DavidNgoue commited on
Commit
72155e2
·
verified ·
1 Parent(s): fe3d944

Update src/streamlit_app.py

Browse files
Files changed (1) hide show
  1. src/streamlit_app.py +189 -153
src/streamlit_app.py CHANGED
@@ -29,28 +29,29 @@ import requests
29
  from transformers import pipeline, BioGptTokenizer, BioGptForCausalLM
30
  from transformers import MarianMTModel, MarianTokenizer
31
 
32
- # Load translations
33
- def load_translations():
 
 
 
34
  try:
35
  with open("translations.json", "r", encoding="utf-8") as f:
36
- translations = json.load(f)
37
- return translations
38
  except FileNotFoundError:
39
- st.error("Translation file not found.")
40
  return {}
41
  except json.JSONDecodeError:
42
- st.error("Translation file is malformed.")
43
  return {}
44
 
45
- translations = load_translations()
46
 
47
  # Get translation function
48
  def t(key, lang="fr"):
49
- translation = translations.get(lang, {}).get(key, key)
50
- return translation
51
 
52
- # Set page configuration
53
- st.set_page_config(page_title=t("app_title"), layout="wide", initial_sidebar_state="expanded")
 
 
54
 
55
  # Load custom CSS
56
  def load_css(file_name):
@@ -85,7 +86,7 @@ class Patient(Base):
85
  biomarkers = Column(String)
86
  created_at = Column(DateTime, default=datetime.utcnow)
87
 
88
- engine = create_engine('sqlite:///patients.db')
89
  Base.metadata.create_all(engine)
90
  Session = sessionmaker(bind=engine)
91
 
@@ -454,11 +455,11 @@ def send_to_rasa(message, lang):
454
  # Load model
455
  input_dims = [100, 50, 30, 20]
456
  best_hyperparams = {
457
- 'hidden_dim': 256, 'latent_dim': 64, 'num_layers': 3, 'dropout': 0.4, 'batch_size': 32
458
  }
459
  try:
460
  model = OmicsVAE(input_dims=input_dims, **best_hyperparams).to(device)
461
- model.load_state_dict(torch.load("omics_vae_best_hyperparams.pth", map_location=device))
462
  model.eval()
463
  except FileNotFoundError:
464
  st.error(t("model_weights_error"))
@@ -475,15 +476,15 @@ lang = st.session_state.language
475
 
476
  # Home Page
477
  if page == t("home"):
478
- st.markdown(f"<div class='title animate__fadeIn'>{t('app_title')}</div>", unsafe_allow_html=True)
479
  st.markdown(f"""
480
  <div class='intro animate__fadeIn'>
481
  <p>{t('home_intro_1').format(author="<b>Ngoue David Roger Yannick</b>")}</p>
482
  <p>{t('home_intro_2')}</p>
483
- </div>
484
  """, unsafe_allow_html=True)
485
 
486
- st.markdown(f"<div class='section-header'>{t('why_omics')}</div>", unsafe_allow_html=True)
487
  st.markdown(f"""
488
  <div class='content animate__fadeIn'>
489
  <p>{t('omics_description')}</p>
@@ -493,13 +494,13 @@ if page == t("home"):
493
  <li><b>{t('proteomics')}</b>: {t('proteomics_desc')}</li>
494
  <li><b>{t('metabolomics')}</b>: {t('metabolomics_desc')}</li>
495
  </ul>
 
496
  <p>{t('omics_integration')}</p>
497
- </div>
498
  """, unsafe_allow_html=True)
499
 
