Merge pull request #99 from michaelmarty/v3

Version 7.0.2

.gitignore

@@ -27,7 +27,7 @@ TestSpectra
 default_conf.dat
 unidec_src/cfunction/x64
 unidec_src/cfunction/libmypfunc32.dll
-Scripts/MTM/unidec_tests.py
+Scripts/MTM/Old/unidec_tests.py
 pyinstaller_64.bat
 pyinstaller_64_dist.bat
 /Scripts/MTM/fft_test.py
@@ -36,7 +36,7 @@ todo.txt
 unidec/bin/Other_builds/
 unidec_src/Old
 test_GUI.py
-Scripts/MTM/test_UniDec.py
+Scripts/MTM/Old/test_UniDec.py
 unidec/metaunidec/test_MUD.py
 unidec/bin/CDCReaderOld.exe
 Scripts/MTM/Old/fft_test.py
@@ -268,4 +268,8 @@ hashing.py
 PublicScripts/MutantCycleAnalysis/Mutant Cycle Analysis/
 unidec/modules/gui_elements/UniDec.mplstyle
 .eggs/
+Dockerfile_isodec
+unidec/recent.txt
+unidec/src/UniDec/
+
 

Dockerfile

@@ -1,7 +1,7 @@
-FROM python:3.9-bullseye
+FROM python:3.11.9-bookworm
 
 # C dependencies
-RUN apt-get update && apt-get install -y libgtk-3-dev libwxgtk3.0-gtk3-dev libfftw3-dev hdf5-tools libhdf5-dev --no-install-recommends && rm -rf /var/lib/apt/lists/*
+RUN apt-get update && apt-get install -y libfftw3-dev hdf5-tools libhdf5-dev --no-install-recommends && rm -rf /var/lib/apt/lists/*
 
 # To Run GUI
 RUN pip install setuptools attrdict attrdict3 numpy pymzml networkx natsort h5py matplotlib scipy pyteomics mpld3 pandas plotly

GUniDec.spec

@@ -12,6 +12,7 @@ from PyInstaller import compat
 import matplotlib
 import sys
 import hashlib
+import shutil
 
 
 def hashfile(path):
@@ -159,6 +160,11 @@ coll = COLLECT(exe,
 path = "C:\\Python\\UniDec3\\dist\\UniDec_Windows\\GUI_UniDec.exe"
 import subprocess
 
+dst = "C:\\Python\\UniDec3\\dist\\UniDec_Windows\\obo"
+src = "C:\\Python\\UniDec3\\dist\\UniDec_Windows\\_internal\\obo"
+
+shutil.copytree(src, dst)
+
 print("Testing Software...", path)
 
 out = subprocess.call(path)

LICENSE

@@ -1,7 +1,7 @@
 UniDec License:
 
 Copyright (c) 2016, University of Oxford
-              2017-2023, University of Arizona
+              2017-2024, Arizona Board of Regents on behalf of the University of Arizona
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

readme.md

@@ -197,12 +197,24 @@ Of course, using the pre-compiled version means you don't need to know Python at
 
 v.7.0.2
 
+Improvements to UPP outputs. Fixed issue with reports getting overwritten if the same file is used in multiple rows with UPP. 
+
+Added new options in MetaUniDec for Average Charge State Plotting. Added exports of text files for fits and fitdata.
+
+Added new pre-import intensity filter for UCD, which should help with memory crashes on large data files.
+
+Fixed bug opening mzML files with new build.
+
+Fixed bug with smashflag on UPP.
+
 Fixed a few display and interface bugs on UCCD and UCD.
 
 Fixed Waters Data Conversion Wizard issue with Trapping Collision Energy (eV). Stopped it from closing by default when the conversion is initiated.
 
 Fixed bug with KD fitting on DataCollector. Fixed bug with UltraMeta. 
 
