Update README and app.py to enhance project description and technical details for BASIS-China iGEM 2025 deployment of Tranception

README.md

@@ -1,8 +1,8 @@
 ---
 title: Transeption IGEM BASISCHINA 2025
-emoji: 🚀
-colorFrom: yellow
-colorTo: red
+emoji: 🧬
+colorFrom: blue
+colorTo: green
 sdk: gradio
 sdk_version: 5.34.2
 app_file: app.py
@@ -15,4 +15,34 @@ models:
   - PascalNotin/Tranception_Large
 ---
 
+# Tranception Protein Fitness Prediction - BASIS-China iGEM 2025
+
+Welcome to BASIS-China iGEM Team's deployment of Tranception on Hugging Face Spaces!
+
+## About This Project
+
+This is an implementation of the Tranception model for protein fitness prediction, deployed by the BASIS-China iGEM Team 2025. Our goal is to make advanced protein engineering tools accessible to the synthetic biology community.
+
+### Features
+- **In silico directed evolution**: Iteratively improve protein fitness through single amino acid substitutions
+- **Comprehensive fitness analysis**: Generate heatmaps showing fitness scores for all possible mutations
+- **Zero GPU support**: Leverages Hugging Face's dynamic GPU allocation for efficient inference
+- **Multiple model sizes**: Choose between Small, Medium, and Large models based on your needs
+
+### Technical Implementation
+This deployment utilizes Hugging Face's Zero GPU infrastructure, which:
+- Dynamically allocates H200 GPU resources when available
+- Seamlessly falls back to CPU processing when GPUs are unavailable
+- Ensures efficient resource management for all users
+
+## About BASIS-China iGEM Team
+
+We are a high school synthetic biology team participating in the International Genetically Engineered Machine (iGEM) competition. Our 2025 project focuses on protein engineering and computational biology applications.
+
+## Credits
+
+This implementation is based on:
+**Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval**
+by Pascal Notin, Mafalda Dias, Jonathan Frazer, Javier Marchena-Hurtado, Aidan N. Gomez, Debora S. Marks, and Yarin Gal.
+
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -390,9 +390,10 @@ tranception_design = gr.Blocks()
 
 with tranception_design:
     gr.Markdown("# In silico directed evolution for protein redesign with Tranception")
-    gr.Markdown("## 🧬 Hugging Face Spaces Demo")
-    gr.Markdown("Perform in silico directed evolution with Tranception to iteratively improve the fitness of a protein of interest, one mutation at a time. At each step, the Tranception model computes the log likelihood ratios of all possible single amino acid substitution Vs the starting sequence, and outputs a fitness heatmap and recommandations to guide the selection of the mutation to apply.")
-    gr.Markdown("**Note**: This demo runs on CPU in Hugging Face Spaces. For faster inference, consider using GPU locally or selecting the Small model.")
+    gr.Markdown("## 🧬 BASIS-China iGEM Team 2025 - Protein Engineering Platform")
+    gr.Markdown("### Welcome to BASIS-China's implementation of Tranception on Hugging Face Spaces!")
+    gr.Markdown("We are the BASIS-China iGEM team, and we're excited to present our deployment of the Tranception model for protein fitness prediction. This tool enables in silico directed evolution to iteratively improve protein fitness through single amino acid substitutions. At each step, Tranception computes log likelihood ratios for all possible mutations compared to the starting sequence, generating fitness heatmaps and recommendations to guide protein engineering.")
+    gr.Markdown("**Technical Details**: This deployment leverages Hugging Face's Zero GPU infrastructure, which dynamically allocates H200 GPU resources when available. This allows for efficient inference while managing computational resources effectively. When GPU resources are temporarily unavailable, the system seamlessly falls back to CPU processing.")
     
     with gr.Tabs():
         with gr.TabItem("Input"):
@@ -476,9 +477,11 @@ with tranception_design:
     )
     
     gr.Markdown("<p>You may now use the output mutated sequence above as the starting sequence for another round of in silico directed evolution.</p>")
-    gr.Markdown("For more information about the Tranception model, please refer to our paper below:")
+    gr.Markdown("### About BASIS-China iGEM Team")
+    gr.Markdown("We are a high school synthetic biology team participating in the International Genetically Engineered Machine (iGEM) competition. Our 2025 project focuses on protein engineering and computational biology applications. This Tranception deployment is part of our broader effort to make advanced protein design tools accessible to the synthetic biology community.")
+    gr.Markdown("### About Tranception")
     gr.Markdown("<p><b>Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval</b><br>Pascal Notin, Mafalda Dias, Jonathan Frazer, Javier Marchena-Hurtado, Aidan N. Gomez, Debora S. Marks<sup>*</sup>, Yarin Gal<sup>*</sup><br><sup>* equal senior authorship</sup></p>")
-    gr.Markdown("Links: <a href='https://proceedings.mlr.press/v162/notin22a.html' target='_blank'>Paper</a>  <a href='https://github.com/OATML-Markslab/Tranception' target='_blank'>Code</a>  <a href='https://sites.google.com/view/proteingym/substitutions' target='_blank'>ProteinGym</a>")
+    gr.Markdown("Links: <a href='https://proceedings.mlr.press/v162/notin22a.html' target='_blank'>Paper</a>  <a href='https://github.com/OATML-Markslab/Tranception' target='_blank'>Code</a>  <a href='https://sites.google.com/view/proteingym/substitutions' target='_blank'>ProteinGym</a>  <a href='https://igem.org/teams/5247' target='_blank'>BASIS-China iGEM Team</a>")
 
 if __name__ == "__main__":
     # Configure queue for better resource management