Merge pull request #26 from ZhixuNi/master

GUI scale, pymzML 2.2.5 and other fix
SysMedOs · Aug 6, 2019 · cb05357 · cb05357
2 parents 0abf9f2 + df174c0
commit cb05357
Show file tree

Hide file tree

Showing 10 changed files with 97 additions and 61 deletions.
diff --git a/ConfigurationFiles/3-Specific_ions.xlsx b/ConfigurationFiles/3-Specific_ions.xlsx
diff --git a/LibLipidHunter/Hunter_Core.py b/LibLipidHunter/Hunter_Core.py
@@ -1175,7 +1175,7 @@ def huntlipids(param_dct: dict, error_lst: list,
         gen_html_report(param_dct, output_df, lipid_info_img_lst)
     else:
         print('[WARNING] !!! User skip image generation !!!!!!')
-
+    print('Time', time.clock(), start_time)
     tot_run_time = time.clock() - start_time
 
     print('[STATUS] >>> >>> >>> FINISHED in %s sec <<< <<< <<<' % tot_run_time)

diff --git a/LibLipidHunter/IsotopeHunter.py b/LibLipidHunter/IsotopeHunter.py
@@ -167,7 +167,7 @@ def peak_top_checker(ms1_pr_mz, spec_df, core_count=1, ms1_precision=50e-6):
             top_obs_i = 0
             top_delta = 0
 
-        if pr_obs_i >= 0.75 * top_obs_i > 0:
+        if pr_obs_i * 1.5 >= top_obs_i > 0:
             peak_top = True
             # print(core_count,
             #       '[PASSED]MS1 PR m/z {pr} is peak top in +/- {delta} m/z, PR i {obs_i}, max i {max_i}'
@@ -374,7 +374,9 @@ def get_isotope_score(self, ms1_pr_mz, ms1_pr_i, formula, spec_df, core_count,
         if ms1_pr_i > max_pre_m_i or pseudo_pr_check == 0:
             elem_dct = self.get_elements(formula)
             mono_mz = self.get_mono_mz(elem_dct)
-            if abs((ms1_pr_mz - mono_mz)) <= ms1_precision * ms1_pr_mz:
+            pr_range_top, range_top_obs_i = self.peak_top_checker(ms1_pr_mz, spec_df, core_count=core_count,
+                                                                  ms1_precision=ms1_precision * 2.5)
+            if pr_range_top and abs((ms1_pr_mz - mono_mz)) <= ms1_precision * ms1_pr_mz:
                 isotope_pattern_df = self.get_isotope_mz(elem_dct, only_c=only_c)
                 # print(isotope_pattern_df)
                 ms1_pr_i -= m0_base_abs

diff --git a/LibLipidHunter/LipidHunter_Main.py b/LibLipidHunter/LipidHunter_Main.py
@@ -64,9 +64,9 @@ def __init__(self, parent=None, cwd=None):
         self.ui.setupUi(self, scale=scale)
 
         # set version
-        version_date = r'06, March, 2019'
+        version_date = r'06, August, 2019'
         version_html = (r'<html><head/><body><p><span style=" font-weight:600;">'
-                        r'LipidHunter 2 (RC) # Released Date: {version_date}'
+                        r'LipidHunter 2 (RC2) # Released Date: {version_date}'
                         r'</span></p></body></html>').format(version_date=version_date)
         self.ui.version_lb.setText(QtGui.QApplication.translate("MainWindow", version_html, None,
                                                                 QtGui.QApplication.UnicodeUTF8))

diff --git a/LibLipidHunter/LipidHunter_UI.py b/LibLipidHunter/LipidHunter_UI.py
@@ -1486,7 +1486,7 @@ def setupUi(self, MainWindow, scale=1):
         QtCore.QMetaObject.connectSlotsByName(MainWindow)
 
     def retranslateUi(self, MainWindow):
-        MainWindow.setWindowTitle(QtGui.QApplication.translate("MainWindow", "LipidHunter 2 (RC) | University of Leipzig ", None, QtGui.QApplication.UnicodeUTF8))
+        MainWindow.setWindowTitle(QtGui.QApplication.translate("MainWindow", "LipidHunter 2 (RC2) | University of Leipzig ", None, QtGui.QApplication.UnicodeUTF8))
         self.label_50.setText(QtGui.QApplication.translate("MainWindow", "Score weight factor settings:", None, QtGui.QApplication.UnicodeUTF8))
         self.tab_a_mzml_pb.setText(QtGui.QApplication.translate("MainWindow", "Open", None, QtGui.QApplication.UnicodeUTF8))
         self.label_3.setText(QtGui.QApplication.translate("MainWindow", "Select lipid class:", None, QtGui.QApplication.UnicodeUTF8))