500
  # About Omics Data Page
501
  elif page == t("about_omics"):
502
- st.markdown(f"<div class='title animate__fadeIn'>{t('about_omics_title')}</div>", unsafe_allow_html=True)
503
  st.markdown(f"""
504
  <div class='content animate__fadeIn'>
505
  <p>{t('about_omics_intro')}</p>
@@ -509,20 +510,20 @@ elif page == t("about_omics"):
509
  st.markdown(f"<div class='section-header'>{t('raw_omics_formats')}</div>", unsafe_allow_html=True)
510
  st.markdown(f"""
511
  <div class='content animate__fadeIn'>
512
- <p>{t('raw_omics_desc')}</p>
513
  <ul>
514
  <li><b>{t('genomics')}</b>: {t('genomics_format')}</li>
515
  <li><b>{t('transcriptomics')}</b>: {t('transcriptomics_format')}</li>
516
  <li><b>{t('proteomics')}</b>: {t('proteomics_format')}</li>
517
  <li><b>{t('metabolomics')}</b>: {t('metabolomics_format')}</li>
518
  </ul>
 
519
  <p>{t('raw_omics_processing')}</p>
520
- </div>
521
  """, unsafe_allow_html=True)
522
 
523
- st.markdown(f"<div class='section-header'>{t('preprocessing_steps')}</div>", unsafe_allow_html=True)
524
  st.markdown(f"""
525
- <div class='content animate__fadeIn'>
526
  <p>{t('preprocessing_desc')}</p>
527
  <ol>
528
  <li><b>{t('quality_control')}</b>: {t('quality_control_desc')}</li>
@@ -531,8 +532,8 @@ elif page == t("about_omics"):
531
  <li><b>{t('standardization')}</b>: {t('standardization_desc')}</li>
532
  <li><b>{t('feature_selection')}</b>: {t('feature_selection_desc')}</li>
533
  </ol>
 
534
  <p>{t('preprocessing_importance')}</p>
535
- </div>
536
  """, unsafe_allow_html=True)
537
 
538
  st.markdown(f"<div class='section-header'>{t('csv_format')}</div>", unsafe_allow_html=True)
@@ -546,18 +547,19 @@ elif page == t("about_omics"):
546
  <li><b>{t('separator')}</b>: {t('separator_desc')}</li>
547
  <li><b>{t('header')}</b>: {t('header_desc')}</li>
548
  </ul>
 
549
  <p>{t('csv_example')}</p>
550
  <pre class='code-block'>
551
- Patient_ID,UMOD_rs12917707,APOL1_rs73885319,MYH9_rs4821480,Status
552
- P001,0,1,2,Unknown
553
  </pre>
554
- <p>{t('csv_patient_id')}</p>
555
  </div>
556
  """, unsafe_allow_html=True)
557
 
558
  st.markdown(f"<div class='section-header'>{t('data_quality')}</div>", unsafe_allow_html=True)
559
  st.markdown(f"""
560
- <div class='content animate__fadeIn'>
561
  <p>{t('data_quality_desc')}</p>
562
  <ul>
563
  <li><b>{t('consistency')}</b>: {t('consistency_desc')}</li>
@@ -565,8 +567,8 @@ P001,0,1,2,Unknown
565
  <li><b>{t('accuracy')}</b>: {t('accuracy_desc')}</li>
566
  <li><b>{t('alignment')}</b>: {t('alignment_desc')}</li>
567
  </ul>
 
568
  <p>{t('data_quality_importance')}</p>
569
- </div>
570
  """, unsafe_allow_html=True)
571
 
572
  # Predict Risk Page
@@ -595,9 +597,9 @@ elif page == t("predict_risk"):
595
  cols = st.columns(4)
596
  for idx, omic in enumerate(file_paths):
597
  with cols[idx]:
598
- uploaded_file = st.file_uploader(f"{t(omic)} (CSV)", type="csv", key=omic)
599
  if uploaded_file:
600
- temp_path = f"temp_{omic}.csv"
601
  with open(temp_path, "wb") as f:
602
  f.write(uploaded_file.getbuffer())
603
  file_paths[omic] = temp_path
@@ -618,51 +620,71 @@ elif page == t("predict_risk"):
618
  patient_tensors = [torch.tensor(data_dict[omic].values, dtype=torch.float32) for omic in data_dict]
619
  patient_dataset = TensorDataset(*patient_tensors)
620
  patient_loader = DataLoader(patient_dataset, batch_size=best_hyperparams['batch_size'],
621
- shuffle=False)
622
 
