pycompound 0.1.8__tar.gz → 0.1.10__tar.gz

pycompound-0.1.10/PKG-INFO

@@ -0,0 +1,28 @@
+Metadata-Version: 2.4
+Name: pycompound
+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
+Project-URL: Homepage, https://github.com/hdlugas/pycompound
+Project-URL: Issues, https://github.com/hdlugas/pycompound/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: matplotlib==3.8.4
+Requires-Dist: numpy==1.26.4
+Requires-Dist: pandas==2.2.2
+Requires-Dist: scipy==1.13.1
+Requires-Dist: pyteomics==4.7.2
+Requires-Dist: netCDF4==1.6.5
+Requires-Dist: lxml>=5.1.0
+Requires-Dist: orjson==3.11.0
+Requires-Dist: shiny==1.4.0
+Requires-Dist: joblib==1.5.2
+Dynamic: license-file
+
+# PyCompound
+
+A Python-based tool for spectral library matching, PyCompound is available as a Python package (pycompound) with a command-line interface (CLI) available and as a GUI application build with Python/Shiny. It performs spectral library matching to identify chemical compounds, offering a range of spectrum preprocessing transformations and similarity measures, including Cosine, three entropy-based similarity measures, and a plethora of binary similarity measures. PyCompound also includes functionality to tune parameters commonly used in a compound identification workflow given a query library of spectra with known ID. PyCompound supports both high-resolution mass spectrometry (HRMS) data (e.g., LC-MS/MS) and nominal-resolution mass spectrometry (NRMS) data (e.g., GC-MS). For the full documentation, see the GitHub repository https://github.com/hdlugas/pycompound.

{pycompound-0.1.8 → 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-0.1.10/README_PyPI.md

@@ -0,0 +1,3 @@
+# PyCompound
+
+A Python-based tool for spectral library matching, PyCompound is available as a Python package (pycompound) with a command-line interface (CLI) available and as a GUI application build with Python/Shiny. It performs spectral library matching to identify chemical compounds, offering a range of spectrum preprocessing transformations and similarity measures, including Cosine, three entropy-based similarity measures, and a plethora of binary similarity measures. PyCompound also includes functionality to tune parameters commonly used in a compound identification workflow given a query library of spectra with known ID. PyCompound supports both high-resolution mass spectrometry (HRMS) data (e.g., LC-MS/MS) and nominal-resolution mass spectrometry (NRMS) data (e.g., GC-MS). For the full documentation, see the GitHub repository https://github.com/hdlugas/pycompound.

{pycompound-0.1.8 → pycompound-0.1.10}/pyproject.toml

@@ -4,12 +4,12 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pycompound"
-version = "0.1.8"
+version = "0.1.10"
 authors = [
   { name="Hunter Dlugas", email="fy7392@wayne.edu" },
 ]
 description = "Python package to perform compound identification in mass spectrometry via spectral library matching."
-readme = "README.md"
+readme = "README_PyPI.md"
 requires-python = ">=3.9"
 classifiers = [
     "Programming Language :: Python :: 3",

{pycompound-0.1.8 → 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-0.1.8 → pycompound-0.1.10}/src/pycompound/spec_lib_matching.py

@@ -31,7 +31,8 @@ def objective_function_HRMS(X, ctx):
         p["wf_mz"], p["wf_int"], p["LET_threshold"],
         p["entropy_dimension"],
         ctx["high_quality_reference_library"],
-        verbose=False
+        verbose=False,
+        exact_match_required=ctx["exact_match_required"]
     )
     print(f"\nparams({ctx['optimize_params']}) = {np.array(X)}\naccuracy: {acc*100}%")
     return 1.0 - acc
@@ -45,7 +46,8 @@ def objective_function_NRMS(X, ctx):
         ctx["mz_min"], ctx["mz_max"], ctx["int_min"], ctx["int_max"],
         p["noise_threshold"], p["wf_mz"], p["wf_int"], p["LET_threshold"], p["entropy_dimension"],
         ctx["high_quality_reference_library"],
-        verbose=False
+        verbose=False,
+        exact_match_required=ctx["exact_match_required"]
     )
     print(f"\nparams({ctx['optimize_params']}) = {np.array(X)}\naccuracy: {acc*100}%")
     return 1.0 - acc
@@ -53,7 +55,7 @@ def objective_function_NRMS(X, ctx):
 
