Delete app.py

app.py

@@ -1,197 +0,0 @@
-#!/usr/bin/env python3
-"""
-Flexynesis Tissue VAE – Web Application
-========================================
-Upload a gene expression matrix → get UBERON tissue classification + embeddings.
-
-Run locally:
-    streamlit run app.py
-
-Deploy on HuggingFace Spaces:
-    See setup_webapp.py for file preparation.
-
-Author: Amit Pande, MDC Berlin/BIMSB
-"""
-
-import streamlit as st
-import pandas as pd
-import numpy as np
-import torch
-import joblib
-from pathlib import Path
-from sklearn.neighbors import KNeighborsClassifier
-from collections import Counter
-
-# ── Config ──
-MODEL_DIR = Path("model")
-K = 5
-
-st.set_page_config(page_title="Flexynesis Tissue VAE", page_icon="🧬", layout="wide")
-st.title("🧬 Flexynesis Tissue VAE")
-st.markdown(
-    "Upload a bulk RNA-seq gene expression matrix to classify tissue-of-origin "
-    "using a supervised VAE trained on **75,619 samples** from TCGA, GTEx, DepMap, and ARCHS4 "
-    "across **43 UBERON tissue categories** (90.7% balanced accuracy, 121-dim latent space)."
-)
-
-# ── Load model + artifacts ──
-@st.cache_resource
-def load_all():
-    model = torch.load(MODEL_DIR / "vae_tissue.final_model.pth",
-                       map_location='cpu', weights_only=False)
-    model.eval()
-
-    art = joblib.load(MODEL_DIR / "vae_tissue.artifacts.joblib")
-    gene_list  = list(art['feature_lists']['gex'])
-    scaler     = art['transforms']['gex']
-    label_enc  = art['label_encoders']['uberon_tissue']
-
-    train_emb  = pd.read_csv(MODEL_DIR / "embeddings_train.csv", index_col=0)
-    test_emb   = pd.read_csv(MODEL_DIR / "embeddings_test.csv",  index_col=0)
-    train_clin = pd.read_csv(MODEL_DIR / "train_clin.csv", index_col=0)
-    test_clin  = pd.read_csv(MODEL_DIR / "test_clin.csv",  index_col=0)
-
-    all_emb  = pd.concat([train_emb, test_emb])
-    all_clin = pd.concat([train_clin, test_clin])
-    idx      = all_emb.index.intersection(all_clin.index)
-    ref_emb  = all_emb.loc[idx]
-    ref_clin = all_clin.loc[idx]
-    mask = (ref_clin['uberon_tissue'].notna() &
-            ~ref_clin['uberon_tissue'].isin(['unknown','other','unmapped','nan','']))
-    ref_emb  = ref_emb[mask]
-    ref_clin = ref_clin[mask]
-
-    knn = KNeighborsClassifier(n_neighbors=K, metric='cosine', n_jobs=-1)
-    knn.fit(ref_emb.values, ref_clin['uberon_tissue'].values)
-
-    classes = list(label_enc.categories_[0]) if hasattr(label_enc, 'categories_') else None
-
-    return model, gene_list, scaler, knn, ref_emb, ref_clin, classes
-
-try:
-    model, gene_list, scaler, knn_ref, ref_emb, ref_clin, classes = load_all()
-    st.success(
-        f"✅ {len(gene_list):,} genes · "
-        f"{len(ref_emb):,} reference samples · "
-        f"{ref_clin['uberon_tissue'].nunique()} tissues"
-    )
-except Exception as e:
-    st.error(f"Load error: {e}")
-    st.info("Place model files in `model/` directory. Run `python setup_webapp.py` first.")