623
  # Extract latent representations
624
  encoded_data = extract_latent_representations(model, patient_loader, device)
625
 
626
  # Calculate risk scores
627
- umap_df = calculate_risk_scores(encoded_data, data_dict, irc_biomarkers, labels, label_encoder)
 
 
 
 
628
 
629
  # Perform SHAP analysis
630
- output_dir = "temp_output"
631
  os.makedirs(output_dir, exist_ok=True)
632
- important_biomarkers, shap_plot_path = perform_shap_analysis(
 
633
  model, combined_data, input_dims, device, feature_names, output_dir, irc_biomarkers
634
  )
 
 
635
 
636
  # Generate dynamic recommendations
 
637
  risk_score = umap_df[t('risk_score')].iloc[0]
638
- biomarkers = important_biomarkers[t('feature')].head(5).tolist()
639
  recommendations = []
640
  for intent in ["medication", "diet", "exercise"]:
641
- prompt = formulate_prompt(intent, risk_score, biomarkers)
642
- rec = generate_recommendation(prompt)
643
- if validate_recommendation(rec):
644
- rec = translate_recommendation(rec, lang)
645
- recommendations.append(rec)
646
- else:
647
- recommendations.append(t(f"{intent}_error", lang))
 
 
 
 
 
648
 
649
  # Generate PDF report
 
650
  pdf_path = os.path.join(output_dir, f"ckd_risk_report_{st.session_state.patient_id}.pdf")
651
- generate_pdf_report(risk_score, important_biomarkers, shap_plot_path, recommendations, pdf_path,
652
  lang)
 
 
653
 
654
  # Save to database
 
655
  session = Session()
656
  patient = Patient(
657
  patient_id=st.session_state.patient_id,
658
  risk_score=risk_score,
659
  biomarkers=', '.join(biomarkers)
660
  )
661
- session.add(patient)
662
  session.commit()
663
  session.close()
 
 
664
 
665
  # Store results
 
666
  st.session_state.results = {
667
  'umap_df': umap_df,
668
  'important_biomarkers': important_biomarkers,
@@ -670,86 +692,90 @@ elif page == t("predict_risk"):
670
  'pdf_path': pdf_path,
671
  'recommendations': recommendations
672
  }
673
-
674
- # Display results
675
- st.markdown(f"<div class='section-header'>{t('prediction_results')}</div>", unsafe_allow_html=True)
676
- st.markdown(f"<div class='result-box'>{t('ckd_risk_score').format(score=risk_score):.2f}</div>",
677
- unsafe_allow_html=True)
678
-
679
- # Risk gauge
680
- fig_gauge = go.Figure(go.Indicator(
681
- mode="gauge+number",
682
- value=risk_score,
683
- title={'text': t('risk_score', lang), 'font': {'color': '#FFD700'}},
684
- gauge={
685
- 'axis': {'range': [0, 100], 'tickcolor': '#FFF', 'tickfont': {'color': '#FFF'}},
686
- 'bar': {'color': "#1E3A8A"},
687
- 'steps': [
688
- {'range': [0, 33], 'color': "#4ADE80"},
689
- {'range': [33, 66], 'color': "#FACC15"},
690
- {'range': [66, 100], 'color': "#EF4444"}
691
- ],
692
- 'threshold': {
693
- 'line': {'color': "#FFD700", 'width': 4},
694
- 'thickness': 0.75,
695
- 'value': risk_score
 
 
 
 
 
