_df(self.bpeng.rundf)
+        self.reset_hidden_columns()
+
     def on_hide_columns(self, event=None, reset=False):
         columns_to_hide = ["Tolerance", "File", "Time", "Config", "Sequence", "Directory", "Matches"]
         if not self.hide_col_flag and not reset:
@@ -457,17 +513,19 @@ def on_exit(self, event=None):
 if __name__ == "__main__":
     app = wx.App()
     frame = UPPApp()
-    frame.usedeconbox.SetValue(False)
+    frame.usedeconbox.SetValue(True)
     path = "C:\\Data\\Wilson_Genentech\\sequences_short.xlsx"
+    path = "C:\\Data\\Wilson_Genentech\\BsAb\\BsAb test short.xlsx"
 
     # frame.on_help_page()
     # exit()
-    if True:
+    if False:
         frame.load_file(path)
         # frame.set_dir_tet_box("C:\\Data\\Wilson_Genentech\\Data")
         # print(df)
-        frame.on_run()
+        # frame.on_run()
         # frame.on_run_selected(rows=[1])
         # frame.on_run_selected(rows=[0])
+        # frame.on_add_files()
 
     app.MainLoop()