feat: implement full TMT analysis pipeline, result visualizations, and Windows compatibility.

app.py

@@ -8,33 +8,35 @@
         with open("settings.json", "r") as f:
             st.session_state.settings = json.load(f)
 
+# Initialize session state for workspace
+if "chosen-workspace" not in st.session_state:
+    if "workspace" in st.session_state:
+        st.session_state["chosen-workspace"] = str(st.session_state.workspace.stem)
+    else:
+        st.session_state["chosen-workspace"] = "default"
+
 if __name__ == '__main__':
     pages = {
         str(st.session_state.settings["app-name"]) : [
             st.Page(Path("content", "quickstart.py"), title="Quickstart", icon="👋"),
             st.Page(Path("content", "documentation.py"), title="Documentation", icon="📖"),
         ],
-        "pyOpenMS Toolbox": [
-            st.Page(Path("content", "digest.py"), title="In Silico Digest", icon="✂️"),
-            st.Page(Path("content", "peptide_mz_calculator.py"), title="m/z Calculator", icon="⚖️"),
-            st.Page(Path("content", "isotope_pattern_generator.py"), title="Isotopic Pattern Calculator", icon="📶"),
-            st.Page(Path("content", "fragmentation.py"), title="Fragment Ion Generation", icon="💥"),
-        ],
         "TOPP Workflow Framework": [
             st.Page(Path("content", "topp_workflow_file_upload.py"), title="File Upload", icon="📁"),
             st.Page(Path("content", "topp_workflow_parameter.py"), title="Configure", icon="⚙️"),
             st.Page(Path("content", "topp_workflow_execution.py"), title="Run", icon="🚀"),
-            st.Page(Path("content", "topp_workflow_results.py"), title="Results", icon="📊"),
-        ],
-        "pyOpenMS Workflow" : [
-            st.Page(Path("content", "file_upload.py"), title="File Upload", icon="📂"),
-            st.Page(Path("content", "raw_data_viewer.py"), title="View MS data", icon="👀"),
-            st.Page(Path("content", "run_example_workflow.py"), title="Run Workflow", icon="⚙️"),
-            st.Page(Path("content", "download_section.py"), title="Download Results", icon="⬇️"),
+            # st.Page(Path("content", "topp_workflow_results.py"), title="Results", icon="📊"),
         ],
-        "Others Topics": [
-            st.Page(Path("content", "simple_workflow.py"), title="Simple Workflow", icon="⚙️"),
-            st.Page(Path("content", "run_subprocess.py"), title="Run Subprocess", icon="🖥️"),
+        "Results": [
+            st.Page(Path("content", "results_database_search.py"), title="Database Search", icon="🔬"),
+            st.Page(Path("content", "results_rescoring.py"), title="Rescoring", icon="📈"),
+            st.Page(Path("content", "results_filtered.py"), title="Filtered PSMs", icon="🎯"),
+            st.Page(Path("content", "results_abundance.py"), title="Abundance", icon="📋"),
+            st.Page(Path("content", "results_volcano.py"), title="Volcano", icon="🌋"),
+            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_pathway.py"), title="Pathway Analysis", icon="🧪"),
         ]
     }
 