 
 
-def tune_params_DE(query_data=None, reference_data=None, chromatography_platform='HRMS', precursor_ion_mz_tolerance=None, ionization_mode=None, adduct=None, similarity_measure='cosine', weights=None, spectrum_preprocessing_order='CNMWL', mz_min=0, mz_max=999999999, int_min=0, int_max=999999999, high_quality_reference_library=False, optimize_params=["window_size_centroiding","window_size_matching","noise_threshold","wf_mz","wf_int","LET_threshold","entropy_dimension"], param_bounds={"window_size_centroiding":(0.0,0.5),"window_size_matching":(0.0,0.5),"noise_threshold":(0.0,0.25),"wf_mz":(0.0,5.0),"wf_int":(0.0,5.0),"LET_threshold":(0.0,5.0),"entropy_dimension":(1.0,3.0)}, 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=3, de_workers=1):
+def tune_params_DE(query_data=None, reference_data=None, chromatography_platform='HRMS', precursor_ion_mz_tolerance=None, ionization_mode=None, adduct=None, similarity_measure='cosine', weights=None, spectrum_preprocessing_order='CNMWL', mz_min=0, mz_max=999999999, int_min=0, int_max=999999999, high_quality_reference_library=False, optimize_params=["window_size_centroiding","window_size_matching","noise_threshold","wf_mz","wf_int","LET_threshold","entropy_dimension"], param_bounds={"window_size_centroiding":(0.0,0.5),"window_size_matching":(0.0,0.5),"noise_threshold":(0.0,0.25),"wf_mz":(0.0,5.0),"wf_int":(0.0,5.0),"LET_threshold":(0.0,5.0),"entropy_dimension":(1.0,3.0)}, 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=3, de_workers=1, exact_match_required=False):
 
     if query_data is None:
         print('\nError: No argument passed to the mandatory query_data. Please pass the path to the TXT file of the query data.')
@@ -63,7 +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')
@@ -106,6 +108,7 @@ def tune_params_DE(query_data=None, reference_data=None, chromatography_platform
         high_quality_reference_library=high_quality_reference_library,
         default_params=default_params,
         optimize_params=optimize_params,
+        exact_match_required=exact_match_required
     )
 
     bounds = [param_bounds[p] for p in optimize_params]
@@ -136,14 +139,7 @@ default_HRMS_grid = {'similarity_measure':['cosine'], 'weight':[{'Cosine':0.25,'
 default_NRMS_grid = {'similarity_measure':['cosine'], 'weight':[{'Cosine':0.25,'Shannon':0.25,'Renyi':0.25,'Tsallis':0.25}], 'spectrum_preprocessing_order':['FCNMWL'], 'mz_min':[0], 'mz_max':[9999999], 'int_min':[0], 'int_max':[99999999], 'noise_threshold':[0.0], 'wf_mz':[0.0], 'wf_int':[1.0], 'LET_threshold':[0.0], 'entropy_dimension':[1.1], 'high_quality_reference_library':[False]}
 
