pycompound 0.1.6__py3-none-any.whl → 0.1.7__py3-none-any.whl

pycompound/build_library.py

@@ -6,18 +6,19 @@ from pathlib import Path
 from pyteomics import mgf
 from pyteomics import mzml
 import sys
+import json
 
 def build_library_from_raw_data(input_path=None, output_path=None, is_reference=False):
     '''
-    Converts mgf, mzML, cdf, or msp file to the necessary format for spectral library matching.
+    Converts mgf, mzML, cdf, json, or msp file to the necessary format for spectral library matching.
 
-    --input_path: Path to input file (must be mgf, mzML, cdf, or msp file). Mandatory argument.
+    --input_path: Path to input file (must be mgf, mzML, cdf, json, or msp file). Mandatory argument.
     --output_path: Path to output TXT file. Default: current working directory.
     --is_reference: Boolean flag indicating whether IDs of spectra should be written to output. Only pass true if building a reference library with known compound IDs. Only applicable to mgf and msp files. Options: \'True\', \'False\'. Optional argument. Default: False.
     '''
 
     if input_path is None:
-        print('Error: please specify input_path (i.e. the path to the input mgf, mzML, cdf, or msp file). Mandatory argument.')
+        print('Error: please specify input_path (i.e. the path to the input mgf, mzML, cdf, json, or msp file). Mandatory argument.')
         sys.exit()
 
     if output_path is None:
@@ -37,18 +38,21 @@ def build_library_from_raw_data(input_path=None, output_path=None, is_reference=
         input_file_type = 'mgf'
     elif last_four_chars == 'mzML' or last_four_chars == 'mzml' or last_four_chars == 'MZML':
         input_file_type = 'mzML'
+    elif last_four_chars == 'json' or last_four_chars == 'JSON':
+        input_file_type = 'json'
     elif last_three_chars == 'cdf' or last_three_chars == 'CDF':
         input_file_type = 'cdf'
     elif last_three_chars == 'msp' or last_three_chars == 'MSP':
         input_file_type = 'msp'
     else:
-        print('ERROR: either an \'mgf\', \'mzML\', \'cdf\', or \'msp\' file must be passed to --input_path')
+        print('ERROR: either an \'mgf\', \'mzML\', \'cdf\', \'json\', or \'msp\' file must be passed to --input_path')
         sys.exit()
 
 
     spectra = []
     if input_file_type == 'mgf':
-        with mgf.read(input_path, index_by_scans = True) as reader:
+        #with mgf.read(input_path, index_by_scans = True) as reader:
+        with mgf.read(input_path, use_index=False) as reader:
             for spec in reader:
                 spectra.append(spec)
     if input_file_type == 'mzML':
@@ -61,18 +65,24 @@ def build_library_from_raw_data(input_path=None, output_path=None, is_reference=
         ids = []
         mzs = []
         ints = []
+        precursor_ion_mzs = []
         for i in range(0,len(spectra)):
             for j in range(0,len(spectra[i]['m/z array'])):
                 if input_file_type == 'mzML':
-                    ids.append(f'ID_{i+1}')
-                else:
                     if is_reference == False:
                         ids.append(f'ID_{i+1}')
-                    elif is_reference == True:
+                    else:
+                        ids.append(spectra[i]['id'])
+                elif input_file_type == 'mgf':
+                    precursor_ion_mzs.append(spectra[i]['params']['pepmass'][0])
+                    if is_reference == False:
+                        ids.append(f'ID_{i+1}')
+                    else:
                         ids.append(spectra[i]['params']['name'])
                 mzs.append(spectra[i]['m/z array'][j])
                 ints.append(spectra[i]['intensity array'][j])
 
+
     if input_file_type == 'cdf':
         dataset = nc.Dataset(input_path, 'r')
         all_mzs = dataset.variables['mass_values'][:]
@@ -98,31 +108,78 @@ def build_library_from_raw_data(input_path=None, output_path=None, is_reference=
                 ints.append(ints_tmp[j])
 
