refactor: decouple GO enrichment logic and improve data flow safety

app.py

@@ -27,6 +27,7 @@
             st.Page(Path("content", "results_pca.py"), title="PCA", icon="📊"),
             st.Page(Path("content", "results_heatmap.py"), title="Heatmap", icon="🔥"),
             st.Page(Path("content", "results_library.py"), title="Spectral Library", icon="📚"),
+            st.Page(Path("content", "results_proteomicslfq.py"), title="Proteomics LFQ", icon="🧪"),
         ],
     }
 

content/results_pca.py

@@ -33,8 +33,8 @@
 
 top_proteins = (
     pivot_df
-    .dropna(subset=["p-value"])
-    .sort_values("p-value", ascending=True)
+    .dropna(subset=["p-adj"])
+    .sort_values("p-adj", ascending=True)
     .head(top_n)["ProteinName"]
 )
 
@@ -81,7 +81,7 @@
 
 st.plotly_chart(fig_pca, use_container_width=True)
 
-st.markdown(f"**Proteins used:** {expr_df_pca.shape[0]} (top {top_n} by p-value)")
+st.markdown(f"**Proteins used:** {expr_df_pca.shape[0]} (top {top_n} by p-adj)")
 
 st.markdown("---")
 st.markdown("**Other visualizations:**")

content/results_proteomicslfq.py

@@ -0,0 +1,101 @@
+from pathlib import Path
+import streamlit as st
+import pandas as pd
+import numpy as np
+import plotly.express as px
+
+from src.common.common import page_setup
+from src.common.results_helpers import get_abundance_data
+
+# ================================
+# Page setup
+# ================================
+params = page_setup()
+st.title("ProteomicsLFQ Results")
+
+# ================================
+# Workspace check
+# ================================
+if "workspace" not in st.session_state:
+    st.warning("Please initialize your workspace first.")
+    st.stop()
+
+# ================================
+# Load abundance data
+# ================================
+res = get_abundance_data(st.session_state["workspace"])
+if res is None:
+    st.info(
+        "Abundance data not available or incomplete. "
+        "Please run the workflow and configure sample groups first."
+    )
+    st.stop()
+
+pivot_df, expr_df, group_map = res
+
+# ================================
+# Tabs
+# ================================
+protein_tab, = st.tabs(["🧬 Protein Table"])
+
+# ================================
+# Protein-level results
+# ================================
+with protein_tab:
+    st.markdown("### 🧬 Protein-Level Abundance Table")
+    st.info(
+        "This protein-level table is generated by grouping all PSMs that map to the "
+        "same protein and aggregating their intensities across samples.\n\n"
+        "Additionally, log2 fold change and p-values are calculated between sample groups."
+    )
+
+    if pivot_df.empty:
+        st.info("No protein-level data available.")
+    else:
+        st.session_state["pivot_df"] = pivot_df
+        st.dataframe(pivot_df.sort_values("p-value"), use_container_width=True)
+
+# ======================================================
+# GO Enrichment Results 
+# ======================================================
+st.markdown("---")
+st.subheader("🧬 GO Enrichment Analysis")
+
+results_dir = Path(st.session_state["workspace"]) / "topp-workflow" / "results" / "go-terms"
+go_json_file = results_dir / "go_results.json"
+
+if not go_json_file.exists():
+    st.info("GO Enrichment results are not available yet. Please run the analysis first.")
+else:
+    import json
+    import plotly.io as pio
+
+    with open(go_json_file, "r") as f:
+        go_data = json.load(f)
+
+    bp_tab, cc_tab, mf_tab = st.tabs([
+        "🧬 Biological Process",
+        "🏠 Cellular Component",
+        "⚙️ Molecular Function",
+    ])
+
+    for tab, go_type in zip([bp_tab, cc_tab, mf_tab], ["BP", "CC", "MF"]):
+        with tab:
+            if go_type not in go_data:
+                st.info(f"No enriched {go_type} terms found.")
+                continue
+
+            fig_json = go_data[go_type]["fig_json"]
+            df_dict = go_data[go_type]["df_dict"]
+
+            fig = pio.from_json(fig_json)
+
+            df_go = pd.DataFrame(df_dict)
+
+            if df_go.empty:
+                st.info(f"No enriched {go_type} terms found.")
+            else:
+                st.plotly_chart(fig, use_container_width=True)
+
+                st.markdown(f"#### {go_type} Enrichment Results")
+                st.dataframe(df_go, use_container_width=True)

content/results_volcano.py

@@ -32,9 +32,9 @@
     st.stop()
 
 volcano_df = pivot_df.copy()
-volcano_df = volcano_df.dropna(subset=["log2FC", "p-value"])
+volcano_df = volcano_df.dropna(subset=["log2FC", "p-adj"])
 
-volcano_df["neg_log10_p"] = -np.log10(volcano_df["p-value"])
+volcano_df["neg_log10_padj"] = -np.log10(volcano_df["p-adj"])
 
 fc_thresh = st.slider(
     "log2 Fold Change threshold",
@@ -45,7 +45,7 @@
 )
 
 p_thresh = st.slider(
-    "p-value threshold",
+    "p-adj (FDR) threshold",
     min_value=0.001,
     max_value=0.1,
     value=0.05,
@@ -54,21 +54,26 @@
 
 volcano_df["Significance"] = "Not significant"
 volcano_df.loc[
-    (volcano_df["p-value"] <= p_thresh) & (volcano_df["log2FC"] >= fc_thresh),
+    (volcano_df["p-adj"] <= p_thresh) & (volcano_df["log2FC"] >= fc_thresh),
     "Significance",
 ] = "Up-regulated"
 
 volcano_df.loc[
-    (volcano_df["p-value"] <= p_thresh) & (volcano_df["log2FC"] <= -fc_thresh),
+    (volcano_df["p-adj"] <= p_thresh) & (volcano_df["log2FC"] <= -fc_thresh),
     "Significance",
 ] = "Down-regulated"
 
 fig_volcano = px.scatter(
     volcano_df,
     x="log2FC",
-    y="neg_log10_p",
+    y="neg_log10_padj",
     color="Significance",
-    hover_data=["ProteinName", "p-value"],
+    hover_data=["ProteinName", "log2FC", "p-value", "p-adj"],
+    color_discrete_map={
+        "Up-regulated": "red",
+        "Down-regulated": "blue",
+        "Not significant": "lightgrey",
+    }
 )
 
 fig_volcano.add_vline(x=fc_thresh, line_dash="dash")
@@ -81,7 +86,7 @@
 
 fig_volcano.update_layout(
     xaxis_title="log2 Fold Change",
-    yaxis_title="-log10(p-value)",
+    yaxis_title="-log10(p-adj)",
     xaxis_range=x_range,
     height=600,
 )

content/workflow_run.py

@@ -5,5 +5,4 @@
 params = page_setup()
 
 wf = WorkflowTest()
-
 wf.show_execution_section()

requirements.txt

@@ -145,7 +145,8 @@ polars>=1.0.0
 cython
 easypqp>=0.1.34
 pyprophet>=2.2.0
-
+mygene
 # Redis Queue dependencies (for online mode)
 redis>=5.0.0
 rq>=1.16.0
+statsmodels