Merge branch 'asmsbugfixes2024' into 'master'

Asmsbugfixes2024

See merge request mass-spectrometry/corems!108

Author: corilo

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 2.0.8
+current_version = 2.0.9
 commit = False
 tag = False
 

README.md

@@ -50,7 +50,7 @@ CoreMS aims to provide
 
 ## Current Version
 
- `2.0.8`
+ `2.0.9`
 
 ***
 
@@ -323,7 +323,7 @@ UML (unified modeling language) diagrams for Direct Infusion FT-MS and GC-MS cla
 
 If you use CoreMS in your work, please use the following citation:
 
-Version [2.0.8 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.8), archived on Zenodo:  
+Version [2.0.9 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.9), archived on Zenodo:  
 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4641552.svg)](https://doi.org/10.5281/zenodo.4641552)
 

corems/__init__.py

@@ -1,5 +1,5 @@
 __author__ = 'Yuri E. Corilo'
-__version__ = '2.0.8'
+__version__ = '2.0.9'
 __doc__ = '''
 <div align="left">
 

corems/encapsulation/factory/processingSetting.py

@@ -63,16 +63,16 @@ def __post_init__(self):
         self.header_translate = {'m/z': Labels.mz, 
                                  'mOz': Labels.mz,
                                  'Mass': Labels.mz,
-                                 'Resolving Power': 'Resolving Power',
+                                 'Resolving Power': Labels.rp,
                                  'Res.': Labels.rp,
+                                 'resolution': Labels.rp,
                                  'Intensity': Labels.abundance,
                                  'I': Labels.abundance,
                                  'Abundance': Labels.abundance,
+                                 'abs_abu': Labels.abundance,
                                  'Signal/Noise': Labels.s2n,
                                  'S/N': Labels.s2n,
-                                 'abs_abu': Labels.abundance,
-                                 'sn': Labels.s2n,
-                                 'resolution': Labels.rp}
+                                 'sn': Labels.s2n}
 
     def add_mz_label(self, label):
         """Add a label to the header_translate dictionary to be translated to the corems label for mz."""

corems/mass_spectra/factory/LC_Temp.py

@@ -10,14 +10,17 @@ class TIC_Data:
     Time: [floats]
         list of retention times
     TIC: [floats]
-        total ion chromatogram
+        total ion current [chromatogram]
+    BPC: [floats]
+        base peak [chromatogram]
     Apexes: [int]    
         original thermo apex scan number after peak picking 
      '''
 
      scans : List[int] = field(default_factory=list)
      time : List[float] = field(default_factory=list)
      tic : List[float] = field(default_factory=list)
+     bpc : List[float] = field(default_factory=list)
      apexes : List[int] = field(default_factory=list)
 
 @dataclass

corems/mass_spectra/input/rawFileReader.py

@@ -503,9 +503,15 @@ def func(evt):
             # plt.show()
 
     def get_tic(
-        self, ms_type="MS !d", peak_detection=True, smooth=True, plot=False, ax=None
+        self, ms_type="MS !d", peak_detection=True, smooth=True, plot=False, ax=None,trace_type='TIC',
     ) -> Tuple[TIC_Data, axes.Axes]:
-        """ms_type: str ('MS', MS2')
+        """ms_type: str ('MS !d', 'MS2', None)
+            if you use None you get all scans.
+        peak_detection: bool
+        smooth: bool
+        plot: bool
+        ax: matplotlib axis object
+        trace_type: str ('TIC','BPC')
 
         returns:
             chroma: dict
@@ -520,9 +526,16 @@ def get_tic(
                 original thermo apex scan number after peak picking
             }
         """
-
-        settings = ChromatogramTraceSettings(TraceType.TIC)
-        settings.Filter = ms_type
+        if trace_type == 'TIC':
+            settings = ChromatogramTraceSettings(TraceType.TIC)
+        elif trace_type == 'BPC':
+            settings = ChromatogramTraceSettings(TraceType.BasePeak)
+        else:
+            print(f'{trace_type} undefined')
+        if ms_type == "all":
+            settings.Filter = None
+        else:
+            settings.Filter = ms_type
 
         chroma_settings = IChromatogramSettings(settings)
 