diff --git a/LibLipidHunter/PanelPlotter.py b/LibLipidHunter/PanelPlotter.py
@@ -48,16 +48,17 @@ def plot_spectra(abbr, mz_se, xic_df, ident_info_dct, spec_info_dct, isotope_sco
     obs_ident_df = ident_info_dct['IDENT']
 
     obs_fa_df = ident_info_dct['OBS_FA']
-    obs_fa_df['obs_mz'] = obs_fa_df['obs_mz'].astype(float).round(4)
-    obs_fa_df['obs_ppm'] = obs_fa_df['obs_ppm'].astype(int).tolist()
-    obs_fa_df['obs_i_r'] = obs_fa_df['obs_i_r'].astype(float).round(1)
+    if not obs_fa_df.empty:
+        obs_fa_df['obs_mz'] = obs_fa_df['obs_mz'].astype(float).round(4)
+        obs_fa_df['obs_ppm'] = obs_fa_df['obs_ppm'].astype(int).tolist()
+        obs_fa_df['obs_i_r'] = obs_fa_df['obs_i_r'].astype(float).round(1)
 
     if 'OBS_LYSO' in list(ident_info_dct.keys()):
         obs_lyso_df = ident_info_dct['OBS_LYSO']
-        obs_lyso_df['obs_mz'] = obs_lyso_df['obs_mz'].astype(float).round(4)
-        obs_lyso_df['obs_ppm'] = obs_lyso_df['obs_ppm'].astype(int).tolist()
-        obs_lyso_df['obs_i_r'] = obs_lyso_df['obs_i_r'].astype(float).round(1)
         if not obs_lyso_df.empty:
+            obs_lyso_df['obs_mz'] = obs_lyso_df['obs_mz'].astype(float).round(4)
+            obs_lyso_df['obs_ppm'] = obs_lyso_df['obs_ppm'].astype(int).tolist()
+            obs_lyso_df['obs_i_r'] = obs_lyso_df['obs_i_r'].astype(float).round(1)
             obs_dg_na_df = obs_lyso_df.loc[obs_lyso_df['TYPE'] == 'NL_Na']
             obs_dg_na_df.reset_index(drop=True, inplace=True)
             obs_dg_na_idx = obs_lyso_df.index[obs_lyso_df['TYPE'] == 'NL_Na'].tolist()
@@ -563,6 +564,7 @@ def plot_msms():
             plt.setp(base_l, visible=False)
         else:
             pass
+
         if other_frag_df is not False:
             marker_l, stem_l, base_l = msms_pic.stem(other_frag_df['mz'], other_frag_df['i'], markerfmt=' ',
                                                      use_line_collection=True)
@@ -671,16 +673,15 @@ def plot_msms_low():
             else:
                 _fa_table2 = False
             # Create the table with the Free FA fragments for TG and PL
-            if obs_fa_df.loc[obs_fa_df['TYPE'] == 'FA']['obs_abbr'].values.tolist():
+            _fa_ident_lst = obs_fa_df.loc[obs_fa_df['TYPE'] == 'FA']['obs_abbr'].values.tolist()
+            if _fa_ident_lst:
                 _fa_table_df = pd.DataFrame(
                     data={'#': obs_fa_df.loc[obs_fa_df['TYPE'] == 'FA']['obs_rank'].astype(int).values.tolist(),
-                          'identification': obs_fa_df.loc[obs_fa_df['TYPE'] == 'FA']['obs_abbr'].values.tolist(),
+                          'identification': _fa_ident_lst,
                           'm/z': obs_fa_df.loc[obs_fa_df['TYPE'] == 'FA']['obs_mz'].tolist(),
                           'ppm': obs_fa_df.loc[obs_fa_df['TYPE'] == 'FA']['obs_ppm'].tolist(),
                           'i (%)': obs_fa_df.loc[obs_fa_df['TYPE'] == 'FA']['obs_i_r'].tolist()})
                 _fa_table_df = _fa_table_df.reindex(columns=_fa_col_labels)
-                print('_fa_table_df')
-                print(_fa_table_df)
                 _fa_table_vals = list(map(list, _fa_table_df.values))
                 _fa_col_width_lst = [0.03, 0.2, 0.10, 0.06, 0.06]
                 # _fa_col_width_lst2 = [0.03, 0.2, 0.30, 0.26, 0.26]