+Fixed bugs with UCD Thermo imports and with Thermo header information for resolution.
+
 v.7.0.1
 
 Continued development and tweaks to UniChromCD. Bug fixes and GUI improvements. Added multiplex spectrum cropping. New HT sequences.

unidec/DataCollector.py

@@ -559,7 +559,7 @@ def __init__(self, parent, title, config=None, pks=None, *args, **kwargs):
                 # self.on_run(0)
                 self.on_fitting()
             if True and platform.node() == 'MTM-VOSTRO':
-                path = "Z:\mtmarty\Data\Others\Miranda\collection2.json"
+                path = "Z:\\mtmarty\\Data\\Others\\Miranda\\collection2.json"
                 self.load(path)
             try:
                 # testdir = "C:\Python\unidec\unidec_src\unidec\\x64\Release"

unidec/IsoDec/__main__.py

@@ -0,0 +1,63 @@
+import sys
+import getopt
+import argparse
+import os
+import platform
+sys.path.append("..")
+
+if platform.system() == "Windows":
+    udpath = "C:\\Python\\UniDec3"
+elif platform.system() == "Linux":
+    udpath = "/home/u17/mtmarty/UniDec"
+
+sys.path.append(udpath)
+
+
+def main(*args, **kwargs):
+    print(sys.argv)
+    print("Running Command Line IsoDec")
+
+    try:
+        opts, args = getopt.getopt(sys.argv[1:], "f:o:", ["file=", "out="])
+    except getopt.GetoptError as e:
+        print("Error in Argv. Likely unknown option: ", sys.argv, e)
+        print("Known options: -f, -o")
+        return None
+
+    print("ARGS:", args)
+    print("KWARGS:", kwargs)
+    print("OPTS:", opts)
+    infile = None
+    outfile = None
+    if opts is not None:
+        for opt, arg in opts:
+            if opt in ("-f", "--file"):
+                infile = arg
+                print("Opening File:", infile)
+            if opt in ("-o", "--out"):
+                outfile = arg
+                print("Output File:", outfile)
+
+    if "train" in args:
+        from unidec.IsoDec.train import main
+        main()
+
+    if "generate" in args:
+        print("Generating Pkl Files")
+        if infile is None:
+            print("No Input File Specified")
+            return None
+        from unidec.IsoDec.trainingdata import process_file
+        process_file(infile)
+
+    if "generate_script" in args:
+        print("Generating Pkl Files")
+        directory = os.getcwd()
+        print("Directory:", directory)
+        from unidec.IsoDec.generate import generate_all
+        generate_all(directory)
+
+
+
+if __name__ == '__main__':
+    main()