 
-def _eval_one_HRMS(df_query, df_reference,
-              precursor_ion_mz_tolerance_tmp, ionization_mode_tmp, adduct_tmp,
-              similarity_measure_tmp, weight,
-              spectrum_preprocessing_order_tmp, mz_min_tmp, mz_max_tmp,
-              int_min_tmp, int_max_tmp, noise_threshold_tmp,
-              window_size_centroiding_tmp, window_size_matching_tmp,
-              wf_mz_tmp, wf_int_tmp, LET_threshold_tmp,
-              entropy_dimension_tmp, high_quality_reference_library_tmp):
+def _eval_one_HRMS(df_query, df_reference, precursor_ion_mz_tolerance_tmp, ionization_mode_tmp, adduct_tmp, similarity_measure_tmp, weight, spectrum_preprocessing_order_tmp, mz_min_tmp, mz_max_tmp, int_min_tmp, int_max_tmp, noise_threshold_tmp, window_size_centroiding_tmp, window_size_matching_tmp, wf_mz_tmp, wf_int_tmp, LET_threshold_tmp, entropy_dimension_tmp, high_quality_reference_library_tmp, exact_match_required_tmp):
 
     acc = get_acc_HRMS(
         df_query=df_query, df_reference=df_reference,
@@ -160,7 +156,8 @@ def _eval_one_HRMS(df_query, df_reference,
         LET_threshold=LET_threshold_tmp,
         entropy_dimension=entropy_dimension_tmp,
         high_quality_reference_library=high_quality_reference_library_tmp,
-        verbose=False
+        verbose=False,
+        exact_match_required=exact_match_required_tmp
     )
 
     return (
@@ -172,12 +169,7 @@ def _eval_one_HRMS(df_query, df_reference,
     )
 
 
-def _eval_one_NRMS(df_query, df_reference, unique_query_ids, unique_reference_ids,
-              similarity_measure_tmp, weight,
-              spectrum_preprocessing_order_tmp, mz_min_tmp, mz_max_tmp,
-              int_min_tmp, int_max_tmp, noise_threshold_tmp,
-              wf_mz_tmp, wf_int_tmp, LET_threshold_tmp,
-              entropy_dimension_tmp, high_quality_reference_library_tmp):
+def _eval_one_NRMS(df_query, df_reference, unique_query_ids, unique_reference_ids, similarity_measure_tmp, weight, spectrum_preprocessing_order_tmp, mz_min_tmp, mz_max_tmp, int_min_tmp, int_max_tmp, noise_threshold_tmp, wf_mz_tmp, wf_int_tmp, LET_threshold_tmp, entropy_dimension_tmp, high_quality_reference_library_tmp, exact_match_required):
 
     acc = get_acc_NRMS(
         df_query=df_query, df_reference=df_reference,
@@ -191,7 +183,8 @@ def _eval_one_NRMS(df_query, df_reference, unique_query_ids, unique_reference_id
         LET_threshold=LET_threshold_tmp,
         entropy_dimension=entropy_dimension_tmp,
         high_quality_reference_library=high_quality_reference_library_tmp,
-        verbose=False
+        verbose=False,
+        exact_match_required=exact_match_required_tmp
     )
 
     return (
@@ -202,7 +195,7 @@ def _eval_one_NRMS(df_query, df_reference, unique_query_ids, unique_reference_id
 
 
 
-def tune_params_on_HRMS_data_grid(query_data=None, reference_data=None, precursor_ion_mz_tolerance=None, ionization_mode=None, adduct=None, grid=None, output_path=None, return_output=False):
+def tune_params_on_HRMS_data_grid(query_data=None, reference_data=None, precursor_ion_mz_tolerance=None, ionization_mode=None, adduct=None, grid=None, output_path=None, return_output=False, exact_match_required=False):
     grid = {**default_HRMS_grid, **(grid or {})}
     for key, value in grid.items():
         globals()[key] = value
@@ -251,7 +244,9 @@ def tune_params_on_HRMS_data_grid(query_data=None, reference_data=None, precurso
 
