Merge pull request #571 from bigbio/dev

Fixing the bug for big datasets.

Author: ypriverol

CITATION.cff

@@ -42,7 +42,7 @@ authors:
 repository-code: "https://github.com/bigbio/pmultiqc"
 url: "https://github.com/bigbio/pmultiqc"
 license: MIT
-version: 0.0.40
+version: 0.0.41
 identifiers:
   - type: doi
     value: 10.1101/2025.11.02.685980

README.md

@@ -60,8 +60,12 @@ pmultiqc supports the following data sources:
    - `*.mzid`: Identification results
    - `*.mzML` or `*.mgf`: Corresponding spectra files
 
-6. **[FragPipe](https://fragpipe.nesvilab.org)** files:
-   - `psm.tsv`: FragPipe report files
+6. **[FragPipe](https://fragpipe.nesvilab.org)** main report files:
+   - `psm.tsv`: FDR-filtered PSMs
+   - `ion.tsv`: FDR-filtered ions
+   - `combined_ion.tsv`: FDR-filtered ions
+   - `combined_peptide.tsv`: FDR-filtered peptides
+   - `combined_protein.tsv`: FDR-filtered proteins
 
 ## Installation
 

docs/README.md

@@ -81,7 +81,11 @@ pmultiqc supports the following data sources:
    - `*.mzML` or `*.mgf`: Corresponding spectra files
 
 ### 6. [FragPipe](https://fragpipe.nesvilab.org) files:
-   - `psm.tsv`: FragPipe report file
+   - `psm.tsv`: FDR-filtered PSMs
+   - `ion.tsv`: FDR-filtered ions
+   - `combined_ion.tsv`: FDR-filtered ions
+   - `combined_peptide.tsv`: FDR-filtered peptides
+   - `combined_protein.tsv`: FDR-filtered proteins
 
 ## 💾 Installation
 

pmultiqc/modules/common/common_utils.py

@@ -595,6 +595,9 @@ def aggregate_general_stats(
     sdrf_file_df
 ):
 
+    if not ms1_general_stats:
+        return None
+
     if sdrf_file_df.empty:
 
         rows_by_group = dict()

pmultiqc/modules/common/dia_utils.py

@@ -1,7 +1,6 @@
 import itertools
 import numpy as np
 import pandas as pd
-import os
 import re
 from collections import OrderedDict
 from sdrf_pipelines.openms.openms import UnimodDatabase

pmultiqc/modules/common/plots/id.py

@@ -857,10 +857,35 @@ def draw_identi_num(
 
 def draw_modifications(sub_section, modified_data):
 
-    if isinstance(modified_data["plot_data"], list):
+    plot_data = modified_data.get("plot_data", None)
+    if not plot_data:
+        return
+
+    if isinstance(plot_data, dict):
+        iterable = [plot_data]
+        plot_label = ["by Run"]
+    elif isinstance(plot_data, list):
+        iterable = plot_data
         plot_label = ["by Run", "by Sample"]
     else:
-        plot_label = ["by Run"]
+        log.warning(
+            f"draw_modifications: Unsupported plot_data type: {type(plot_data)}, skipping plot."
+        )
+        return
+
+    modified_values = [
+        value
+        for item in iterable
+        if isinstance(item, dict)
+        for subdict in item.values()
+        if isinstance(subdict, dict)
+        for value in subdict.values()
+        if isinstance(value, (int, float))
+    ]
+
+    if not any(modified_values):
+        log.warning("draw_modifications: All plot_data values are zero, skipping plot.")
+        return
 
     draw_config = {
         "id": "modifications",
@@ -875,7 +900,7 @@ def draw_modifications(sub_section, modified_data):
     }
 
     bar_html = bargraph.plot(
-        data=modified_data["plot_data"], cats=modified_data["cats"], pconfig=draw_config
+        data=plot_data, cats=modified_data["cats"], pconfig=draw_config
     )
     bar_html = plot_html_check(bar_html)
 

pyproject.toml

@@ -3,7 +3,7 @@ name = "pmultiqc"
 description = "Python package for quality control of proteomics datasets, based on multiqc package"
 readme = "README.md"
 license = "MIT"
-version = "0.0.40"
+version = "0.0.41"
 authors = [
     "Yasset Perez-Riverol <[email protected]>",
     "Dai Chengxin <[email protected]>",

recipe/meta.yaml

@@ -1,6 +1,6 @@
 # recipe/meta.yaml
 {% set name = "pmultiqc" %}
-{% set version = "0.0.40" %}
+{% set version = "0.0.41" %}
 
 package:
   name: {{ name }}