pycompound 0.1.9__tar.gz → 0.1.10__tar.gz

{pycompound-0.1.9/src/pycompound.egg-info → pycompound-0.1.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pycompound
-Version: 0.1.9
+Version: 0.1.10
 Summary: Python package to perform compound identification in mass spectrometry via spectral library matching.
 Author-email: Hunter Dlugas <fy7392@wayne.edu>
 License-Expression: MIT

{pycompound-0.1.9 → pycompound-0.1.10}/README.md

@@ -19,9 +19,9 @@ A Python-based tool for spectral library matching, PyCompound is available as a
 ## 1. Install dependencies
 PyCompound requires the Python dependencies Matplotlib, NumPy, Pandas, SciPy, Pyteomics, and netCDF4. Specifically, this software was validated with python=3.12.4, matplotlib=3.8.4, numpy=1.26.4, pandas=2.2.2, scipy=1.13.1, pyteomics=4.7.2, netCDF4=1.6.5, lxml=5.1.0, joblib=1.5.2, and shiny=1.4.0, although it may work with other versions of these tools. A user may consider creating a conda environment (see [https://docs.conda.io/projects/conda/en/latest/user-guide/getting-started.html](https://docs.conda.io/projects/conda/en/latest/user-guide/getting-started.html) for guidance on getting started with conda if you are unfamiliar). For a system with conda installed, one can create the environment pycompound_env, activate it, and install the necessary dependencies with:
 ```
-conda create -n pycompound_env python=3.12
+conda create -n pycompound_env python=3.12 -y
 conda activate pycompound_env
-pip install pycompound==0.1.7
+pip install pycompound==0.1.10
 ```
 
 <a name="functionality"></a>

{pycompound-0.1.9 → pycompound-0.1.10}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pycompound"
-version = "0.1.9"
+version = "0.1.10"
 authors = [
   { name="Hunter Dlugas", email="fy7392@wayne.edu" },
 ]

{pycompound-0.1.9 → pycompound-0.1.10}/src/pycompound/plot_spectra.py

@@ -14,7 +14,7 @@ def generate_plots_on_HRMS_data(query_data=None, reference_data=None, spectrum_I
     else:
         extension = query_data.rsplit('.',1)
         extension = extension[(len(extension)-1)]
-        if extension == 'mgf' or extension == 'MGF' or extension == 'mzML' or extension == 'mzml' or extension == 'MZML' or extension == 'cdf' or extension == 'CDF':
+        if extension == 'mgf' or extension == 'MGF' or extension == 'mzML' or extension == 'mzml' or extension == 'MZML' or extension == 'cdf' or extension == 'CDF' or extension == 'msp' or extension == 'MSP' or extension == 'json' or extension == 'JSON':
             output_path_tmp = query_data[:-3] + 'txt'
             build_library_from_raw_data(input_path=query_data, output_path=output_path_tmp, is_reference=True)
             df_query = pd.read_csv(output_path_tmp, sep='\t')
@@ -29,7 +29,7 @@ def generate_plots_on_HRMS_data(query_data=None, reference_data=None, spectrum_I
     else:
         extension = reference_data.rsplit('.',1)
         extension = extension[(len(extension)-1)]
-        if extension == 'mgf' or extension == 'MGF' or extension == 'mzML' or extension == 'mzml' or extension == 'MZML' or extension == 'cdf' or extension == 'CDF':
+        if extension == 'mgf' or extension == 'MGF' or extension == 'mzML' or extension == 'mzml' or extension == 'MZML' or extension == 'cdf' or extension == 'CDF' or extension == 'msp' or extension == 'MSP' or extension == 'json' or extension == 'JSON':
             output_path_tmp = reference_data[:-3] + 'txt'
             build_library_from_raw_data(input_path=reference_data, output_path=output_path_tmp, is_reference=True)
             df_reference = pd.read_csv(output_path_tmp, sep='\t')
@@ -298,7 +298,7 @@ def generate_plots_on_NRMS_data(query_data=None, reference_data=None, spectrum_I
     else:
         extension = query_data.rsplit('.',1)
         extension = extension[(len(extension)-1)]
-        if extension == 'mgf' or extension == 'MGF' or extension == 'mzML' or extension == 'mzml' or extension == 'MZML' or extension == 'cdf' or extension == 'CDF':
+        if extension == 'mgf' or extension == 'MGF' or extension == 'mzML' or extension == 'mzml' or extension == 'MZML' or extension == 'cdf' or extension == 'CDF' or extension == 'msp' or extension == 'MSP' or extension == 'json' or extension == 'JSON':
             output_path_tmp = query_data[:-3] + 'txt'
             build_library_from_raw_data(input_path=query_data, output_path=output_path_tmp, is_reference=False)
             df_query = pd.read_csv(output_path_tmp, sep='\t')
@@ -312,7 +312,7 @@ def generate_plots_on_NRMS_data(query_data=None, reference_data=None, spectrum_I
     else:
         extension = reference_data.rsplit('.',1)
         extension = extension[(len(extension)-1)]
-        if extension == 'mgf' or extension == 'MGF' or extension == 'mzML' or extension == 'mzml' or extension == 'MZML' or extension == 'cdf' or extension == 'CDF':
+        if extension == 'mgf' or extension == 'MGF' or extension == 'mzML' or extension == 'mzml' or extension == 'MZML' or extension == 'cdf' or extension == 'CDF' or extension == 'msp' or extension == 'MSP' or extension == 'json' or extension == 'JSON':
             output_path_tmp = reference_data[:-3] + 'txt'
             build_library_from_raw_data(input_path=reference_data, output_path=output_path_tmp, is_reference=True)
             df_reference = pd.read_csv(output_path_tmp, sep='\t')
@@ -395,8 +395,8 @@ def generate_plots_on_NRMS_data(query_data=None, reference_data=None, spectrum_I
         print(f'Warning: plots will be saved to the PDF ./spectrum1_{spectrum_ID1}_spectrum2_{spectrum_ID2}_plot.pdf in the current working directory.')
         output_path = f'{Path.cwd()}/spectrum1_{spectrum_ID1}_spectrum2_{spectrum_ID2}.pdf'
 