696
  }
697
- }
698
- ))
699
- fig_gauge.update_layout(
700
- paper_bgcolor="#0E1117",
701
- font={'color': "#FFF"},
702
- margin=dict(l=20, r=20, t=50, b=20)
703
- )
704
- st.plotly_chart(fig_gauge, use_container_width=True)
705
-
706
- # SHAP bar plot
707
- st.markdown(f"<div class='subheader'>{t('key_biomarkers')}</div>", unsafe_allow_html=True)
708
- shap_fig = plt.figure(figsize=(12, 8))
709
- sns.barplot(data=important_biomarkers.head(20), x='SHAP_Mean_Abs', y=t('feature'), hue=t('omic'),
710
- palette='husl')
711
- plt.title(t('shap_top_features'), fontsize=16, color='#FFF')
712
- plt.xlabel(t('shap_mean_value'), fontsize=12, color='#FFF')
713
- plt.ylabel(t('feature'), fontsize=12, color='#FFF')
714
- plt.legend(title=t('omics'), facecolor='#1C2526', edgecolor='#FFF', labelcolor='#FFF')
715
- plt.gca().set_facecolor('#0E1117')
716
- plt.gca().tick_params(colors='#FFF')
717
- plt.gcf().set_facecolor('#0E1117')
718
- st.pyplot(shap_fig)
719
 
720
  # Display saved SHAP plot
721
  if os.path.exists(shap_plot_path):
722
- st.image(shap_plot_path, caption=t('shap_caption'), use_column_width=True)
723
 
724
  # Recommendations
725
  st.markdown(f"<div class='subheader'>{t('recommendations')}</div>", unsafe_allow_html=True)
726
  for rec in recommendations:
727
- st.markdown(f"<div class='recommendation'>{rec}</div>", unsafe_allow_html=True)
728
 
729
  # Download results
730
  st.markdown(f"<div class='subheader'>{t('download_results')}</div>", unsafe_allow_html=True)
731
- col1, col2 = st.columns(2)
732
  with col1:
733
- csv = important_biomarkers.to_csv(index=False)
734
- b64 = base64.b64encode(csv.encode()).decode()
735
  download_text = t('download_biomarkers', lang=st.session_state.language)
736
  href = f'<a href="data:file/csv;base64,{b64}" download="important_biomarkers.csv" class="download-btn">{download_text}</a>'
737
  st.markdown(href, unsafe_allow_html=True)
738
  with col2:
739
  with open(pdf_path, "rb") as f:
740
  pdf_data = f.read()
741
- b64_pdf = base64.b64encode(pdf_data).decode()
742
- download_text_pdf = t('download_report', lang=st.session_state.language)
743
- href_pdf = f'<a href="data:application/pdf;base64,{b64_pdf}" download="ckd_risk_report.pdf" class="download-btn">{download_text_pdf}</a>'
744
- st.markdown(href_pdf, unsafe_allow_html=True)
745
-
746
  except Exception as e:
747
  st.error(t("file_process_error").format(error=str(e)))
 
748
  else:
749
- st.warning(t("upload_warning"))
750
 
751
  # Chatbot Assistant Page
752
- elif page == t("chatbot"):
753
  st.markdown(f"<div class='title animate__fadeIn'>{t('chatbot_title')}</div>", unsafe_allow_html=True)
754
  st.markdown(f"""
755
  <div class='content animate__fadeIn'>
@@ -757,9 +783,9 @@ elif page == t("chatbot"):
757
  </div>
758
  """, unsafe_allow_html=True)
759
 
760
- # Chat interface
761
  st.markdown(f"<div class='section-header'>{t('chat_with_assistant')}</div>", unsafe_allow_html=True)
762
- chat_container = st.container()
763
  with chat_container:
764
  for message in st.session_state.chat_history:
765
  if message['role'] == 'user':
@@ -768,50 +794,57 @@ elif page == t("chatbot"):
768
  st.markdown(f"<div class='chat-bubble bot'>{message['content']}</div>", unsafe_allow_html=True)
769
 
