[BIOBERT-FTM] Add/Update Space files (2025-10-17T20:54:49.835623+00:00)

README.md

@@ -1,12 +1,23 @@
 ---
-title: BIOBERT FTM Demo
-emoji: 🏢
-colorFrom: yellow
-colorTo: pink
+title: BIOBERT-FTM Demo
+emoji: 🧬
+colorFrom: green
+colorTo: blue
 sdk: gradio
-sdk_version: 5.49.1
+sdk_version: 4.44.0
+python_version: 3.10
 app_file: app.py
 pinned: false
+license: apache-2.0
+models:
+  - Milad96/BIOBERT-FTM-mlm
+  - Milad96/BIOBERT-FTM-tasks
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# BIOBERT-FTM — Gradio Space
+
+Interactive demo for **Fill‑Mask (MLM)** and **Bio‑NER (genes)** powered by:
+- Tokenizer/MLM: `Milad96/BIOBERT-FTM-mlm`
+- NER model: `Milad96/BIOBERT-FTM-tasks/ner-spyysalo_bc2gm_corpus`
+
+> Tip: GPU is optional but recommended. This Space reads public model weights from the Hub.

app.py

@@ -0,0 +1,129 @@
+# BIOBERT-FTM — Gradio Space App
+import os, json
+import torch
+import gradio as gr
+from transformers import AutoTokenizer, AutoConfig, AutoModelForTokenClassification, pipeline
+
+# ---- Model sources (override via Space Secrets or env) ----
+TOKENIZER_REPO = os.getenv("MLM_MODEL_REPO_ID", "Milad96/BIOBERT-FTM-mlm")
+TASK_MODEL_REPO = os.getenv("TASK_MODEL_REPO_ID", "Milad96/BIOBERT-FTM-tasks")
+NER_SUBFOLDER   = os.getenv("NER_SUBFOLDER", "ner-spyysalo_bc2gm_corpus")
+
+DEVICE = 0 if torch.cuda.is_available() else -1
+
+tokenizer = AutoTokenizer.from_pretrained(TOKENIZER_REPO, use_fast=True)
+config = AutoConfig.from_pretrained(TASK_MODEL_REPO, subfolder=NER_SUBFOLDER)
+model = AutoModelForTokenClassification.from_pretrained(
+    TASK_MODEL_REPO, subfolder=NER_SUBFOLDER, torch_dtype=torch.float32
+)
+
+ner = pipeline(
+    "token-classification",
+    model=model,
+    tokenizer=tokenizer,
+    device=DEVICE,
+    aggregation_strategy="simple"
+)
+
+fill_mask = pipeline(
+    "fill-mask",
+    model=TOKENIZER_REPO,
+    tokenizer=TOKENIZER_REPO,
+    device=DEVICE
+)
+
+EXAMPLE_TEXTS = [
+    "Mutations in BRCA1 and TP53 are frequently reported in breast cancer.",
+    "The expression of EGFR and KRAS was quantified by qPCR.",
+    "BRCA2 interacts with RAD51 during homologous recombination.",
+]
+
+MASK_EXAMPLES = [
+    "SARS-CoV-2 infects [MASK] epithelial cells in the respiratory tract.",
+    "Dexamethasone is commonly used to treat [MASK] inflammation.",
+]
+
+def run_fill_mask(text: str, topk: int = 5):
+    if not text or "[MASK]" not in text:
+        return "Input must contain [MASK] token.", f"Device: {'cuda' if DEVICE==0 else 'cpu'}"
+    try:
+        res = fill_mask(text, top_k=int(topk))
+        if isinstance(res, dict):  # older transformers may return dict for top_k=1
+            res = [res]
+        lines = []
+        for p in res:
+            seq = p.get("sequence", "")
+            score = float(p.get("score", 0.0))
+            lines.append(f"→ {seq} (score={score:.4f})")
+        return "\n".join(lines), f"Device: {'cuda' if DEVICE==0 else 'cpu'}"
+    except Exception as e:
+        return f"⚠️ Error: {e}", f"Device: {'cuda' if DEVICE==0 else 'cpu'}"
+
+
+def run_ner(text: str, score_threshold: float = 0.50):
+    if not text:
+        return "", "[]"
+    try:
+        preds = ner(text)
+        if not isinstance(preds, list):
+            preds = []
+        spans = []
+        for s in preds:
+            try:
+                sc = float(s.get("score", 0.0))
+                if sc < float(score_threshold):
+                    continue
+                start = int(s.get("start", 0))
+                end = int(s.get("end", 0))
+                spans.append({
+                    "entity": s.get("entity_group") or s.get("entity") or "",
+                    "start": start,
+                    "end": end,
+                    "text": text[start:end],
+                    "score": sc
+                })
+            except Exception:
+                # Skip any malformed span safely
+                continue
+        # Markdown summary
+        if spans:
+            lines = [f"Found {len(spans)} spans:"]
+            for sp in spans:
+                lines.append(
+                    f"- [{sp['entity']}] {sp['text']} (start={sp['start']}, end={sp['end']}, score={sp['score']:.4f})"
+                )
+            md = "\n".join(lines)
+        else:
+            md = "No spans above threshold."
+        return md, json.dumps(spans, ensure_ascii=False, indent=2)
+    except Exception as e:
+        return f"⚠️ Error: {e}", "[]"
+
+with gr.Blocks(title="BIOBERT-FTM Demo", theme=gr.themes.Default()) as demo:
+    gr.Markdown("""
+    # 🧬 BIOBERT-FTM — Demo
+    **Fill‑Mask** (MLM) and **Bio‑NER** (Gene) demo powered by your fine‑tuned checkpoints.
+    """)
+
+    with gr.Tabs():
+        with gr.TabItem("Fill-Mask"):
+            inp_mask = gr.Textbox(label="Input (must contain [MASK])", value=MASK_EXAMPLES[0])
+            topk = gr.Slider(1, 10, value=5, step=1, label="Top‑K")
+            btn = gr.Button("Run Fill-Mask")
+            out_txt = gr.Textbox(label="Predictions", lines=6)
+            out_meta = gr.Textbox(label="Meta")
+            btn.click(run_fill_mask, inputs=[inp_mask, topk], outputs=[out_txt, out_meta])
+            gr.Examples(MASK_EXAMPLES, inputs=[inp_mask])
+
+        with gr.TabItem("NER (Genes)"):
+            inp = gr.Textbox(label="Input text", value=EXAMPLE_TEXTS[0])
+            thr = gr.Slider(0, 1, value=0.50, step=0.01, label="Score threshold")
+            go = gr.Button("Run NER")
+            out_md = gr.Markdown()
+            out_json = gr.JSON()
+            go.click(run_ner, inputs=[inp, thr], outputs=[out_md, out_json])
+            gr.Examples(EXAMPLE_TEXTS, inputs=[inp])
+
+if __name__ == "__main__":
+    # When running inside Spaces, just `python app.py` is enough.
+    demo.queue().launch()

requirements.txt

@@ -0,0 +1,6 @@
+transformers==4.57.1
+torch>=2.3
+accelerate>=0.28.0
+gradio>=4.29.0,<5
+huggingface_hub>=0.23.0
+numpy

space_env_hints.json

@@ -0,0 +1,5 @@
+{
+  "MLM_MODEL_REPO_ID": "Milad96/BIOBERT-FTM-mlm",
+  "TASK_MODEL_REPO_ID": "Milad96/BIOBERT-FTM-tasks",
+  "NER_SUBFOLDER": "ner-spyysalo_bc2gm_corpus"
+}