-    min_mz = np.min([np.min(df_query['mz_ratio'].tolist()), np.min(df_reference['mz_ratio'].tolist())])
-    max_mz = np.max([np.max(df_query['mz_ratio'].tolist()), np.max(df_reference['mz_ratio'].tolist())])
+    min_mz = int(np.min([np.min(df_query['mz_ratio'].tolist()), np.min(df_reference['mz_ratio'].tolist())]))
+    max_mz = int(np.max([np.max(df_query['mz_ratio'].tolist()), np.max(df_reference['mz_ratio'].tolist())]))
     mzs = np.linspace(min_mz,max_mz,(max_mz-min_mz+1))
 
     unique_query_ids = df_query['id'].unique().tolist()

{pycompound-0.1.9 → pycompound-0.1.10}/src/pycompound/spec_lib_matching.py

@@ -65,7 +65,7 @@ def tune_params_DE(query_data=None, reference_data=None, chromatography_platform
         extension = extension[(len(extension)-1)]
         if extension == 'mgf' or extension == 'MGF' or extension == 'mzML' or extension == 'mzml' or extension == 'MZML' or extension == 'cdf' or extension == 'CDF' or extension == 'msp' or extension == 'MSP' or extension == 'json' or extension == 'JSON':
             output_path_tmp = query_data[:-3] + 'txt'
-            build_library_from_raw_data(input_path=query_data, output_path=output_path_tmp, is_reference=False)
+            build_library_from_raw_data(input_path=query_data, output_path=output_path_tmp, is_reference=True)
             df_query = pd.read_csv(output_path_tmp, sep='\t')
         if extension == 'txt' or extension == 'TXT':
             df_query = pd.read_csv(query_data, sep='\t')
@@ -805,7 +805,7 @@ def run_spec_lib_matching_on_NRMS_data(query_data=None, reference_data=None, lik
     else:
         extension = query_data.rsplit('.',1)
         extension = extension[(len(extension)-1)]
-        if extension == 'mgf' or extension == 'MGF' or extension == 'mzML' or extension == 'mzml' or extension == 'MZML' or extension == 'cdf' or extension == 'CDF':
+        if extension == 'mgf' or extension == 'MGF' or extension == 'mzML' or extension == 'mzml' or extension == 'MZML' or extension == 'cdf' or extension == 'CDF' or extension == 'msp' or extension == 'MSP' or extension == 'json' or extension == 'JSON':
             output_path_tmp = query_data[:-3] + 'txt'
             build_library_from_raw_data(input_path=query_data, output_path=output_path_tmp, is_reference=False)
             df_query = pd.read_csv(output_path_tmp, sep='\t')

{pycompound-0.1.9 → pycompound-0.1.10/src/pycompound.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pycompound
-Version: 0.1.9
+Version: 0.1.10
 Summary: Python package to perform compound identification in mass spectrometry via spectral library matching.
 Author-email: Hunter Dlugas <fy7392@wayne.edu>
 License-Expression: MIT