@@ -532,7 +545,7 @@ def get_tic(
 
         trace = ChromatogramSignal.FromChromatogramData(data)
 
-        data = TIC_Data(time=[], scans=[], tic=[], apexes=[])
+        data = TIC_Data(time=[], scans=[], tic=[], bpc=[], apexes=[])
 
         if trace[0].Length > 0:
             for i in range(trace[0].Length):
@@ -564,7 +577,7 @@ def get_tic(
                     ax = plt.gca()
                     # fig, ax = plt.subplots(figsize=(6, 3))
 
-                ax.plot(data.time, data.tic, label=" TIC")
+                ax.plot(data.time, data.tic, label=trace_type)
                 ax.set_xlabel("Time (min)")
                 ax.set_ylabel("a.u.")
                 if peak_detection:
@@ -578,8 +591,13 @@ def get_tic(
                         )
 
                 # plt.show()
+                if trace_type == 'BPC':
+                    data.bpc = data.tic
+                    data.tic = []
                 return data, ax
-
+            if trace_type == 'BPC':
+                data.bpc = data.tic
+                data.tic = []
             return data, None
 
         else:

corems/mass_spectrum/calc/Calibration.py

@@ -381,13 +381,15 @@ def recalibrate_mass_spectrum(self, cal_peaks_mz : list[float], cal_refs_mz : li
             if self.mzsegment:
                 # Recombine the mass domains
                 mz_domain = np.concatenate([mz_domain,mz_exp_peaks_unchanged])
-                mz_profile_calc = np.concatenate([mz_profile_calc,mz_exp_profile_unchanged])
-                # Sort them 
                 mz_domain.sort()
-                mz_profile_calc.sort()
+                if not self.mass_spectrum.is_centroid:
+                    mz_profile_calc = np.concatenate([mz_profile_calc,mz_exp_profile_unchanged])
+                    mz_profile_calc.sort()
+                # Sort them 
                 if mz_exp_peaks[0] > mz_exp_peaks[1]: #If originally descending mass order
                     mz_domain = mz_domain[::-1]
-                    mz_profile_calc = mz_profile_calc[::-1]
+                    if not self.mass_spectrum.is_centroid:
+                        mz_profile_calc = mz_profile_calc[::-1]
 
             self.mass_spectrum.mz_cal = mz_domain
             if not self.mass_spectrum.is_centroid:

corems/mass_spectrum/calc/PeakPicking.py

@@ -453,7 +453,10 @@ def get_threshold(self, intes):
         elif noise_threshold_method == 'signal_noise':
 
             abundance_threshold = self.settings.noise_threshold_min_s2n
-            factor = self.baseline_noise_std
+            if self.is_centroid:
+                factor = 1
+            else:
+                factor = self.baseline_noise_std
 
         elif noise_threshold_method == "relative_abundance":
 

corems/ms_peak/calc/MSPeakCalc.py

@@ -27,9 +27,9 @@ class MSPeakCalculation:
         The parent MSParent object associated with the MSPeakCalculation object.
     mz_exp : float
         The experimental m/z value of the peak.
-    start_scan : int
+    peak_left_index : int
         The start scan index of the peak.
-    final_scan : int
+    peak_right_index : int
         The final scan index of the peak.
     resolving_power : float
         The resolving power of the peak.
@@ -136,11 +136,10 @@ def calc_area(self):
         float
             peak area
         """
-        #TODO throughout change final_scan and start_scan when the MSPeakClasses 
-        if self.final_scan > self.start_scan:
+        if self.peak_right_index > self.peak_left_index:
 