content/results_abundance.py

@@ -0,0 +1,132 @@
+"""Abundance (ProteomicsLFQ) Results Page."""
+import streamlit as st
+import pandas as pd
+import numpy as np
+from pathlib import Path
+from scipy.stats import ttest_ind
+from src.common.common import page_setup
+from statsmodels.stats.multitest import multipletests
+from src.common.results_helpers import get_workflow_dir, get_abundance_data
+
+params = page_setup()
+st.title("Abundance Quantification")
+
+st.markdown(
+    """
+View protein and PSM-level quantification from **ProteomicsLFQ**.
+This page calculates differential expression statistics between sample groups.
+"""
+)
+
+if "workspace" not in st.session_state:
+    st.warning("Please initialize your workspace first.")
+    st.stop()
+
+results_dir = Path(st.session_state["workspace"]) / "topp-workflow" / "results" / "quant_results"
+consensus_out = results_dir / "openms_design_protein_openms.csv"
+
+@st.cache_data
+def load_data(file_path):
+    return pd.read_csv(file_path, sep="\t", comment="#", engine="python")
+
+if consensus_out.exists():
+
+    # df = load_data(consensus_out)
+    # # ratio column removal
+    # df = df.loc[:, ~df.columns.str.contains('ratio', case=False)]
+
+    pre_processing_tab, protein_tab = st.tabs(["Pre-processing", "Protein Table"])
+
+    with pre_processing_tab:
+        # result = get_abundance_data(st.session_state["workspace"])
+        # DEBUG: 상세 원인 출력 (임시)
+        try:
+            result = get_abundance_data(st.session_state["workspace"])
+        except Exception as e:
+            st.exception(e)
+            result = None
+
+        if result is None:
+            ws = st.session_state.get("workspace")
+            st.error("Debug: get_abundance_data returned None")
+            st.write("workspace:", ws)
+            wf = Path(ws) / "topp-workflow"
+            st.write("workflow dir exists:", wf.exists(), "->", wf)
+            qdir = wf / "results" / "quant_results"
+            st.write("quant_dir exists:", qdir.exists(), "->", qdir)
+            if qdir.exists():
+                st.write("csv files:", sorted([p.name for p in qdir.glob('*.csv')]))
+            # show cached param snapshot if available
+            try:
+                from src.workflow.ParameterManager import ParameterManager
+                pm = ParameterManager(wf)
+                st.write("parameters keys (sample):", list(pm.get_parameters_from_json().items())[:20])
+            except Exception as e:
+                st.write("Param manager error:", e)
+            st.stop()
+
+        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
+
+        st.write("### Final Results (Group row removed, Stats added)")
+        st.dataframe(pivot_df.head(10))
+
+
+    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."
+        )
+
+        # 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}**")
+
+        exclude_cols = ["protein", "log2FC", "p-value", "p-adj", 
+                        "n_proteins", "n_peptides", "protein_score"]
+
+        # Get sample columns (between stats and PeptideSequence)
+        sample_cols = [c for c in pivot_df.columns if c 
+                        not in exclude_cols and "ratio" not in c.lower()]
+
+        # Create bar chart column with log2-transformed values
+        pivot_df["Intensity"] = pivot_df[sample_cols].apply(
+            lambda row: [np.log2(v + 1) for v in row], axis=1
+        )
+
+        # Reorder columns: place Intensity after p-value
+        display_cols = ["protein", "log2FC", "p-value", "Intensity"] + sample_cols
+        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="Sample intensities (log2 scale)",
+                    width="small",
+                    y_min=0,
+                ),
+            },
+            width="stretch"
+        )
+else:
+    st.warning(f"File not found: {consensus_out}")
+
+st.markdown("---")
+st.markdown("**Next steps:** Explore statistical visualizations")
+col1, col2, col3 = st.columns(3)
+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="📊")
+with col3:
+    st.page_link("content/results_heatmap.py", label="Heatmap", icon="🔥")

content/results_database_search.py

@@ -0,0 +1,79 @@
+"""Database Search (Comet) Results Page."""
+import streamlit as st
+from pathlib import Path
+from src.common.common import page_setup
+from src.common.results_helpers import get_workflow_dir
+from openms_insight import Table, Heatmap, LinePlot, SequenceView, StateManager
+
+params = page_setup()
+st.title("Database Search Results")
+
+st.markdown(
+    """
+View peptide-spectrum matches (PSMs) identified by **Comet** database search.
+Click on a PSM to view the annotated spectrum and peptide sequence.
+"""
+)
+
+st.info(
+    "**Score:** The e-value (expectation value) represents the expected number of random PSMs "
+    "with an equal or better score. Lower values indicate higher confidence identifications."
+)
+
+if "workspace" not in st.session_state:
+    st.warning("Please initialize your workspace first.")
+    st.stop()
+
+workflow_dir = get_workflow_dir(st.session_state["workspace"])
+comet_dir = workflow_dir / "results" / "comet_results"
+cache_dir = workflow_dir / "results" / "insight_cache"
+
+if not comet_dir.exists():
+    st.info("No database search results available yet. Please run the workflow first.")
+    st.page_link("content/workflow_run.py", label="Go to Run", icon="🚀")
+    st.stop()
+
+comet_files = sorted(comet_dir.glob("*.idXML"))
+
+if not comet_files:
+    st.warning("No identification output files found.")
+    st.stop()
+
+selected_file = st.selectbox(
+    "Select identification result file",
+    comet_files,
+    format_func=lambda x: x.name
+)
+
+cache_id_prefix = selected_file.stem
+
+# Check if cache exists
+if not (cache_dir / f"table_{cache_id_prefix}").is_dir():
+    st.warning("Visualization cache not found. Please re-run the workflow.")
+    st.stop()
+
+# Initialize state manager for cross-component linking
+state_manager = StateManager()
+
+# Load components from cache (no data parameter needed)
+table = Table(cache_id=f"table_{cache_id_prefix}", cache_path=str(cache_dir))
+heatmap = Heatmap(cache_id=f"heatmap_{cache_id_prefix}", cache_path=str(cache_dir))
+seq_view = SequenceView(cache_id=f"seqview_{cache_id_prefix}", cache_path=str(cache_dir))
+line_plot = LinePlot(cache_id=f"lineplot_{cache_id_prefix}", cache_path=str(cache_dir))
+
+# Render components
+st.subheader("PSM Overview")
+heatmap(state_manager=state_manager, height=350)
+
+st.subheader("PSM Table")
+table(state_manager=state_manager, height=533)
+
+st.subheader("Peptide Sequence")
+seq_view(key=f"seqview_{cache_id_prefix}", state_manager=state_manager, height=533)
+
+st.subheader("MS2 Spectrum")
+line_plot(key=f"lineplot_{cache_id_prefix}", state_manager=state_manager, height=450, sequence_view_key=f"seqview_{cache_id_prefix}")
+
+st.markdown("---")
+st.markdown("**Next step:** View rescoring results")
+st.page_link("content/results_rescoring.py", label="Go to Rescoring", icon="📈")