diff --git a/LibLipidHunter/SpectraReader.py b/LibLipidHunter/SpectraReader.py
@@ -81,8 +81,17 @@ def extract_mzml(mzml: str, rt_range: list, dda_top: int = 6,
 
     print('[STATUS] >>> Start to process file: %s' % mzml)
     print('[INFO] --> Processing RT: %.2f -> %.2f with DDA Top % i' % (rt_start, rt_end, dda_top))
-
-    spec_obj = pymzml.run.Reader(mzml, MS1_Precision=ms1_precision, MSn_Precision=ms2_precision)
+    try:
+        spec_obj = pymzml.run.Reader(mzml, MS1_Precision=ms1_precision, MSn_Precision=ms2_precision)
+    except (IOError, OSError):
+        try:
+            # Try to use the CV from mzML 4.0 released in 2016
+            spec_obj = pymzml.run.Reader(mzml, MS1_Precision=ms1_precision, MSn_Precision=ms2_precision,
+                                         obo_version='4.0.1')
+        except (IOError, OSError):
+            # try to use legacy version 1.1.0 to parse the mzML
+            spec_obj = pymzml.run.Reader(mzml, MS1_Precision=ms1_precision, MSn_Precision=ms2_precision,
+                                         obo_version='1.1.0')
 
     spec_idx = 0
     dda_event_idx = 0
@@ -287,7 +296,8 @@ def get_spectra(mz, mz_lib, func_id, ms2_scan_id, ms1_obs_mz_lst,
                                 try:
                                     ms2_df.drop('rt', axis=1, inplace=True)
                                 except (KeyError, ValueError):
-                                    print('[ERROR] !!! MS2_df do not have rt column...')
+                                    # print('[INFO] !!! MS2_df do not have rt column...')
+                                    pass
                             else:
                                 print('[WARNING] !!! MS2 spectra not in the list ...')
                         else:

diff --git a/README.md b/README.md
@@ -1,13 +1,15 @@
 # About LipidHunter 2 #
 ![LipidHunter_logo](LipidHunter.png)
 
-![Platforms](https://img.shields.io/badge/Platform-Linux%20%7C%20macOS%20%7C%20Windows-blue.svg)
-[![Travis (.com) all](https://img.shields.io/travis/com/ZhixuNi/lipidhunter/master.svg)](https://travis-ci.com/SysMedOs/epiLION)
-![GitHub last commit](https://img.shields.io/github/last-commit/ZhixuNi/lipidhunter.svg)
-![pyup dependencies](https://pyup.io/repos/github/ZhixuNi/lipidhunter/shield.svg)
 ![GitHub (Pre-)Release Date](https://img.shields.io/github/release-date-pre/SysMedOs/LipidHunter.svg)
-![GitHub commits since latest release](https://img.shields.io/github/commits-since/SysMedOs/lipidhunter/LipidHunter2_RC.svg)
 ![total downloads](https://img.shields.io/github/downloads/SysMedOs/lipidhunter/total.svg?color=orange)
+![GitHub commits since latest release](https://img.shields.io/github/commits-since/SysMedOs/lipidhunter/LipidHunter2_RC.svg)
+![GitHub last commit](https://img.shields.io/github/last-commit/ZhixuNi/lipidhunter.svg)
+
+[![Travis (.com) all](https://img.shields.io/travis/com/ZhixuNi/lipidhunter/master.svg)](https://travis-ci.com/SysMedOs/epiLION)
+![Platform macOS](https://img.shields.io/badge/Platform-macOS-lightgrey.svg)
+![Platform Linux](https://img.shields.io/badge/Platform-Linux-orange.svg)
+![Platform Windows](https://img.shields.io/badge/Platform-Windows-blue.svg)
 
 LipidHunter 2 has significant improvement from the original LipidHunter.
 The major improvements are listed below:
@@ -65,12 +67,10 @@ https://github.com/SysMedOs/lipidhunter/releases
 
 ### Windows version ###
 
-* The binary excutable version of LipidHunter 2 is provided for Windows users. (Windows 7, 8, and 10, 64bit system required)
-
-    + [`.exe` installation file](https://github.com/SysMedOs/lipidhunter/releases/download/LipidHunter2_RC/Lipidhunter2_RC_Setup.exe)
-
-    + [`.zip` portable zip file](https://github.com/SysMedOs/lipidhunter/releases/download/LipidHunter2_RC/LipidHunter2_RC.zip)
+* The binary executable version of LipidHunter 2 is provided for Windows users. (Windows 7, 8, and 10, 64bit system required)
 