-            yy = self._ms_parent.abundance_profile[self.start_scan:self.final_scan]
-            xx = self._ms_parent.mz_exp_profile[self.start_scan:self.final_scan]
+            yy = self._ms_parent.abundance_profile[self.peak_left_index:self.peak_right_index]
+            xx = self._ms_parent.mz_exp_profile[self.peak_left_index:self.peak_right_index]
             # check if the axis is high to low m/z or not. if its MSFromFreq its high mz first, if its from Profile, its low mz first
             if xx[0] > xx[-1]:
                 xx = flip(xx)    
@@ -182,8 +181,8 @@ def fit_peak(self,mz_extend=6, delta_rp = 0, model='Gaussian'):
         mz_extend here extends the x-axis domain so that we have sufficient points either side of the apex to fit.
         Takes about 10ms per peak
         """
-        start_index = self.start_scan - mz_extend  if not self.start_scan == 0 else 0
-        final_index = self.final_scan + mz_extend  if not self.final_scan == len(self._ms_parent.mz_exp_profile) else self.final_scan
+        start_index = self.peak_left_index - mz_extend  if not self.peak_left_index == 0 else 0
+        final_index = self.peak_right_index + mz_extend  if not self.peak_right_index == len(self._ms_parent.mz_exp_profile) else self.peak_right_index
 
         # check if MSPeak contains the resolving power info
         if self.resolving_power:
@@ -385,8 +384,8 @@ def fit_peak_pso(self, mz_extend : int=6, upsample_multiplier : int=5):
             # Thermo data is noise reduced by also noise subtracted, so starts at 0
             # Absorption mode/phased data will have positive and negative components and may not be baseline corrected
 
-        start_index = self.start_scan - mz_extend  if not self.start_scan == 0 else 0
-        final_index = self.final_scan + mz_extend  if not self.final_scan == len(self._ms_parent.mz_exp_profile) else self.final_scan
+        start_index = self.peak_left_index - mz_extend  if not self.peak_left_index == 0 else 0
+        final_index = self.peak_right_index + mz_extend  if not self.peak_right_index == len(self._ms_parent.mz_exp_profile) else self.peak_right_index
 
         # check if MSPeak contains the resolving power info
         if self.resolving_power:
@@ -649,8 +648,8 @@ def get_mz_domain(self, oversample_multiplier, mz_overlay):
             x-axis domain for fit
         
         """
-        start_index = self.start_scan - mz_overlay  if not self.start_scan == 0 else 0
-        final_index = self.final_scan + mz_overlay  if not self.final_scan == len(self._ms_parent.mz_exp_profile) else self.final_scan
+        start_index = self.peak_left_index - mz_overlay  if not self.peak_left_index == 0 else 0
+        final_index = self.peak_right_index + mz_overlay  if not self.peak_right_index == len(self._ms_parent.mz_exp_profile) else self.peak_right_index
 
         if oversample_multiplier == 1:
 

corems/ms_peak/factory/MSPeakClasses.py

@@ -79,10 +79,9 @@ def __init__(
         self.resolving_power = float(resolving_power)
         self.signal_to_noise = float(signal_to_noise)
         # profile indexes
-        #TODO fix these names from 'scan' to be more logical about peak indexes.
-        self.start_scan = int(indexes[0])
-        self.apex_scan = int(indexes[1])
-        self.final_scan = int(indexes[2])
+        self.peak_left_index = int(indexes[0])
+        self.peak_apex_index = int(indexes[1])
+        self.peak_right_index = int(indexes[2])
 
         # mass spec obj index
         self.index = int(index)
@@ -318,15 +317,15 @@ def plot(
 
             if ax is None:
                 ax = plt.gca()
-            x = self._ms_parent.mz_exp_profile[self.start_scan : self.final_scan]
-            y = self._ms_parent.abundance_profile[self.start_scan : self.final_scan]
+            x = self._ms_parent.mz_exp_profile[self.peak_left_index : self.peak_right_index]
+            y = self._ms_parent.abundance_profile[self.peak_left_index : self.peak_right_index]
 
             ax.plot(x, y, color=color, label="Data")
             ax.set(xlabel="m/z", ylabel="abundance")
             if derivative and not self._ms_parent.is_centroid:
                 dy = sp.derivate(
                     self._ms_parent.abundance_profile[
-                        self.start_index : self.final_index + 1
+                        self.peak_left_index : self.peak_right_index + 1
                     ]
                 )
                 ax.plot(x, dy, c=deriv_color)