feat: integrate LFQ and TMT workflows (#27)

* feat: LFQ/TMT Integration

* fix: resolve merge conflicts and add tool_instance-name support to run_topp

Author: hjn0415a

app.py

@@ -27,7 +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="🧪"),
+            st.Page(Path("content", "results_pathway_analysis.py"), title="Pathway Analysis", icon="📉"),
         ],
     }
 

content/results_abundance.py

@@ -4,6 +4,7 @@
 from pathlib import Path
 from src.common.common import page_setup
 from src.common.results_helpers import get_workflow_dir, get_abundance_data
+from src.workflow.ParameterManager import ParameterManager
 
 params = page_setup()
 st.title("Abundance Quantification")
@@ -21,6 +22,10 @@
 
 workflow_dir = get_workflow_dir(st.session_state["workspace"])
 quant_dir = workflow_dir / "results" / "quant_results"
+parameter_manager = ParameterManager(workflow_dir, "TOPP Workflow")
+
+workflow_params = parameter_manager.get_parameters_from_json() 
+analysis_mode = workflow_params.get("analysis-mode", "LFQ")
 
 if not quant_dir.exists():
     st.info("No quantification results available yet. Please run the workflow first.")
@@ -35,6 +40,60 @@
 
 csv_file = csv_files[0]
 
+def render_protein_table(pivot_df, group_map, is_lfq=True):
+    """Common function to render the protein-level abundance table"""
+    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."
+    )
+
+    # Display group comparison info
+    groups = sorted(set(group_map.values()))
+    if len(groups) >= 2:
+        group1, group2 = sorted(groups)[:2]
+        st.info(f"Statistical comparison: **{group2} vs {group1}**")
+
+    if is_lfq:
+        # Handle LFQ mode columns (Raw Intensity)
+        id_col = "ProteinName"
+        exclude_cols = [id_col, "log2FC", "p-value", "PeptideSequence"]
+        sample_cols = [c for c in pivot_df.columns if c not in exclude_cols]
+        
+        pivot_df["Intensity"] = pivot_df[sample_cols].apply(list, axis=1)
+        display_cols = [id_col, "log2FC", "p-value", "Intensity"] + sample_cols + ["PeptideSequence"]
+        help_text = "Raw sample intensities"
+        y_min = None
+    else:
+        # Handle non-LFQ mode columns (Log2-transformed Intensity)
+        id_col = "protein"
+        exclude_cols = [id_col, "log2FC", "p-value", "p-adj", "n_proteins", "n_peptides", "protein_score"]
+        sample_cols = [c for c in pivot_df.columns if c not in exclude_cols and "ratio" not in c.lower()]
+        
+        pivot_df["Intensity"] = pivot_df[sample_cols].apply(
+            lambda row: [np.log2(v + 1) for v in row], axis=1
+        )
+        display_cols = [id_col, "log2FC", "p-value", "Intensity"] + sample_cols
+        help_text = "Sample intensities (log2 scale)"
+        y_min = 0
+
+    # Filter to available columns, then sort and display
+    available_cols = [c for c in display_cols if c in pivot_df.columns]
+    
+    st.dataframe(
+        pivot_df[available_cols].sort_values("p-value"),
+        column_config={
+            "Intensity": st.column_config.BarChartColumn(
+                "Intensity",
+                help=help_text,
+                width="small",
+                y_min=y_min,
+            ),
+        },
+        use_container_width=True,
+    )
+
 protein_tab, psm_tab = st.tabs(["Protein Table", "PSM-level Quantification Table"])
 
 try:
@@ -44,58 +103,44 @@
         st.info("No data found in this file.")
         st.stop()
 
-    with protein_tab:
-        st.markdown("### Protein-Level Abundance Table")
+    result = get_abundance_data(st.session_state["workspace"])
 
-        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 analysis_mode == "LFQ":
+        protein_tab, psm_tab = st.tabs(["Protein Table", "PSM-level Quantification Table"])
 
-        result = get_abundance_data(st.session_state["workspace"])
-        if result is None:
-            st.warning("Could not compute abundance data. Please ensure sample groups are defined in the Configure page.")
-            st.page_link("content/workflow_configure.py", label="Go to Configure", icon="⚙️")
-            st.stop()
+        with protein_tab:
+            if result is None:
+                st.warning("Could not compute abundance data. Please ensure sample groups are defined in the Configure page.")
+                # st.page_link("content/workflow_configure.py", label="Go to Configure", icon="⚙️")
+                st.stop()
+            
+            pivot_df, expr_df, group_map = result
+            render_protein_table(pivot_df, group_map, is_lfq=True)
 