     param_grid = product(similarity_measure, weight, spectrum_preprocessing_order, mz_min, mz_max, int_min, int_max, noise_threshold,
                          window_size_centroiding, window_size_matching, wf_mz, wf_int, LET_threshold, entropy_dimension, high_quality_reference_library)
-    results = Parallel(n_jobs=-1, verbose=10)(delayed(_eval_one_HRMS)(df_query, df_reference, precursor_ion_mz_tolerance, ionization_mode, adduct,  *params) for params in param_grid)
+    #results = Parallel(n_jobs=-1, verbose=10)(delayed(_eval_one_HRMS)(df_query, df_reference, precursor_ion_mz_tolerance, ionization_mode, adduct, (*params for params in param_grid), exact_match_required))
+    results = Parallel(n_jobs=-1, verbose=10)(delayed(_eval_one_HRMS)(df_query, df_reference, precursor_ion_mz_tolerance, ionization_mode, adduct, *params, exact_match_required) for params in param_grid)
+
 
     df_out = pd.DataFrame(results, columns=[
         'ACC','SIMILARITY.MEASURE','WEIGHT','SPECTRUM.PROCESSING.ORDER', 'MZ.MIN','MZ.MAX','INT.MIN','INT.MAX','NOISE.THRESHOLD',
@@ -275,7 +270,7 @@ def tune_params_on_HRMS_data_grid(query_data=None, reference_data=None, precurso
 
 
 
-def tune_params_on_NRMS_data_grid(query_data=None, reference_data=None, grid=None, output_path=None, return_output=False):
+def tune_params_on_NRMS_data_grid(query_data=None, reference_data=None, grid=None, output_path=None, return_output=False, exact_match_required=False):
     grid = {**default_NRMS_grid, **(grid or {})}
     for key, value in grid.items():
         globals()[key] = value
@@ -318,7 +313,8 @@ def tune_params_on_NRMS_data_grid(query_data=None, reference_data=None, grid=Non
 
     param_grid = product(similarity_measure, weight, spectrum_preprocessing_order, mz_min, mz_max, int_min, int_max,
                          noise_threshold, wf_mz, wf_int, LET_threshold, entropy_dimension, high_quality_reference_library)
-    results = Parallel(n_jobs=-1, verbose=10)(delayed(_eval_one_NRMS)(df_query, df_reference, unique_query_ids, unique_reference_ids, *params) for params in param_grid)
+    #results = Parallel(n_jobs=-1, verbose=10)(delayed(_eval_one_NRMS)(df_query, df_reference, unique_query_ids, unique_reference_ids, *params) for params in param_grid, exact_match_required)
+    results = Parallel(n_jobs=-1, verbose=10)(delayed(_eval_one_NRMS)(df_query, df_reference, unique_query_ids, unique_reference_ids, *params, exact_match_required) for params in param_grid)
 
     df_out = pd.DataFrame(results, columns=['ACC','SIMILARITY.MEASURE','WEIGHT','SPECTRUM.PROCESSING.ORDER', 'MZ.MIN','MZ.MAX','INT.MIN','INT.MAX',
                                             'NOISE.THRESHOLD','WF.MZ','WF.INT','LET.THRESHOLD','ENTROPY.DIMENSION', 'HIGH.QUALITY.REFERENCE.LIBRARY'])
@@ -339,7 +335,7 @@ def tune_params_on_NRMS_data_grid(query_data=None, reference_data=None, grid=Non
 
 
 
-def get_acc_HRMS(df_query, df_reference, precursor_ion_mz_tolerance, ionization_mode, adduct, similarity_measure, weights, spectrum_preprocessing_order, mz_min, mz_max, int_min, int_max, window_size_centroiding, window_size_matching, noise_threshold, wf_mz, wf_int, LET_threshold, entropy_dimension, high_quality_reference_library, verbose=True):
+def get_acc_HRMS(df_query, df_reference, precursor_ion_mz_tolerance, ionization_mode, adduct, similarity_measure, weights, spectrum_preprocessing_order, mz_min, mz_max, int_min, int_max, window_size_centroiding, window_size_matching, noise_threshold, wf_mz, wf_int, LET_threshold, entropy_dimension, high_quality_reference_library, verbose=True, exact_match_required=False):
 