-    st.stop()
-
-# ── Helpers ──
-def orient_matrix(df):
-    genes_in_cols = len(set(df.columns) & set(gene_list))
-    genes_in_rows = len(set(df.index)   & set(gene_list))
-    if genes_in_rows > genes_in_cols:
-        df = df.T
-    return df
-
-def encode(model, X_tensor):
-    with torch.no_grad():
-        h  = model.encoders[0](X_tensor)
-        mu = model.FC_mean(h[0])
-    return mu
-
-def classify_from_logits(model, mu, classes):
-    with torch.no_grad():
-        logits = model.MLPs['uberon_tissue'](mu)
-        # Mask out nan class if present
-        label_mapping = model.dataset.label_mappings['uberon_tissue']
-        name_to_idx   = {v: k for k, v in label_mapping.items()}
-        nan_idx = name_to_idx.get('nan', None)
-        if nan_idx is not None:
-            logits[:, nan_idx] = -1e9
-        probs    = torch.softmax(logits, dim=1)
-        pred_idx = logits.argmax(dim=1)
-    pred_labels = [label_mapping[int(i)] for i in pred_idx]
-    return pred_labels, probs.numpy()
-
-# ── File upload ──
-st.markdown("---")
-col1, col2 = st.columns([2, 1])
-with col1:
-    uploaded = st.file_uploader(
-        "Upload CSV/TSV (genes × samples or samples × genes)",
-        type=["csv", "tsv", "txt"],
-        help="HGNC gene symbols. Log2-transformed expression values (TPM, RPKM, or counts).")
-with col2:
-    st.markdown(f"""
-    **Expected input:**
-    - HGNC gene symbols
-    - {len(gene_list):,} genes used by model
-    - Log2-transformed expression
-    """)
-
-if uploaded:
-    sep = '\t' if uploaded.name.endswith(('.tsv', '.txt')) else ','
-    df  = pd.read_csv(uploaded, index_col=0, sep=sep)
-    st.write(f"**Uploaded:** {df.shape[0]:,} × {df.shape[1]:,}")
-    st.dataframe(df.iloc[:5, :5], use_container_width=True)
-
-    if st.button("🚀 Classify Tissues", type="primary"):
-        with st.spinner("Processing..."):
-            df      = orient_matrix(df)
-            overlap = len(set(df.columns) & set(gene_list))
-            st.write(f"Gene overlap: **{overlap:,}/{len(gene_list):,}** ({100*overlap/len(gene_list):.1f}%)")
-            if overlap < 1000:
-                st.warning("Low gene overlap — results may be unreliable.")
-
-            aligned        = pd.DataFrame(0.0, index=df.index, columns=gene_list)
-            common         = [g for g in gene_list if g in df.columns]
-            aligned[common] = df[common].values
-            aligned        = aligned.fillna(0)
-
-            X_scaled = scaler.transform(aligned.values)
-            X_tensor = torch.tensor(X_scaled, dtype=torch.float32)
-
-            mu         = encode(model, X_tensor)
-            embeddings = mu.numpy()
-
-            pred_labels, probs = classify_from_logits(model, mu, classes)
-            max_probs          = probs.max(axis=1)
-
-            distances, indices = knn_ref.kneighbors(embeddings)
-            breakdowns = []
-            for i in range(len(embeddings)):
-                nn_clin = ref_clin.iloc[indices[i]]
-                src_counts = Counter(nn_clin['source'].values)
-                breakdowns.append('; '.join(f"{s}:{c}" for s, c in src_counts.most_common()))
-
-        st.markdown("---")
-        st.subheader("📊 Results")
-        results = pd.DataFrame({
-            'Sample':           df.index,
-            'Tissue':           pred_labels,
-            'Confidence':       [f"{p:.1%}" for p in max_probs],
-            'kNN Dist':         distances.mean(axis=1).round(4),
-            'Sources':          breakdowns,
-        })
-        st.dataframe(results, use_container_width=True, height=400)
-
-        col1, col2 = st.columns(2)
-        with col1:
-            st.subheader("Tissue Distribution")
-            st.bar_chart(pd.Series(pred_labels).value_counts())
-        with col2:
-            st.subheader("Confidence Distribution")
-            st.bar_chart(pd.DataFrame({'Confidence': max_probs}, index=df.index))
-
-        st.markdown("---")
-        c1, c2 = st.columns(2)
-        with c1:
-            emb_df = pd.DataFrame(embeddings, index=df.index,
-                                  columns=[f"z{i}" for i in range(121)])
-            st.download_button("📥 Embeddings (CSV)", emb_df.to_csv(),
-                               "flexynesis_embeddings.csv", "text/csv")
-        with c2:
-            st.download_button("📥 Classifications (CSV)", results.to_csv(index=False),
-                               "flexynesis_classifications.csv", "text/csv")
-
-st.markdown("---")
-st.caption(
-    "Flexynesis Tissue VAE · Akalin Lab, MDC Berlin/BIMSB · "
-    "75,619 samples · 43 UBERON tissues · 90.7% balanced accuracy · "
-    "GitHub: github.com/BIMSBbioinfo/flexynesis"
-)