Create app.py

app.py

@@ -0,0 +1,146 @@
+from transformers import pipeline
+import gradio as gr
+from flair.data import Sentence
+from flair.models import SequenceTagger
+import torch
+
+
+
+#constants
+
+GR_TXT1 = """
+    Recent studies have identified several key mutations associated with familial breast cancer.
+    The BRCA1 c.5266dupC mutation (p.Gln1756Profs74) was detected in 12% of patients, while the BRCA2 p.Ser1982fs variant showed reduced penetrance.
+    Analysis revealed that the TP53 R175H substitution co-occurred with EGFR L858R in 8 cases.
+    Additionally, the HER2 amplification correlated with response to trastuzumab therapy.
+    Novel variants including PIK3CA E545K and AKT1 E17K were identified in endocrine-resistant tumors.
+    The KRAS G12D mutation remained a negative predictive marker for anti-EGFR therapy.
+"""
+
+GR_TXT2 = """
+    During the 12-week treatment period, 23 patients experienced adverse events.
+    The most common was grade 2 nausea occurring in 15 participants, followed by fatigue in 11 cases.
+    Three patients developed severe neutropenia requiring dose reduction, and two experienced thrombocytopenia.
+    One case of drug-induced hepatotoxicity was documented with elevated ALT levels.
+    Mild headache and dizziness were reported by 8 patients during the first week.
+    Serious adverse events included one instance of anaphylaxis and two cases of Stevens-Johnson syndrome, leading to treatment discontinuation.
+    No cardiovascular events or nephrotoxicity were observed.
+  """
+
+
+GR_MARKDOWN_TXT = """ 
+# 🧬 OTAR3088 Work-in-progress NER-models demo space 
+This space allows for the **visualisation of outputs / review of our WIP NER-models.** Presently these models include... 👀:  
+- **Adverse Events**  
+- **Variants**   
+
+👉 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 = {
+    "Variants-V1": "OTAR3088/Variants-V1",
+    "AdverseEvent-PHEE-V1": "OTAR3088/hf-phee-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:
+    with gr.Row():
+        with gr.Column(scale=7):
+            gr.Markdown(GR_MARKDOWN_TXT,elem_classes="full-width")
+            input_text = gr.Textbox(label="Enter your text here", type='text', placeholder="Biomedical Input text", lines=8)
+        
+
+            gr.Examples(
+                    examples=[GR_TXT1, GR_TXT2],
+                inputs=[input_text],
+                label= "Example Biomedical texts to try (fabricated texts, not from literature)"
+            )
+            run_btn = gr.Button("Submit Text", variant="primary")
+
+        with gr.Column(scale=7):
+            model_choice = gr.Dropdown(choices=list(MODEL_REGISTRY.keys()), label="Select a model for Inference")
+            output_highlight = gr.HighlightedText(label="Tagged Entities")
+            
+
+    # with gr.Row():
+    #   with gr.Column(scale=7):
+    #     input_text = gr.Textbox(label="Enter your text here", type='text', placeholder="Biomedical Input text", lines=8)
+        
+
+    #     gr.Examples(
+    #             examples=[GR_TXT1, GR_TXT2],
+    #         inputs=[input_text],
+    #         label= "Example Biomedical texts to try"
+    #     )
+    #     run_btn = gr.Button("Submit Text", variant="primary")
+
+
+    run_btn.click(
+          fn=tagger,
+          inputs=[input_text, model_choice],
+          outputs=[output_highlight]
+      )
+
+        
+
+    return demo
+
+
+
+
+if __name__ == "__main__":
+  app = gradio_ui()
+  app.launch()