     n_top_matches_to_save = 1
     unique_reference_ids = df_reference['id'].dropna().astype(str).unique().tolist()
@@ -445,11 +441,17 @@ def get_acc_HRMS(df_query, df_reference, precursor_ion_mz_tolerance, ionization_
     df_tmp = pd.DataFrame({'TRUE.ID': df_scores.index.to_list(), 'PREDICTED.ID': top_ids, 'SCORE': top_scores})
     #if verbose:
     #    print(df_tmp)
-    acc = (df_tmp['TRUE.ID'] == df_tmp['PREDICTED.ID']).mean()
+    if exact_match_required == True:
+        acc = (df_tmp['TRUE.ID'] == df_tmp['PREDICTED.ID']).mean()
+    else:
+        true_lower = df_tmp['TRUE.ID'].str.lower()
+        pred_lower = df_tmp['PREDICTED.ID'].str.lower()
+        matches = [t in p for t, p in zip(true_lower, pred_lower)]
+        acc = sum(matches) / len(matches)
     return acc
 
 
-def get_acc_NRMS(df_query, df_reference, unique_query_ids, unique_reference_ids, similarity_measure, weights, spectrum_preprocessing_order, mz_min, mz_max, int_min, int_max, noise_threshold, wf_mz, wf_int, LET_threshold, entropy_dimension, high_quality_reference_library, verbose=True):
+def get_acc_NRMS(df_query, df_reference, unique_query_ids, unique_reference_ids, similarity_measure, weights, spectrum_preprocessing_order, mz_min, mz_max, int_min, int_max, noise_threshold, wf_mz, wf_int, LET_threshold, entropy_dimension, high_quality_reference_library, verbose=True, exact_match_required=False):
 
     n_top_matches_to_save = 1
 
@@ -532,7 +534,13 @@ def get_acc_NRMS(df_query, df_reference, unique_query_ids, unique_reference_ids,
     df_tmp = pd.DataFrame(out, columns=['TRUE.ID','PREDICTED.ID','SCORE'])
     #if verbose:
     #    print(df_tmp)
-    acc = (df_tmp['TRUE.ID']==df_tmp['PREDICTED.ID']).mean()
+    if exact_match_required == True:
+        acc = (df_tmp['TRUE.ID'] == df_tmp['PREDICTED.ID']).mean()
+    else:
+        true_lower = df_tmp['TRUE.ID'].str.lower()
+        pred_lower = df_tmp['PREDICTED.ID'].str.lower()
+        matches = [t in p for t, p in zip(true_lower, pred_lower)]
+        acc = sum(matches) / len(matches)
     return acc
 
 
@@ -797,7 +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-0.1.10/src/pycompound.egg-info/PKG-INFO

@@ -0,0 +1,28 @@
+Metadata-Version: 2.4
+Name: pycompound
+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
+Project-URL: Homepage, https://github.com/hdlugas/pycompound
+Project-URL: Issues, https://github.com/hdlugas/pycompound/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: matplotlib==3.8.4
+Requires-Dist: numpy==1.26.4
+Requires-Dist: pandas==2.2.2
+Requires-Dist: scipy==1.13.1
+Requires-Dist: pyteomics==4.7.2
+Requires-Dist: netCDF4==1.6.5
+Requires-Dist: lxml>=5.1.0
+Requires-Dist: orjson==3.11.0
+Requires-Dist: shiny==1.4.0
+Requires-Dist: joblib==1.5.2
+Dynamic: license-file
+
+# PyCompound
+
+A Python-based tool for spectral library matching, PyCompound is available as a Python package (pycompound) with a command-line interface (CLI) available and as a GUI application build with Python/Shiny. It performs spectral library matching to identify chemical compounds, offering a range of spectrum preprocessing transformations and similarity measures, including Cosine, three entropy-based similarity measures, and a plethora of binary similarity measures. PyCompound also includes functionality to tune parameters commonly used in a compound identification workflow given a query library of spectra with known ID. PyCompound supports both high-resolution mass spectrometry (HRMS) data (e.g., LC-MS/MS) and nominal-resolution mass spectrometry (NRMS) data (e.g., GC-MS). For the full documentation, see the GitHub repository https://github.com/hdlugas/pycompound.

