Add app.py

app.py

@@ -0,0 +1,141 @@
+from transformers import pipeline
+import gradio as gr
+from flair.data import Sentence
+from flair.models import SequenceTagger
+import torch
+
+
+
+#constants
+GR_PLACEHOLDER_TXT = """
+Aside from in vivo models, numerous studies investigating bacterial virulence and pathogenesis have also 
+employed in vitro cell line models to gain an initial understanding of the intricate host-pathogen interactions. 
+These studies, which are simpler and more cost-effective than those using in vivo models, 
+serve as the foundation for many in vivo studies by providing additional data to support any conclusions [12]. 
+Epithelial mucous membrane cells are the primary focus of most in vitro investigations due to them being usually the initial point of contact for infections [12,13].
+ HeLa cells, which originate from human cervical epithelial cells, are thus frequently selected for bacterial adhesion and invasion and are particularly suitable for experiments [14]. 
+ A. baumannii frequently infects human epithelial tissues, such as the respiratory system, skin and mucosal linings [15]. 
+ HeLa cells are resilient and readily cultured in vitro, exhibiting a rapid growth rate. 
+ This ensures the availability of a uniform and consistent cell population for studies, rendering them economical and reliable.
+"""
+
+
+GR_MARKDOWN_TXT = """ 
+
+# 🧬 OTAR3088 Biomedical NER Demo
+
+Welcome to the **OTAR3088 Entity Extraction for Knowledge discovery Project demo**.  
+
+This space showcases models trained to recognize the following biomedical entities:  
+- **CellLine**  
+- **CellType**  
+- **Tissue**  
+
+These entities are collectively referred to as **"CELLaTe"**.  
+
+👉 Try it out:  
+1. Select a model from the dropdown menu.  
+2. Enter/paste your text into the input box, or use our provided example biomedical paragraphs.  
+3. View the extracted entities highlighted directly in "Tagged Entities" box.  
+
+**Note:** Models in this demo are continuously updated and improved as part of our ongoing research.  
+
+
+"""
+
+
+GR_THEME = gr.themes.Soft(
+    primary_hue="indigo",
+    secondary_hue="rose",
+    neutral_hue="gray"
+)
+
+
+
+
+MODEL_REGISTRY = {
+    "CellFinder-V1-Model": "OTAR3088/bioformer-cellfinder_V1",
+    "CeLLaTe-V1-Model": "OTAR3088/bioformer-cellate_V1",
+   "Flair-CeLLaTe-Model": "OTAR3088/flair-microsoft-cellate_cellfinder-V1"
+   }
+
+
+hf_pipes = {}
+flair_pipes = {}
+
+
+
+def load_model(model_name):
+  if model_name.lower().startswith("flair"):
+    if not model_name in flair_pipes:
+      # Force default tensor type
+      torch.set_default_dtype(torch.float32)
+
+      flair_pipes[model_name] = SequenceTagger.load(MODEL_REGISTRY[model_name])
+      flair_pipes[model_name].to(torch.device("cpu"))
+      flair_pipes[model_name].float()
+    return flair_pipes[model_name], "flair"
+  else:
+    if not model_name in hf_pipes:
+      hf_pipes[model_name] = pipeline("ner", model=MODEL_REGISTRY[model_name], aggregation_strategy='simple')
+    return hf_pipes[model_name], "hf"
+
+
+
+def tagger(text, model_name):
+  model, model_type = load_model(model_name)
+  if model_type == "flair":
+    sentence = Sentence(text)
+    model.predict(sentence)
+    entities = [{"start": ent.start_position, 
+                 "end": ent.end_position, 
+                 "score": ent.score, 
+                 "entity": ent.tag} for ent in sentence.get_spans('ner')]
+
+  elif model_type == "hf":
+    entities = model(text)
+
+  return {"text": text, "entities": entities}
+
+
+def gradio_ui():
+  with gr.Blocks(theme=GR_THEME) as demo:
+    gr.Markdown(GR_MARKDOWN_TXT)
+
+    with gr.Row():
+      with gr.Column(scale=7):
+        model_choice = gr.Dropdown(choices=list(MODEL_REGISTRY.keys()), label="Select a model for Inference")
+        input_text = gr.Textbox(label="Enter your text here", type='text', placeholder="Biomedical Input text", lines=8)
+        
+
+        gr.Examples(
+            examples=[GR_PLACEHOLDER_TXT],
+            inputs=[input_text],
+            label= "Example Biomedical texts to try"
+        )
+        run_btn = gr.Button("Submit Text")
+
+      with gr.Column(scale=7):
+        output_highlight = gr.HighlightedText(label="Tagged Entities")
+
+    run_btn.click(
+          fn=tagger,
+          inputs=[input_text, model_choice],
+          outputs=[output_highlight]
+      )
+
+        
+
+    return demo
+
+
+
+
+if __name__ == "__main__":
+  app = gradio_ui()
+  app.launch(share=True, debug=True)
+
+
+
+
+