Initial file upload

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data/protein_clusters.xlsx filter=lfs diff=lfs merge=lfs -text
+data/protein_dendrogram.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,14 +1,13 @@
 ---
-title: Proteins From Bert Point Pf View
-emoji: 👁
-colorFrom: indigo
-colorTo: green
+title: Proteins From Bert Point Of View
+emoji: 🏆
+colorFrom: red
+colorTo: indigo
 sdk: gradio
-sdk_version: 5.49.1
+sdk_version: 4.31.1
 app_file: app.py
 pinned: false
 license: bigscience-openrail-m
-short_description: Protein clustering using unikei/bert-base-proteins
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,31 @@
+import gradio as gr
+import pandas as pd
+
+image_path = "data/protein_dendrogram.png"
+
+protein_clusters = pd.read_excel('data/protein_clusters.xlsx')
+max_length = 500
+protein_clusters['proteins'] = protein_clusters['proteins'].apply(lambda x: x[:max_length] + ('...' if len(x) > max_length else ''))
+protein_clusters['protein groups'] = protein_clusters['protein groups'].apply(lambda x: x[:max_length] + ('...' if len(x) > max_length else ''))
+protein_clusters['protein features'] = protein_clusters['protein features'].apply(lambda x: x[:max_length] + ('...' if len(x) > max_length else ''))
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Protein similarity from BERT point of view")
+    gr.Markdown("This app displays protein similarity captured in the model [unikei/bert-base-proteins]("
+                "https://huggingface.co/unikei/bert-base-proteins).")
+
+    gr.Image(image_path,
+             label="Right click to zoom in new tab.",
+             container=True
+             )
+
+    gr.Markdown("\n")
+    gr.Markdown("Click on the [link](https://huggingface.co/spaces/unikei/proteins-from-bert-point-of-view/blob/main/data/protein_clusters.xlsx) to download the spreadsheet.")
+    gr.DataFrame(protein_clusters,
+                 interactive=False,
+                 wrap=True,
+                 column_widths=[5, 5, 30, 30, 30])
+    #
+
+demo.launch()

data/protein_clusters.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880a52865cea129e1b6099db85f5fd5a6fc6b2f0f047991f2900744b20473ec8
+size 211288

requirements.txt

@@ -0,0 +1,3 @@
+gradio==4.31.1
+pandas==2.2.2
+openpyxl==3.1.2