 
-    if input_file_type == 'msp':
+
+    if input_file_type == "msp":
         ids = []
         mzs = []
         ints = []
-        with open(input_path, 'r') as f:
+        precursor_ion_mzs = []
+        spectrum_id = None
+        precursor_ion_mz = None
+        with open(input_path, "r", encoding="utf-8", errors="ignore") as f:
             i = 0
             for line in f:
                 line = line.strip()
-                if line.startswith('Name:'):
+                if not line:
+                    continue
+
+                if line.startswith("Name:"):
                     i += 1
-                    if is_reference == False:
-                        spectrum_id = f'ID_{i+1}'
-                    elif is_reference == True:
-                        spectrum_id = line.replace('Name: ','')
-                elif line and line[0].isdigit():
+                    if not is_reference:
+                        spectrum_id = f"ID_{i}"
+                    else:
+                        spectrum_id = line.replace("Name:", "", 1).strip()
+
+                elif line.startswith("PrecursorMZ:"):
+                    try:
+                        precursor_ion_mz = float(line.replace("PrecursorMZ:", "", 1).strip())
+                    except ValueError:
+                        precursor_ion_mz = None
+
+                elif line[0].isdigit():
                     try:
                         mz, intensity = map(float, line.split()[:2])
-                        ids.append(spectrum_id)
-                        mzs.append(mz)
-                        ints.append(intensity)
                     except ValueError:
                         continue
 
+                    if spectrum_id is None:
+                        continue
+
+                    ids.append(spectrum_id)
+                    mzs.append(mz)
+                    ints.append(intensity)
+                    precursor_ion_mzs.append(precursor_ion_mz)
+
+
+
+    if input_file_type == 'json':
+        data = json.load(open(input_path))
+        ids = []
+        mzs = []
+        ints = []
+        precursor_ion_mzs = []
+        for i in range(0,len(data)):
+            spec_ID_tmp = data[i]['spectrum_id']
+            tmp = data[i]['peaks_json']
+            tmp = tmp[1:-1].split(",")
+            tmp = [a.replace("[","") for a in tmp]
+            tmp = [a.replace("]","") for a in tmp]
+            mzs_tmp = tmp[0::2]
+            ints_tmp = tmp[1::2]
+            if is_reference == False:
+                ids.extend([f'ID_{i+1}'] * len(mzs_tmp))
+            elif is_reference == True:
+                ids.extend([spec_ID_tmp] * len(mzs_tmp))
+            mzs.extend(mzs_tmp)
+            ints.extend(ints_tmp)
+            precursor_ion_mzs.extend([data[i]['Precursor_MZ']] * len(mzs_tmp))
+
+
+    if len(precursor_ion_mzs) > 0:
+        df = pd.DataFrame({'id':ids, 'mz_ratio':mzs, 'intensity':ints, 'precursor_ion_mz':precursor_ion_mzs})
+    else:
+        df = pd.DataFrame({'id':ids, 'mz_ratio':mzs, 'intensity':ints})
 
-    df = pd.DataFrame({'id':ids, 'mz_ratio':mzs, 'intensity':ints})
     df.to_csv(output_path, index=False, sep='\t')
 
 

pycompound/plot_spectra.py

@@ -315,7 +315,7 @@ def generate_plots_on_HRMS_data(query_data=None, reference_data=None, spectrum_I
     plt.savefig(output_path, format='pdf')
 
     if return_plot == True:
-        return plt
+        return fig 
 
 
 

pycompound/processing.py

@@ -295,13 +295,13 @@ def get_reference_df(reference_data, likely_reference_IDs=None):
     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':
-        output_path_tmp = reference_data[:-3] + 'csv'
+        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)
-    if extension == 'csv' or extension == 'CSV':
-        df_reference = pd.read_csv(reference_data)
+        df_reference = pd.read_csv(output_path_tmp, sep='\t')
+    if extension == 'txt' or extension == 'TXT':
+        df_reference = pd.read_csv(reference_data, sep='\t')
     if likely_reference_IDs is not None:
-        likely_reference_IDs = pd.read_csv(likely_reference_IDs, header=None)
+        likely_reference_IDs = pd.read_csv(likely_reference_IDs, header=None, sep='\t')
         df_reference = df_reference.loc[df_reference.iloc[:,0].isin(likely_reference_IDs.iloc[:,0].tolist())]
     return df_reference