Create app.py

app.py

@@ -0,0 +1,46 @@
+import gradio as gr
+import numpy as np
+import pandas as pd
+from huggingface_hub import hf_hub_download
+from transformers import AutoConfig, AutoModel, AutoTokenizer
+import torch
+
+print("Loading BulkRNABert...")
+config = AutoConfig.from_pretrained("InstaDeepAI/BulkRNABert", trust_remote_code=True)
+config.embeddings_layers_to_save = (4,)
+tokenizer = AutoTokenizer.from_pretrained("InstaDeepAI/BulkRNABert", trust_remote_code=True)
+model = AutoModel.from_pretrained("InstaDeepAI/BulkRNABert", config=config, trust_remote_code=True)
+print("✓ Model loaded")
+
+# Cache the required gene list once at startup
+csv_path = hf_hub_download(
+    repo_id="InstaDeepAI/BulkRNABert",
+    filename="data/tcga_sample.csv",
+    repo_type="model",
+)
+ref_df = pd.read_csv(csv_path)
+ref_genes = [c for c in ref_df.columns if c != "identifier"]
+
+def get_embeddings(file):
+    df = pd.read_csv(file.name, sep="\t", index_col=0).T
+
+    aligned = pd.DataFrame(0, index=df.index, columns=ref_genes)
+    for g in ref_genes:
+        if g in df.columns:
+            aligned[g] = df[g]
+
+    expr = np.log10(1 + aligned.to_numpy())
+    ids = tokenizer.batch_encode_plus(expr, return_tensors="pt")["input_ids"]
+
+    with torch.no_grad():
+        emb = model(ids)["embeddings_4"].mean(axis=1).numpy()
+
+    return {"shape": list(emb.shape), "first_5_values": emb[:5].tolist()}
+
+iface = gr.Interface(
+    fn=get_embeddings,
+    inputs=gr.File(label="Upload your TSV expression file"),
+    outputs=gr.JSON(label="Embeddings"),
+    title="BulkRNABert Embeddings",
+)
+iface.launch()