770
  # User input
771
- user_input = st.text_input(t("type_message"), key="chat_input")
772
- if st.button(t("send"), key="send_chat"):
773
- if user_input:
774
- # Add user message to history
775
- st.session_state.chat_history.append({'role': 'user', 'content': user_input})
776
-
777
- # Check if user is asking about results
778
- if st.session_state.results and any(
779
- keyword in user_input.lower() for keyword in t('chat_risk_keywords').split(',')):
780
- risk_score = st.session_state.results['umap_df'][t('risk_score')].iloc[0]
781
- biomarkers = st.session_state.results['important_biomarkers'][t('feature')].head(5).tolist()
782
- context = t('chat_risk_response').format(score=risk_score, biomarkers=', '.join(biomarkers))
783
- response = send_to_rasa(f"{context} {user_input}", lang)
784
- else:
785
- # Generate recommendation based on intent
786
- intent = None
787
- if any(keyword in user_input.lower() for keyword in t('chat_medication_keywords').split(',')):
788
- intent = "medication"
789
- elif any(keyword in user_input.lower() for keyword in t('chat_diet_keywords').split(',')):
790
- intent = "diet"
791
- elif any(keyword in user_input.lower() for keyword in t('chat_exercise_keywords').split(',')):
792
- intent = "exercise"
793
-
794
- if intent and st.session_state.results:
795
- risk_score = st.session_state.results['umap_df'][t('risk_score')].iloc[0]
796
- biomarkers = st.session_state.results['important_biomarkers'][t('feature')].head(5).tolist()
797
- prompt = formulate_prompt(intent, risk_score, biomarkers)
798
- response = generate_recommendation(prompt)
799
- if validate_recommendation(response):
800
- response = translate_recommendation(response, lang)
801
  else:
802
- response = t(f"{intent}_error", lang)
803
- else:
804
- response = send_to_rasa(user_input, lang)
805
-
806
- # Add bot response to history
807
- st.session_state.chat_history.append({'role': 'bot', 'content': response})
808
-
809
- # Rerender chat
810
- st.rerun()
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
811
 
812
  # Dashboard Page
813
- elif page == t("dashboard"):
814
  st.markdown(f"<div class='title animate__fadeIn'>{t('dashboard_title')}</div>", unsafe_allow_html=True)
 
815
  st.markdown(f"""
816
  <div class='content animate__fadeIn'>
817
  <p>{t('dashboard_intro')}</p>
@@ -839,7 +872,7 @@ elif page == t("dashboard"):
839
  st.dataframe(filtered_df, use_container_width=True)
840
 
841
  # Plot
842
- fig = px.scatter(
843
  filtered_df,
844
  x=t('risk_score'),
845
  y=t('patient_id'),
@@ -849,28 +882,31 @@ elif page == t("dashboard"):
849
  color_continuous_scale='Viridis'
850
  )
851
  fig.update_layout(
852
- paper_bgcolor="#0E1117",
853
- plot_bgcolor="#1C2526",
854
- font={'color': "#FFF"}
855
  )
856
- st.plotly_chart(fig, use_container_width=True)
857
  else:
858
  st.info(t("no_patients"))
859
  session.close()
860
  except Exception as e:
861
  st.error(t("dashboard_error").format(error=str(e)))
862
 
863
- # Clean up temporary files
864
  for omic, path in st.session_state.uploaded_files.items():
865
  if os.path.exists(path):
866
  os.remove(path)
867
 
868
- # Terminate Rasa server on app close
869
  if rasa_process:
870
- rasa_process.terminate()
 
 
 
871
 
872
  st.markdown(f"""
873
- <div class='footer'>
874
  {t('footer')}
875
  </div>
876
  """, unsafe_allow_html=True)
 
29
  from transformers import pipeline, BioGptTokenizer, BioGptForCausalLM
30
  from transformers import MarianMTModel, MarianTokenizer
31
 
32
+ # Set page configuration as the first Streamlit command
33
+ st.set_page_config(page_title="Omics Risk Predictor", layout="wide", initial_sidebar_state="expanded")
34
+
35
+ # Load translations without Streamlit commands
36
+ def load_translations_raw():
37
  try:
38
  with open("translations.json", "r", encoding="utf-8") as f:
39
+ return json.load(f)
 
40
  except FileNotFoundError:
 
41
  return {}
42
  except json.JSONDecodeError:
 
43
  return {}
44
 
45
+ translations = load_translations_raw()
46
 
47
  # Get translation function
48
  def t(key, lang="fr"):
49
+ return translations.get(lang, {}).get(key, key)
 