-        pivot_df, expr_df, group_map = result
+        with psm_tab:
+            st.markdown("### PSM-level Quantification Table")
+            st.info(
+                "This table shows the PSM-level quantification data, including protein IDs, "
+                "peptide sequences, charge states, and intensities across samples. "
+                "Each row represents one peptide-spectrum match detected from the MS/MS analysis."
+            )
+            st.dataframe(df, use_container_width=True)
 
-        # Display group comparison info
-        groups = sorted(set(group_map.values()))
-        if len(groups) >= 2:
-            group1, group2 = sorted(groups)[:2]
-            st.info(f"Statistical comparison: **{group2} vs {group1}**")
+    else:
+        pre_processing_tab, protein_tab = st.tabs(["Pre-processing", "Protein Table"])
 
-        # Get sample columns (between stats and PeptideSequence)
-        sample_cols = [c for c in pivot_df.columns if c not in ["ProteinName", "log2FC", "p-value", "PeptideSequence"]]
-
-        pivot_df["Intensity"] = pivot_df[sample_cols].apply(list, axis=1)
+        if result is None:
+            st.info("💡 Please complete the configuration in the 'Configure' page to see results.")
+            st.stop()
+            
+        pivot_df, expr_df, group_map = result
 
-        # Reorder columns: place Intensity after p-value
-        display_cols = ["ProteinName", "log2FC", "p-value", "Intensity"] + sample_cols + ["PeptideSequence"]
-        display_df = pivot_df[display_cols]
-
-        st.dataframe(
-            display_df.sort_values("p-value"),
-            column_config={
-                "Intensity": st.column_config.BarChartColumn(
-                    "Intensity",
-                    help="Raw sample intensities",
-                    width="small",
-                ),
-            },
-            use_container_width=True,
-        )
+        with pre_processing_tab:
+            st.write("### Final Results (Group row removed, Stats added)")
+            st.dataframe(pivot_df.head(10))
 
-    with psm_tab:
-        st.markdown("### PSM-level Quantification Table")
-        st.info(
-            "This table shows the PSM-level quantification data, including protein IDs, "
-            "peptide sequences, charge states, and intensities across samples. "
-            "Each row represents one peptide-spectrum match detected from the MS/MS analysis."
-        )
-        st.dataframe(df, use_container_width=True)
+        with protein_tab:
+            render_protein_table(pivot_df, group_map, is_lfq=False)
 
 except Exception as e:
     st.error(f"Failed to load {csv_file.name}: {e}")

content/results_heatmap.py

@@ -5,7 +5,8 @@
 from scipy.cluster.hierarchy import linkage, leaves_list
 from scipy.spatial.distance import pdist
 from src.common.common import page_setup
-from src.common.results_helpers import get_abundance_data
+from src.common.results_helpers import get_abundance_data, get_workflow_dir
+from src.workflow.ParameterManager import ParameterManager
 
 params = page_setup()
 st.title("Heatmap")
@@ -29,48 +30,103 @@
 
 pivot_df, expr_df, group_map = result
 
-top_n = st.slider("Number of proteins", 20, 200, 50, key="heatmap_top_n")
+workflow_dir = get_workflow_dir(st.session_state["workspace"])
+parameter_manager = ParameterManager(workflow_dir, "TOPP Workflow")
 
-var_series = expr_df.var(axis=1)
-top_proteins = var_series.sort_values(ascending=False).head(top_n).index
-heatmap_df = expr_df.loc[top_proteins]
-heatmap_z = heatmap_df.sub(heatmap_df.mean(axis=1), axis=0).div(heatmap_df.std(axis=1), axis=0)
-heatmap_z = heatmap_z.replace([np.inf, -np.inf], np.nan).dropna()
+workflow_params = parameter_manager.get_parameters_from_json() 
+analysis_mode = workflow_params.get("analysis-mode", "LFQ")
 
-if not heatmap_z.empty:
-    row_linkage = linkage(pdist(heatmap_z.values), method="average")
-    row_order = leaves_list(row_linkage)
+st.write("Workflow Analysis Mode:", analysis_mode)
 
-    col_linkage = linkage(pdist(heatmap_z.T.values), method="average")
-    col_order = leaves_list(col_linkage)
+if analysis_mode == "LFQ":
+    top_n = st.slider("Number of proteins", 20, 200, 50, key="heatmap_top_n")
 
-    heatmap_clustered = heatmap_z.iloc[row_order, col_order]
+    var_series = expr_df.var(axis=1)
+    top_proteins = var_series.sort_values(ascending=False).head(top_n).index
+    heatmap_df = expr_df.loc[top_proteins]
+    heatmap_z = heatmap_df.sub(heatmap_df.mean(axis=1), axis=0).div(heatmap_df.std(axis=1), axis=0)
+    heatmap_z = heatmap_z.replace([np.inf, -np.inf], np.nan).dropna()
 
