results_abundance.py

"""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="🔥")