Merge pull request #90 from daichengxin/main

support .d and disable beeswarm

pmultiqc/main.py

@@ -43,8 +43,8 @@ def pmultiqc_plugin_execution_start():
     if 'quantms/mzML' not in config.sp:
         config.update_dict(config.sp, {'quantms/mzML': {'fn': '*.mzML', 'num_lines': 0}})
 
-    if 'quantms/mzml_info' not in config.sp:
-        config.update_dict(config.sp, {'quantms/mzml_info': {'fn': '*_mzml_info.tsv', 'num_lines': 0}})
+    if 'quantms/ms_info' not in config.sp:
+        config.update_dict(config.sp, {'quantms/ms_info': {'fn': '*_ms_info.tsv', 'num_lines': 0}})
 
     if 'quantms/idXML' not in config.sp:
         config.update_dict(config.sp, {'quantms/idXML': {'fn': '*.idXML', 'num_lines': 0}})

pmultiqc/modules/quantms/ms_functions.py

@@ -0,0 +1,47 @@
+"""
+======================
+@author:Chengxin Dai
+
+@time:2023/10/23:17:25
+
+======================
+"""
+import pandas as pd
+
+# The time resulution in seconds.
+# Larger values will result in smaller data files as outputs
+# and will slightly smooth the data. 5 seconds seems to be
+# a good value for qc purposes.
+SECOND_RESOLUTION = 5
+
+
+def get_ms_qc_info(ms_info: pd.DataFrame):
+    """
+    Note that here I am using min and not mean for purely qc reasons.
+    Since the diagnostic aspect here is mainly to see major fluctuations
+    in the intensity, and usually these are scans with very low intensity
+    due to bubbles or ionization issues, thus the mean would hide that.
+
+    @param ms_info:
+    @return:
+    """
+    ms1_info = ms_info[ms_info["MSLevel"] == 1]
+    ms2_info = ms_info[ms_info["MSLevel"] == 2]
+    ms1_info["rt_normalize"] = (ms1_info.sort_values(by="Retention_Time")["Retention_Time"] / SECOND_RESOLUTION).astype(
+        int)
+    tic_data = ms1_info.groupby("rt_normalize")[["Retention_Time", "Summed_Peak_Intensities"]].min()
+    tic_data = dict(zip(tic_data["Retention_Time"], tic_data["Summed_Peak_Intensities"]))
+
+    bpc_data = dict(zip(ms1_info.groupby("rt_normalize")["Retention_Time"].min(),
+                        ms1_info.groupby("rt_normalize")["Summed_Peak_Intensities"].max()))
+
+    ms1_peaks = dict(zip(ms1_info.groupby("rt_normalize")["Retention_Time"].min(),
+                         ms1_info.groupby("rt_normalize")["MS_peaks"].mean()))
+
+    general_stats = {
+            "AcquisitionDateTime": ms1_info["AcquisitionDateTime"][0],
+            "TotalCurrent": ms1_info["Summed_Peak_Intensities"].sum(),
+            "ScanCurrent": ms2_info["Summed_Peak_Intensities"].sum()
+    }
+
+    return tic_data, bpc_data, ms1_peaks, general_stats