Spaces:
Sleeping
Sleeping
Erva Ulusoy
commited on
Commit
·
ec82ae1
1
Parent(s):
41634be
added info about upcoming features, fixed reset button
Browse files- ProtHGT_app.py +11 -2
ProtHGT_app.py
CHANGED
|
@@ -11,7 +11,7 @@ with st.spinner("Please wait while we prepare the environment. This may take a f
|
|
| 11 |
start_time = time.time()
|
| 12 |
os.system("bash setup.sh")
|
| 13 |
end_time = time.time()
|
| 14 |
-
|
| 15 |
with open(".setup_done", "w") as f:
|
| 16 |
f.write("done")
|
| 17 |
|
|
@@ -26,6 +26,15 @@ if 'predictions_df' not in st.session_state:
|
|
| 26 |
if 'submitted' not in st.session_state:
|
| 27 |
st.session_state.submitted = False
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
with st.sidebar:
|
| 31 |
st.markdown("""
|
|
@@ -317,4 +326,4 @@ with st.sidebar:
|
|
| 317 |
if st.button("Reset"):
|
| 318 |
st.session_state.predictions_df = None
|
| 319 |
st.session_state.submitted = False
|
| 320 |
-
st.
|
|
|
|
| 11 |
start_time = time.time()
|
| 12 |
os.system("bash setup.sh")
|
| 13 |
end_time = time.time()
|
| 14 |
+
print(f"Environment prepared in {end_time - start_time:.2f} seconds")
|
| 15 |
with open(".setup_done", "w") as f:
|
| 16 |
f.write("done")
|
| 17 |
|
|
|
|
| 26 |
if 'submitted' not in st.session_state:
|
| 27 |
st.session_state.submitted = False
|
| 28 |
|
| 29 |
+
with st.expander("🚀 Upcoming Features"):
|
| 30 |
+
st.info("""
|
| 31 |
+
We are actively working on enhancing ProtHGT application with new capabilities:
|
| 32 |
+
|
| 33 |
+
- **Real-time data retrieval for new proteins**: Currently, ProtHGT can only generate predictions for proteins that already exist in our knowledge graph. We are developing a new feature that will allow users to **predict functions for entirely new proteins starting from their sequences**. This will work by **retrieving relevant relationship data in real time from external source databases** (e.g., UniProt, STRING, and other biological repositories). The system will dynamically construct a knowledge graph for the query protein, incorporating its interactions, domains, pathways, and other biological associations before running function prediction. This approach will enable ProtHGT to analyze newly discovered or less-studied proteins even if they are not pre-annotated in our dataset.
|
| 34 |
+
- **Expanded embedding options**: Currently, this application represents proteins using **TAPE embeddings**, which serve as the initial numerical representations of protein sequences before being processed in the heterogeneous graph model. We are working on integrating **ProtT5** and **ESM-2** as alternative initial embeddings, allowing users to choose different sequence representations that may enhance performance for specific tasks. A detailed comparison of how these embeddings influence function prediction accuracy will be included in our upcoming publication.
|
| 35 |
+
|
| 36 |
+
Stay tuned for updates and future publications!
|
| 37 |
+
""")
|
| 38 |
|
| 39 |
with st.sidebar:
|
| 40 |
st.markdown("""
|
|
|
|
| 326 |
if st.button("Reset"):
|
| 327 |
st.session_state.predictions_df = None
|
| 328 |
st.session_state.submitted = False
|
| 329 |
+
st.rerun()
|