Spaces:
Sleeping
Sleeping
ex
Browse files- README.txt +43 -0
- app.py +20 -1
README.txt
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Protein Sequence Table
|
| 2 |
+
|
| 3 |
+
A Gradio-based web application that reformats protein sequences based on UniProt IDs and displays detailed annotations in a structured format.
|
| 4 |
+
|
| 5 |
+
## Features
|
| 6 |
+
|
| 7 |
+
The application retrieves protein data from UniProt and presents the following information for each residue:
|
| 8 |
+
- Position number in the sequence
|
| 9 |
+
- Amino acid (single-letter code)
|
| 10 |
+
- Secondary structure annotation
|
| 11 |
+
- Associated Pfam domain
|
| 12 |
+
- Disorder prediction
|
| 13 |
+
- Participation in disulfide bridges
|
| 14 |
+
- Post-translational modifications:
|
| 15 |
+
* Glycosylation sites
|
| 16 |
+
* Phosphorylation sites
|
| 17 |
+
- Functional annotations:
|
| 18 |
+
* Active sites
|
| 19 |
+
* Metal binding sites
|
| 20 |
+
* DNA binding regions
|
| 21 |
+
* RNA binding regions
|
| 22 |
+
* Ligand binding sites
|
| 23 |
+
* Other modifications
|
| 24 |
+
|
| 25 |
+
## Usage
|
| 26 |
+
|
| 27 |
+
1. Launch the application
|
| 28 |
+
2. Enter a valid UniProt ID (e.g., P53_HUMAN) in the input field
|
| 29 |
+
3. Click "Submit" to generate the analysis
|
| 30 |
+
4. Results will be displayed in a interactive data frame format
|
| 31 |
+
|
| 32 |
+
## Requirements
|
| 33 |
+
|
| 34 |
+
- Python 3.7+
|
| 35 |
+
- Gradio
|
| 36 |
+
- Pandas
|
| 37 |
+
- Requests
|
| 38 |
+
- XML parsing libraries
|
| 39 |
+
|
| 40 |
+
## Note
|
| 41 |
+
|
| 42 |
+
The application processes UniProt's XML format to extract annotations.
|
| 43 |
+
|
app.py
CHANGED
|
@@ -244,8 +244,27 @@ def process_uniprot_id(uniprot_id):
|
|
| 244 |
with gr.Blocks() as demo:
|
| 245 |
with gr.Column():
|
| 246 |
gr.Markdown("# Protein Sequence Analysis")
|
| 247 |
-
input_text = gr.Textbox(
|
|
|
|
|
|
|
|
|
|
|
|
|
| 248 |
submit_btn = gr.Button("Submit")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 249 |
output_df = gr.Dataframe()
|
| 250 |
|
| 251 |
submit_btn.click(
|
|
|
|
| 244 |
with gr.Blocks() as demo:
|
| 245 |
with gr.Column():
|
| 246 |
gr.Markdown("# Protein Sequence Analysis")
|
| 247 |
+
input_text = gr.Textbox(
|
| 248 |
+
label="UniProt ID",
|
| 249 |
+
placeholder="Enter UniProt ID (e.g., P53_HUMAN)",
|
| 250 |
+
value="", # Empty default value
|
| 251 |
+
)
|
| 252 |
submit_btn = gr.Button("Submit")
|
| 253 |
+
|
| 254 |
+
# Add examples
|
| 255 |
+
gr.Examples(
|
| 256 |
+
examples=[
|
| 257 |
+
["P06280"], # Alpha-galactosidase A
|
| 258 |
+
["P04637"], # Tumor protein p53
|
| 259 |
+
["P01308"], # Insulin
|
| 260 |
+
["Q8WZ42"], # Titin
|
| 261 |
+
["P04637"], # p53 (alternate entry)
|
| 262 |
+
["P0DTC2"], # SARS-CoV-2 Spike protein
|
| 263 |
+
],
|
| 264 |
+
inputs=input_text,
|
| 265 |
+
label="Example UniProt IDs"
|
| 266 |
+
)
|
| 267 |
+
|
| 268 |
output_df = gr.Dataframe()
|
| 269 |
|
| 270 |
submit_btn.click(
|