unidec/IsoDec/c_interface.py

@@ -0,0 +1,138 @@
+import ctypes
+import os
+import numpy as np
+from unidec.IsoDec.match import MatchedPeak, MatchedCollection
+from unidec.modules.isotopetools import fast_calc_averagine_isotope_dist
+from unidec.IsoDec.plots import *
+import unidec.tools as ud
+
+example = np.array([[5.66785531e+02, 1.47770838e+06],
+                    [5.67057354e+02, 1.54980838e+06],
+                    [5.67507468e+02, 5.21600520e+07],
+                    [5.67708173e+02, 8.35557760e+07],
+                    [5.67908401e+02, 7.28264240e+07],
+                    [5.68060254e+02, 1.87337225e+06],
+                    [5.68108674e+02, 4.35435520e+07],
+                    [5.68239256e+02, 3.88155375e+06],
+                    [5.68309390e+02, 2.05468060e+07],
+                    [5.68509951e+02, 7.18109250e+06],
+                    [5.68707871e+02, 2.30373500e+06],
+                    [5.69150563e+02, 1.57598062e+06],
+                    [5.69243121e+02, 1.96390440e+07],
+                    [5.69334393e+02, 6.82677120e+07],
+                    [5.69425337e+02, 1.22867432e+08],
+                    [5.69516492e+02, 1.45702336e+08],
+                    [5.69607541e+02, 1.20801936e+08],
+                    [5.69698595e+02, 1.06786072e+08],
+                    [5.69789906e+02, 6.56232960e+07],
+                    [5.69881208e+02, 3.41013880e+07],
+                    [5.69972168e+02, 1.70930360e+07],
+                    [5.70063432e+02, 9.17621100e+06],
+                    [5.70699369e+02, 1.96462650e+06]])
+
+dllpath = "C:\\Python\\UniDec3\\unidec\\IsoDec\\src\\isodec\\x64\\Release\\isodeclib.dll"
+
+isodist = ctypes.c_float * 128
+matchedinds = ctypes.c_int * 32
+#print(isodist)
+class MPStruct(ctypes.Structure):
+    _fields_ = [('mz', ctypes.c_float),
+                ('z', ctypes.c_int),
+                ('monoiso', ctypes.c_float),
+                ('peakmass', ctypes.c_float),
+                ('avgmass', ctypes.c_float),
+                ('area', ctypes.c_float),
+                ('peakint', ctypes.c_float),
+                ('matchedindsiso', ctypes.c_int * 64),
+                ('matchedindsexp', ctypes.c_int * 64),
+                ('isomz', isodist),
+                ('isodist', isodist),
+                ('isomass', isodist),
+                ('startindex', ctypes.c_int),
+                ('endindex', ctypes.c_int),
+                ]
+
+
+class IsoDecWrapper:
+    def __init__(self, dllpath=dllpath, modelpath=b"C:\\Python\\UniDec3\\unidec\\IsoDec\\phase_model_2.bin"):
+        # void process_spectrum(const double* cmz, const double* cint, const int n, const char* fname, int* charge)
+        self.c_lib = ctypes.CDLL(dllpath)
+        self.c_lib.predict_charge.argtypes = [ctypes.POINTER(ctypes.c_float), ctypes.POINTER(ctypes.c_float),
+                                              ctypes.c_int, ctypes.c_char_p, ctypes.POINTER(ctypes.c_int)]
+
+        self.c_lib.process_spectrum.argtypes = [ctypes.POINTER(ctypes.c_float), ctypes.POINTER(ctypes.c_float),
+                                                ctypes.c_int, ctypes.c_char_p, ctypes.POINTER(MPStruct)]
+        self.modelpath = ctypes.c_char_p(modelpath)
+
+    def predict_charge(self, centroids):
+        cmz = centroids[:, 0].astype(np.float32)
+        cint = centroids[:, 1].astype(np.float32)
+        n = len(cmz)
+        charge = ctypes.c_int(0)
+        self.c_lib.predict_charge(cmz.ctypes.data_as(ctypes.POINTER(ctypes.c_float)),
+                                  cint.ctypes.data_as(ctypes.POINTER(ctypes.c_float)), n, self.modelpath,
+                                  ctypes.byref(charge))
+        print(charge.value)
+        return charge.value
+
+    def process_spectrum(self, centroids, pks=None, config=None):
+        #print("Running C Interface")
+        cmz = centroids[:, 0].astype(np.float32)
+        cint = centroids[:, 1].astype(np.float32)
+        n = len(cmz)
+        # print(n)
+        elems = (MPStruct * n)()
+        matchedpeaks = ctypes.cast(elems, ctypes.POINTER(MPStruct))
+        nmatched = self.c_lib.process_spectrum(cmz.ctypes.data_as(ctypes.POINTER(ctypes.c_float)),
+                                               cint.ctypes.data_as(ctypes.POINTER(ctypes.c_float)), n, self.modelpath,
+                                               matchedpeaks)
+        # print(nmatched)
+        if pks is None:
+            pks = MatchedCollection()
+        for p in matchedpeaks[:nmatched]:
+            if p.z == 0:
+                continue
+            pk = MatchedPeak(p.z, p.mz)
+            pk.monoiso = p.monoiso
+            pk.peakmass = p.peakmass
+            pk.avgmass = p.avgmass
+
+            if config is not None:
+                pk.scan = config.activescan
+                pk.ms_order = config.activescanorder
+                pk.rt = config.activescanrt
+
+            isodist = np.array(p.isodist)
+            isomz = np.array(p.isomz)
+            isomass = np.array(p.isomass)
+
+            b1 = isodist > np.amax(isodist) * 0.001
+            isodist = isodist[b1]
+            isomz = isomz[b1]
+            isomass = isomass[b1]
+            pk.matchedintensity = np.sum(isodist)
+            pk.isodist = np.transpose((isomz, isodist))
+            pk.massdist = np.transpose((isomass, isodist))
+
+            pk.startindex = p.startindex
+            pk.endindex = p.endindex
+
+            pk.isodist = fast_calc_averagine_isotope_dist(p.monoiso, p.z)
+            #pk.isodist[:,0] /= float(p.z)
+            pk.isodist[:,1] *= p.peakint
+            pks.add_peak(pk)
+            pks.add_pk_to_masses(pk, 10)
+        return pks
+
+
+if __name__ == "__main__":
+    filepath = "C:\\Data\\IsoNN\\test2.txt"
+    #filepath = "C:\\Data\\IsoNN\\test9.txt"
+    spectrum = np.loadtxt(filepath, skiprows=0)
+    #spectrum = ud.datachop(spectrum, 702, 708)
+
+    wrapper = IsoDecWrapper()
+    #wrapper.process_spectrum(spectrum)
+    pks = wrapper.process_spectrum(spectrum)
+    #exit()
+    plot_pks(pks, centroids=spectrum, show=True, title="C Interface")