{pycompound-0.1.8 → pycompound-0.1.10}/src/pycompound.egg-info/SOURCES.txt

@@ -1,5 +1,6 @@
 LICENSE
 README.md
+README_PyPI.md
 pyproject.toml
 src/pycompound/build_library.py
 src/pycompound/plot_spectra.py

{pycompound-0.1.8 → pycompound-0.1.10}/tests/test_plot_spectra.py

@@ -8,7 +8,7 @@ os.makedirs(f'{Path.cwd()}/plots', exist_ok=True)
 
 print('\n\ntest #1:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         high_quality_reference_library=True,
         noise_threshold=0.1,
@@ -17,7 +17,7 @@ generate_plots_on_HRMS_data(
 
 print('\n\ntest #2:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         noise_threshold=0.1,
         similarity_measure='shannon',
@@ -25,7 +25,7 @@ generate_plots_on_HRMS_data(
 
 print('\n\ntest #3:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         similarity_measure='renyi',
         entropy_dimension=1.2,
@@ -33,7 +33,7 @@ generate_plots_on_HRMS_data(
 
 print('\n\ntest #4:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         similarity_measure='tsallis',
         entropy_dimension=1.2,
@@ -41,7 +41,7 @@ generate_plots_on_HRMS_data(
 
 print('\n\ntest #5:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         similarity_measure='tsallis',
         entropy_dimension=1.2,
@@ -49,7 +49,7 @@ generate_plots_on_HRMS_data(
 
 print('\n\ntest #6:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         wf_intensity=0.8,
         wf_mz=1.1,
@@ -57,21 +57,21 @@ generate_plots_on_HRMS_data(
 
 print('\n\ntest #7:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         window_size_centroiding=0.1,
         output_path=f'{Path.cwd()}/plots/test7.pdf')
 
 print('\n\ntest #8:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         window_size_matching=0.25,
         output_path=f'{Path.cwd()}/plots/test8.pdf')
 
 print('\n\ntest #9:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         spectrum_preprocessing_order='WCM',
         wf_mz=0.8,
@@ -80,14 +80,14 @@ generate_plots_on_HRMS_data(
 
 print('\n\ntest #10:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         LET_threshold=3,
         output_path=f'{Path.cwd()}/plots/test10.pdf')
 
 print('\n\ntest #11:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         spectrum_ID1 = 212,
         spectrum_ID2 = 100,
@@ -96,7 +96,7 @@ generate_plots_on_HRMS_data(
 
 print('\n\ntest #12:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         spectrum_ID1 = 'Jamaicamide A M+H',
         spectrum_ID2 = 'Malyngamide J M+H',
@@ -105,7 +105,7 @@ generate_plots_on_HRMS_data(
 
 print('\n\ntest #13:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         spectrum_ID1 = 'Jamaicamide A M+H',
         spectrum_ID2 = 'Jamaicamide A M+H',
@@ -114,13 +114,13 @@ generate_plots_on_HRMS_data(
 
 print('\n\ntest #14:')
 generate_plots_on_NRMS_data(
-        query_data=f'{Path.cwd()}/data/gcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/gcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
         output_path=f'{Path.cwd()}/plots/test14.pdf')
 
 print('\n\ntest #15:')
 generate_plots_on_NRMS_data(
-        query_data=f'{Path.cwd()}/data/gcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/gcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
         spectrum_ID1 = 463514,
         spectrum_ID2 = 112312,
@@ -128,40 +128,40 @@ generate_plots_on_NRMS_data(
 