content/results_filtered.py

@@ -0,0 +1,79 @@
+"""Filtered PSMs Results Page."""
+import streamlit as st
+from pathlib import Path
+from src.common.common import page_setup
+from src.common.results_helpers import get_workflow_dir
+from openms_insight import Table, Heatmap, LinePlot, SequenceView, StateManager
+
+params = page_setup()
+st.title("Filtered PSMs")
+
+st.markdown(
+    """
+View FDR-controlled peptide identifications after **IDFilter** processing.
+These are high-confidence PSMs that passed the specified FDR threshold.
+Click on a PSM to view the annotated spectrum and peptide sequence.
+"""
+)
+
+st.info(
+    "**Score:** The q-value represents the minimum false discovery rate (FDR) at which this PSM "
+    "would be accepted. Lower values indicate higher confidence identifications."
+)
+
+if "workspace" not in st.session_state:
+    st.warning("Please initialize your workspace first.")
+    st.stop()
+
+workflow_dir = get_workflow_dir(st.session_state["workspace"])
+filter_dir = workflow_dir / "results" / "psm_filter"
+cache_dir = workflow_dir / "results" / "insight_cache"
+
+if not filter_dir.exists():
+    st.info("No filtered results available yet. Please run the workflow first.")
+    st.stop()
+
+filter_files = sorted(filter_dir.glob("*.idXML"))
+
+if not filter_files:
+    st.warning("No filtering output files found.")
+    st.stop()
+
+selected_file = st.selectbox(
+    "Select filtering result file",
+    filter_files,
+    format_func=lambda x: x.name
+)
+
+cache_id_prefix = selected_file.stem
+
+# Check if cache exists
+if not (cache_dir / f"table_{cache_id_prefix}").is_dir():
+    st.warning("Visualization cache not found. Please re-run the workflow.")
+    st.stop()
+
+# Initialize state manager for cross-component linking
+state_manager = StateManager()
+
+# Load components from cache (no data parameter needed)
+table = Table(cache_id=f"table_{cache_id_prefix}", cache_path=str(cache_dir))
+heatmap = Heatmap(cache_id=f"heatmap_{cache_id_prefix}", cache_path=str(cache_dir))
+seq_view = SequenceView(cache_id=f"seqview_{cache_id_prefix}", cache_path=str(cache_dir))
+line_plot = LinePlot(cache_id=f"lineplot_{cache_id_prefix}", cache_path=str(cache_dir))
+
+# Render components
+st.subheader("PSM Overview")
+heatmap(state_manager=state_manager, height=350)
+
+st.subheader("PSM Table")
+table(state_manager=state_manager, height=533)
+
+st.subheader("Peptide Sequence")
+seq_view(key=f"seqview_{cache_id_prefix}", state_manager=state_manager, height=533)
+
+st.subheader("MS2 Spectrum")
+line_plot(key=f"lineplot_{cache_id_prefix}", state_manager=state_manager, height=450, sequence_view_key=f"seqview_{cache_id_prefix}")
+
+st.markdown("---")
+st.markdown("**Next step:** View abundance quantification")
+st.page_link("content/results_abundance.py", label="Go to Abundance", icon="📋")