+    + [`.exe` and `.zip` installation file](https://github.com/SysMedOs/lipidhunter/releases/latest)
+
 ### How to install LipidHunter 2 from source code ###
 * Download the LipidHunter 2 as zip file for your system
     + Please use the source code page in the release page https://github.com/SysMedOs/lipidhunter/releases/
@@ -91,7 +91,7 @@ https://github.com/SysMedOs/lipidhunter/releases
         - pip: activate your virtual environment, then `pip install -r requirements.txt`
     + Main dependencies are:
         - Data processing: numpy, pandas, scipy, numba, natsort
-        - mzML reader: pymzml == 0.7.8
+        - mzML reader: pymzml
         - Image plot: matplotlib, plotly(required by pymzml)
         - Excel output: openpyxl, xlrd, xlwt
         - Graphic interface: pyside
@@ -104,11 +104,34 @@ https://github.com/SysMedOs/lipidhunter/releases
 * [LipidHunter user guide](doc/LipidHunter_UserGuide.pdf)
 
 
-* Errors/bugs
-
-    In case you experienced any problems with running LipidHunter
+### mzML File conversion ###
+
+We recommend to use ProteoWizard version 3.0.19217 64 bit version or above to convert your raw files to mzML.
+You can find the latest version of ProteoWizard from:
+
+http://proteowizard.sourceforge.net/download.html
+
+If you have difficulties to run your mzML file.
+Please try to run your analysis again in the LipidHunter_debug.exe and post the error messages 
+to the [issue tracker](https://github.com/SysMedOs/lipidhunter/issues) or contact us.
+
+
+### Graphic interface issue on high resolution screens ###
+
+Please open the `config.ini` file and change `gui_scale = 1` to `gui_scale = 1.5` or `gui_scale = 2`save it 
+and restart LipidHunter.
+If there is no `gui_scale = 1` section, you can manually add it in the end.
+
+We recommend laptop user with high resolution screen to try the scale ratio `2` or `1.5`.
+You can try to set scale factor from `0.75` (75%) to `2.75` (275%) with the step of `0.25` (25%) 
+to find the best value for your screen.
+
+
+### Errors/bugs ###
 
-    please report an issue in the [issue tracker](https://github.com/SysMedOs/lipidhunter/issues) or contact us.
+In case you experienced any problems with running LipidHunter
+
+please report an issue in the [issue tracker](https://github.com/SysMedOs/lipidhunter/issues) or contact us.
 
 ### License ###
 

diff --git a/config.ini b/config.ini
@@ -19,5 +19,5 @@ runhunter_tab = 1
 lipidgen_tab = 1
 default_vendor = 0
 default_lipid = 0
-gui_scale = 5
+gui_scale = 1
 
diff --git a/requirements.txt b/requirements.txt
@@ -1,31 +1,31 @@
 ca-certificates>=2019.3.9
 certifi>=2019.3.9
-codecov==2.0.15
-coverage==4.5.3
-cython==0.29.12
-idna==2.8
-llvmlite==0.29.0
-matplotlib==3.1.1
-natsort==6.0.0
-numba==0.45.0
-numexpr==2.6.9
-numpy==1.16.4
-openpyxl==2.6.2
-packaging==19.0
+codecov>=2.0.15
+coverage>=4.5.3
+cython>=0.29.12
+idna>=2.8
+llvmlite>=0.29.0
+matplotlib>=3.1.1
+natsort>=6.0.0
+numba>=0.45.0
+numexpr>=2.6.9
+numpy>=1.16.4
+openpyxl>=2.6.2
+packaging>=19.0
 pandas==0.25.0
-plotly==4.0.0
+plotly>=4.0.0
 pymzml==2.2.5
-pyparsing==2.4.0
-pyside>=1.2.4
+pyparsing>=2.4.0
+pyside==1.2.4
 python>=3.6.7
-pytest==5.0.1
-pytest-cov==2.7.1
-python-dateutil==2.8.0
-pytz==2019.1
-regex==2019.6.8
-requests==2.22.0
-scipy==1.3.0
-six==1.12.0
-urllib3==1.25.3
-xlrd==1.2.0
-xlwt==1.3.0
+pytest>=5.0.1
+pytest-cov>=2.7.1
+python-dateutil>=2.8.0
+pytz>=2019.1
+regex>=2019.6.8
+requests>=2.22.0
+scipy.=1.3.0
+six>=1.12.0
+urllib3>=1.25.3
+xlrd>=1.2.0
+xlwt>=1.3.0