 print('\n\ntest #17:')
 generate_plots_on_NRMS_data(
-        query_data=f'{Path.cwd()}/data/gcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/gcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
         output_path=f'{Path.cwd()}/plots/test17.pdf')
 
 print('\n\ntest #18:')
 generate_plots_on_NRMS_data(
-        query_data=f'{Path.cwd()}/data/gcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/gcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
         y_axis_transformation='none',
         output_path=f'{Path.cwd()}/plots/test18.pdf')
 
 print('\n\ntest #19:')
 generate_plots_on_NRMS_data(
-        query_data=f'{Path.cwd()}/data/gcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/gcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
         y_axis_transformation='log10',
         output_path=f'{Path.cwd()}/plots/test19.pdf')
 
 print('\n\ntest #20:')
 generate_plots_on_NRMS_data(
-        query_data=f'{Path.cwd()}/data/gcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/gcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
         y_axis_transformation='sqrt',
         output_path=f'{Path.cwd()}/plots/test20.pdf')
 
 print('\n\ntest #21:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         output_path=f'{Path.cwd()}/plots/test_no_wf_normalized_y_axis_no_mz_zoom.pdf')
 
 print('\n\ntest #22:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         wf_mz=2,
         wf_intensity=0.5,
@@ -169,21 +169,21 @@ generate_plots_on_HRMS_data(
 
 print('\n\ntest #23:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         y_axis_transformation='log10',
         output_path=f'{Path.cwd()}/plots/test_no_wf_log10_y_axis_no_mz_zoom.pdf')
 
 print('\n\ntest #24:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         y_axis_transformation='sqrt',
         output_path=f'{Path.cwd()}/plots/test_no_wf_sqrt_y_axis_no_mz_zoom.pdf')
 
 print('\n\ntest #25:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         mz_min = 400,
         mz_max = 650,
@@ -192,49 +192,49 @@ generate_plots_on_HRMS_data(
 
 print('\n\ntest #26:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         high_quality_reference_library=False,
         output_path=f'{Path.cwd()}/plots/test_HRMS.pdf')
 
 print('\n\ntest #27:')
 generate_plots_on_NRMS_data(
-        query_data=f'{Path.cwd()}/data/gcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/gcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
         high_quality_reference_library=False,
         output_path=f'{Path.cwd()}/plots/test_NRMS.pdf')
 
 print('\n\ntest #28:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         similarity_measure='jaccard',
         output_path=f'{Path.cwd()}/plots/test28.pdf')
 
 print('\n\ntest #28:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         similarity_measure='hamming',
         output_path=f'{Path.cwd()}/plots/test28.pdf')
 
 print('\n\ntest #29:')
 generate_plots_on_NRMS_data(
-        query_data=f'{Path.cwd()}/data/gcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/gcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
         similarity_measure='sokal_sneath',
         output_path=f'{Path.cwd()}/plots/test29.pdf')
 
 print('\n\ntest #30:')
 generate_plots_on_NRMS_data(
-        query_data=f'{Path.cwd()}/data/gcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/gcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
         similarity_measure='simpson',
         output_path=f'{Path.cwd()}/plots/test30.pdf')
 
 print('\n\ntest #31:')
 generate_plots_on_NRMS_data(
-        query_data=f'{Path.cwd()}/data/gcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/gcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_gcms_reference_library.txt',
         similarity_measure='mixture',
         weights={'Cosine':0.5, 'Shannon':0.3, 'Renyi':0.1, 'Tsallis':0.1},
@@ -242,9 +242,42 @@ generate_plots_on_NRMS_data(
 
 print('\n\ntest #32:')
 generate_plots_on_HRMS_data(
-        query_data=f'{Path.cwd()}/data/lcms_query_library.txt',
+        query_data=f'{Path.cwd()}/data/lcms_query.txt',
         reference_data=f'{Path.cwd()}/data/trimmed_GNPS_reference_library.txt',
         similarity_measure='mixture',
         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')
+