Merge pull request #160 from bigbio/dev

Dev

Author: ypriverol

docs/LFQ_PXD007683/multiqc_report.html

@@ -23,7 +23,7 @@
 <title>MultiQC Report</title>
 
 <!-- JSON plot data -->
-<script type="text/plain" id="mqc_compressed_plotdata">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</script>
+<script type="text/plain" id="mqc_compressed_plotdata">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</script>
 
 <script type="application/json" id="mqc_config">{"decimalPoint_format": ".", "plots_num_data_points_do_not_automatically_load": 100, "sample_names_rename": [], "show_hide_mode": [], "show_hide_patterns": [], "show_hide_regex": [], "thousandsSep_format": ""}</script>
 
@@ -6974,7 +6974,7 @@ <h4>JavaScript Disabled</h4>
 <div id="analysis_dirs_wrapper">
   <p>Report
 
-    generated on 2025-04-23, 07:12 UTC
+    generated on 2025-05-08, 06:53 UTC
 
 
     based on data in:

docs/PXD003133/multiqc_report.html

@@ -0,0 +1,18 @@
+import numpy as np
+
+
+def qualUniform(group_df_rt):
+    """
+    Parameters:
+    -----------
+    group_df_rt: group["Retention time"] or group["retention_time"]
+    
+    """
+    x = group_df_rt / np.nansum(group_df_rt)
+    n = group_df_rt.notna().sum()
+    y = np.nansum(x) / n
+    worst = ((1 - y) ** 0.5) * 1 / n + (y**0.5) * (n - 1) / n
+    sc = np.sum(np.abs(x - y) ** 0.5) / n
+    result = 1.0 if worst == 0 else float((worst - sc) / worst)
+
+    return result

docs/PXD051187/multiqc_report.html

@@ -11,6 +11,7 @@
 from sklearn.preprocessing import StandardScaler
 
 from pmultiqc.modules.common.file_utils import get_filename
+from ..common.calc_utils import qualUniform
 from ...logging import get_logger, Timer
 
 # Initialize logger for this module
@@ -442,6 +443,112 @@ def get_evidence(file_path):
     return result
 
 
+# HeatMap
+def calculate_heatmap(evidence_df, oversampling, msms_missed_cleavages):
+
+    if any(x is None for x in (evidence_df, oversampling, msms_missed_cleavages)):
+        return None
+    
+    if any(
+        column not in evidence_df.columns
+        for column in ["Potential contaminant", "Intensity", "Raw file", "Retention time", "Charge"]
+    ):
+        return None
+    
+    if evidence_df[evidence_df["Potential contaminant"] == "+"].empty:
+        logger.info("The evidence.txt file does not contain any contaminants")
+
+    evidence_data = evidence_df.copy()
+
+    # 8. Pep Missing Values
+    global_peps = evidence_df["Modified sequence"].unique()
+    global_peps_count = len(global_peps)
+
+    heatmap_dict = dict()
+    for raw_file, group in evidence_data[
+        [
+            "Potential contaminant", "Intensity", "Retention time",
+            "Raw file", "Modified sequence"
+            ]
+        ].groupby("Raw file"):
+
+        # 1. Contaminants
+        contaminant = 1 - (group[group["Potential contaminant"] == "+"]["Intensity"].sum() 
+                           / group["Intensity"].sum())
+        
+        # 2. Peptide Intensity
+        peptide_intensity = np.minimum(1.0, np.nanmedian(group["Intensity"]) / (2**23))
+
+        # 8. Pep Missing Values
+        pep_missing_values = np.minimum(
+            1.0,
+            len(set(global_peps) & set(group["Modified sequence"].unique())) / global_peps_count
+        )
+
+        heatmap_dict[raw_file] = {
+            "Contaminants": contaminant,
+            "Peptide Intensity": peptide_intensity,
+            "ID rate over RT": qualUniform(group["Retention time"]),      # 6. ID rate over RT
+            "Pep Missing Values": pep_missing_values,
+        }
+
+    # 4. Missed Cleavages
+    missed_cleavages = {key: value["0"] / 100 for key, value in msms_missed_cleavages.items()}
+
+    # 5. Missed Cleavages Var
+    mc_median = np.median(list(missed_cleavages.values()))
+    missed_cleavages_var = dict(
+        zip(
+            missed_cleavages.keys(),
+            list(map(lambda v: 1 - np.abs(v - mc_median), missed_cleavages.values())),
+        )
+    )
+    for raw_file in missed_cleavages.keys():
+        heatmap_dict[raw_file]["Missed Cleavages"] = missed_cleavages[raw_file]
+        heatmap_dict[raw_file]["Missed Cleavages Var"] = missed_cleavages_var[raw_file]
+
+    # 3. Charge
+    charge = dict()
+    for raw_file, group in evidence_data.loc[
+        ~evidence_data["is_transferred"], ["Charge", "Raw file"]
+        ].groupby("Raw file"):
+        charge[raw_file] = group["Charge"].value_counts()[2] / len(group)
+    charge_median = np.median(list(charge.values()))
+    heatmap_charge = dict(
+        zip(
+            charge.keys(),
+            list(map(lambda v: 1 - np.abs(v - charge_median), charge.values())),
+        )
+    )
+    for raw_file in heatmap_charge.keys():
+        heatmap_dict[raw_file]["Charge"] = heatmap_charge[raw_file]
+
+    # 7. MS2 OverSampling
+    for raw_file, value in oversampling.items():
+        heatmap_dict[raw_file]["MS2 OverSampling"] = np.minimum(1.0, (value["1"] / 100))
+
+    # Sort the xnames
+    heatmap_xname_order = [
+        "Contaminants",
+        "Peptide Intensity",
+        "Charge",
+        "Missed Cleavages",
+        "Missed Cleavages Var",
+        "ID rate over RT",
+        "MS2 OverSampling",
+        "Pep Missing Values",
+    ]
+
+    for raw_file in heatmap_charge.keys():
+        heatmap_dict[raw_file] = {
+            key: heatmap_dict[raw_file][key]
+            for key in heatmap_xname_order
+            if key in heatmap_dict[raw_file].keys()
+        }
+
+    return heatmap_dict
+
+
 # 3-1. evidence.txt: Top Contaminants per Raw file
 def evidence_top_contaminants(evidence_df, top_n):
     if any(
@@ -450,6 +557,10 @@ def evidence_top_contaminants(evidence_df, top_n):
     ):
         return None
 
+    if evidence_df[evidence_df["Potential contaminant"] == "+"].empty:
+        logger.info("The evidence.txt file does not contain any contaminants")
+        return None
+    
     evidence_data = evidence_df.copy()
 
     if "Protein Names" in evidence_data.columns: