Initial upload of the demo application

README.md

@@ -1,12 +1,27 @@
 ---
-title: CAFA ProtBERT Demo V1
-emoji: 🚀
-colorFrom: blue
-colorTo: yellow
+title: CAFA ProtBERT demo v1
+emoji: 🧬
+colorFrom: purple
+colorTo: blue
 sdk: gradio
-sdk_version: 6.6.0
+sdk_version: 5.50.0
 app_file: app.py
 pinned: false
+license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# CAFA ProtBERT demo v1
+
+This is a demo project to showcase my attempts at predicting the Protin functions - known as GO-terms based of the Prozein amino acid string.
+
+This is essentially the scope of the CAFA 6 challenge that was hosted on Kaggle - https://www.kaggle.com/competitions/cafa-6-protein-function-prediction/overview
+
+This demo takes in a single Protein sequence, and will then predict the corresonding GO-terms based of that, and isplay the score.
+
+Right now, no further post-processing or frills are available.
+
+The model used to perform the predictions is a fine tuned ProtBERT Model. See: https://huggingface.co/Rostlab/prot_bert
+
+And finally, the model isn't to good right now, there is much more experimentation ahead. For instance, the example was reported tith the following GO-terms:
+- GO:1990837
+- GO:0005515

requirements.txt

@@ -0,0 +1,4 @@
+timm
+gradio
+torch
+transformers