{pycompound-0.1.9 → pycompound-0.1.10}/tests/test_plot_spectra.py

@@ -248,3 +248,36 @@ generate_plots_on_HRMS_data(
         weights={'Cosine':0.1, 'Shannon':0.2, 'Renyi':0.3, 'Tsallis':0.4},
         output_path=f'{Path.cwd()}/plots/test32.pdf')
 
+print('\n\ntest #33:')
+generate_plots_on_HRMS_data(
+        query_data=f'{Path.cwd()}/data/lcms_query.msp',
+        reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
+        high_quality_reference_library=True,
+        noise_threshold=0.1,
+        mz_min=100,
+        output_path=f'{Path.cwd()}/plots/test33.pdf')
+
+print('\n\ntest #34:')
+generate_plots_on_HRMS_data(
+        query_data=f'{Path.cwd()}/data/lcms_query_tuning.msp',
+        reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
+        high_quality_reference_library=True,
+        noise_threshold=0.1,
+        mz_min=100,
+        output_path=f'{Path.cwd()}/plots/test34.pdf')
+
+print('\n\ntest #35:')
+generate_plots_on_NRMS_data(
+        query_data=f'{Path.cwd()}/data/gcms_query.msp',
+        reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
+        similarity_measure='shannon',
+        weights={'Cosine':0.5, 'Shannon':0.3, 'Renyi':0.1, 'Tsallis':0.1},
+        output_path=f'{Path.cwd()}/plots/test35.pdf')
+
+print('\n\ntest #36:')
+generate_plots_on_NRMS_data(
+        query_data=f'{Path.cwd()}/data/gcms_query.msp',
+        reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
+        similarity_measure='cosine',
+        output_path=f'{Path.cwd()}/plots/test36.pdf')
+

{pycompound-0.1.9 → pycompound-0.1.10}/tests/test_spec_lib_matching.py

@@ -316,5 +316,15 @@ run_spec_lib_matching_on_HRMS_data(query_data=f'{Path.cwd()}/data/MoNA-export-Hu
                                    adduct='H',
                                    precursor_ion_mz_tolerance=0.5,
                                    print_id_results=True)
+
+print('\n\ntest #53:')
+run_spec_lib_matching_on_HRMS_data(query_data=f'{Path.cwd()}/data/lcms_query.msp',
+                                   reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
+                                   similarity_measure='cosine')
+print('\n\ntest #54:')
+run_spec_lib_matching_on_NRMS_data(query_data=f'{Path.cwd()}/data/gcms_query.msp',
+                                   reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
+                                   similarity_measure='cosine')
+
 """
 

{pycompound-0.1.9 → pycompound-0.1.10}/tests/test_tuning.py

@@ -5,7 +5,18 @@ from pycompound.spec_lib_matching import tune_params_DE
 from pathlib import Path
 import os
 
+print('\n\ntest #9:')
+tune_params_DE(query_data=f'{Path.cwd()}/data/gcms_query_tuning.msp',
+               reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
+               chromatography_platform='NRMS',
+               similarity_measure='tsallis',
+               optimize_params=["wf_mz","wf_int","LET_threshold","entropy_dimension"],
+               param_bounds={"wf_mz":(0.0,5.0),"wf_int":(0.0,5.0),"LET_threshold":(0,5),"entropy_dimension":(1.01,3)},
+               default_params={"noise_threshold":0.10, "wf_mz":0.0, "wf_int":1.0, "LET_threshold":0.0, "entropy_dimension":1.1},
+               maxiters=10,
+               de_workers=5)
 
+"""
 print('\n\ntest #1:')
 tune_params_on_HRMS_data_grid(query_data=f'{Path.cwd()}/data/lcms_query_tuning.txt',
                               reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
@@ -69,3 +80,18 @@ tune_params_DE(query_data=f'{Path.cwd()}/data/gcms_query_tuning.txt',
                maxiters=10,
                de_workers=5)
 
+print('\n\ntest #8:')
+tune_params_DE(query_data=f'{Path.cwd()}/data/lcms_query_tuning.msp',
+               reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
+               precursor_ion_mz_tolerance=0.1,
+               ionization_mode='Positive',
+               adduct='H',
+               chromatography_platform='HRMS',
+               similarity_measure='shannon',
+               optimize_params=["wf_mz","wf_int"],
+               param_bounds={"wf_mz":(0.0,5.0),"wf_int":(0.0,5.0)},
+               default_params={"window_size_centroiding": 0.5, "window_size_matching":0.5, "noise_threshold":0.10, "wf_mz":0.0, "wf_int":1.0, "LET_threshold":0.0, "entropy_dimension":1.1},
+               maxiters=10,
+               de_workers=6)
+"""
+