-    fig_heatmap = px.imshow(
-        heatmap_clustered,
-        labels=dict(x="Sample", y="Protein", color="Z-score"),
-        aspect="auto",
-        color_continuous_scale=[[0.0, "#3b6fb6"], [0.5, "white"], [1.0, "#b40426"]],
-        zmin=-3, zmax=3
-    )
+    if not heatmap_z.empty:
+        row_linkage = linkage(pdist(heatmap_z.values), method="average")
+        row_order = leaves_list(row_linkage)
 
-    fig_heatmap.update_layout(
-        height=700,
-        xaxis={'side': 'bottom'},
-        yaxis={'side': 'left'}
-    )
+        col_linkage = linkage(pdist(heatmap_z.T.values), method="average")
+        col_order = leaves_list(col_linkage)
 
-    fig_heatmap.update_xaxes(tickfont=dict(size=10))
-    fig_heatmap.update_yaxes(tickfont=dict(size=8))
+        heatmap_clustered = heatmap_z.iloc[row_order, col_order]
 
-    st.plotly_chart(fig_heatmap, use_container_width=True)
+        fig_heatmap = px.imshow(
+            heatmap_clustered,
+            labels=dict(x="Sample", y="Protein", color="Z-score"),
+            aspect="auto",
+            color_continuous_scale=[[0.0, "#3b6fb6"], [0.5, "white"], [1.0, "#b40426"]],
+            zmin=-3, zmax=3
+        )
+
+        fig_heatmap.update_layout(
+            height=700,
+            xaxis={'side': 'bottom'},
+            yaxis={'side': 'left'}
+        )
+
+        fig_heatmap.update_xaxes(tickfont=dict(size=10))
+        fig_heatmap.update_yaxes(tickfont=dict(size=8))
+
+        st.plotly_chart(fig_heatmap, use_container_width=True)
+    else:
+        st.warning("Insufficient data to generate the heatmap.")
+
+    st.markdown("---")
+    st.markdown("**Other visualizations:**")
+    col1, col2 = st.columns(2)
+    with col1:
+        st.page_link("content/results_volcano.py", label="Volcano Plot", icon="🌋")
+    with col2:
+        st.page_link("content/results_pca.py", label="PCA", icon="📊")
 else:
-    st.warning("Insufficient data to generate the heatmap.")
-
-st.markdown("---")
-st.markdown("**Other visualizations:**")
-col1, col2 = st.columns(2)
-with col1:
-    st.page_link("content/results_volcano.py", label="Volcano Plot", icon="🌋")
-with col2:
-    st.page_link("content/results_pca.py", label="PCA", icon="📊")
+    top_n = st.slider("Number of proteins", 20, 200, 50, key="heatmap_top_n")
+
+    var_series = expr_df.var(axis=1)
+    top_proteins = var_series.sort_values(ascending=False).head(top_n).index
+    heatmap_df = expr_df.loc[top_proteins]
+    heatmap_z = heatmap_df.sub(heatmap_df.mean(axis=1), axis=0).div(heatmap_df.std(axis=1), axis=0)
+    heatmap_z = heatmap_z.replace([np.inf, -np.inf], np.nan).dropna()
+
+    if not heatmap_z.empty:
+        row_linkage = linkage(pdist(heatmap_z.values), method="average")
+        row_order = leaves_list(row_linkage)
+
+        col_linkage = linkage(pdist(heatmap_z.T.values), method="average")
+        col_order = leaves_list(col_linkage)
+
+        heatmap_clustered = heatmap_z.iloc[row_order, col_order]
+
+        fig_heatmap = px.imshow(
+            heatmap_clustered,
+            labels=dict(x="Sample", y="Protein", color="Z-score"),
+            aspect="auto",
+            color_continuous_scale=[[0.0, "#3b6fb6"], [0.5, "white"], [1.0, "#b40426"]],
+            zmin=-3, zmax=3
+        )
+
+        fig_heatmap.update_layout(
+            height=700,
+            xaxis={'side': 'bottom'},
+            yaxis={'side': 'left'}
+        )
+
+        fig_heatmap.update_xaxes(tickfont=dict(size=10))
+        fig_heatmap.update_yaxes(tickfont=dict(size=8))
+
+        st.plotly_chart(fig_heatmap, width="stretch")
+    else:
+        st.warning("Insufficient data to generate the heatmap.")
+
+    st.markdown("---")
+    st.markdown("**Other visualizations:**")
+    col1, col2 = st.columns(2)
+    with col1:
+        st.page_link("content/results_volcano.py", label="Volcano Plot", icon="🌋")
+    with col2:
+        st.page_link("content/results_pca.py", label="PCA", icon="📊")