50
 
51
+ # Check for translation file errors after set_page_config
52
+ if not translations:
53
+ st.error("Translation file not found or malformed.")
54
+ st.stop()
55
 
56
  # Load custom CSS
57
  def load_css(file_name):
 
86
  biomarkers = Column(String)
87
  created_at = Column(DateTime, default=datetime.utcnow)
88
 
89
+ engine = create_engine('sqlite:///data/patients.db')
90
  Base.metadata.create_all(engine)
91
  Session = sessionmaker(bind=engine)
92
 
 
455
  # Load model
456
  input_dims = [100, 50, 30, 20]
457
  best_hyperparams = {
458
+ 'hidden_dim': 256, 'latent_dim': 100, 'num_layers': 4, 'dropout': 0.3, 'batch_size': 32
459
  }
460
  try:
461
  model = OmicsVAE(input_dims=input_dims, **best_hyperparams).to(device)
462
+ model.load_state_dict(torch.load("omics_vae_best_hyperparameters.pth", map_location=device))
463
  model.eval()
464
  except FileNotFoundError:
465
  st.error(t("model_weights_error"))
 
476
 
477
  # Home Page
478
  if page == t("home"):
479
+ st.markdown(f"<div class='title animate__fadeIn'>{t('home_page_title')}</div>", unsafe_allow_html=True)
480
  st.markdown(f"""
481
  <div class='intro animate__fadeIn'>
482
  <p>{t('home_intro_1').format(author="<b>Ngoue David Roger Yannick</b>")}</p>
483
  <p>{t('home_intro_2')}</p>
484
+ </div>
485
  """, unsafe_allow_html=True)
486
 
487
+ st.markdown(f"<div class='section-header section__fadeIn'>{t('why_omics')}</div>", unsafe_allow_html=True)
488
  st.markdown(f"""
489
  <div class='content animate__fadeIn'>
490
  <p>{t('omics_description')}</p>
 
494
  <li><b>{t('proteomics')}</b>: {t('proteomics_desc')}</li>
495
  <li><b>{t('metabolomics')}</b>: {t('metabolomics_desc')}</li>
496
  </ul>
497
+ </div>
498
  <p>{t('omics_integration')}</p>
 
499
  """, unsafe_allow_html=True)
500
 
501
  # About Omics Data Page
502
  elif page == t("about_omics"):
503
+ st.markdown(f"<div class='title animate__fadeIn'>{t('about_omics_data_title')}</div>", unsafe_allow_html=True)
504
  st.markdown(f"""
505
  <div class='content animate__fadeIn'>
506
  <p>{t('about_omics_intro')}</p>
 
510
  st.markdown(f"<div class='section-header'>{t('raw_omics_formats')}</div>", unsafe_allow_html=True)
511
  st.markdown(f"""
512
  <div class='content animate__fadeIn'>
513
+ <p>{t('raw_omics')}</p>
514
  <ul>
515
  <li><b>{t('genomics')}</b>: {t('genomics_format')}</li>
516
  <li><b>{t('transcriptomics')}</b>: {t('transcriptomics_format')}</li>
517
  <li><b>{t('proteomics')}</b>: {t('proteomics_format')}</li>
518
  <li><b>{t('metabolomics')}</b>: {t('metabolomics_format')}</li>
519
  </ul>
520
+ </div>
521
  <p>{t('raw_omics_processing')}</p>
 
522
  """, unsafe_allow_html=True)
523
 
524
+ st.markdown(f"<div class='section-header'}>{t('preprocessing_steps')}</div>", unsafe_allow_html=True)
525
  st.markdown(f"""
526
+ <div class='content animate__fadeIn'}>
527
  <p>{t('preprocessing_desc')}</p>
528
  <ol>
529
  <li><b>{t('quality_control')}</b>: {t('quality_control_desc')}</li>
 
532
  <li><b>{t('standardization')}</b>: {t('standardization_desc')}</li>
533
  <li><b>{t('feature_selection')}</b>: {t('feature_selection_desc')}</li>
534
  </ol>
535
+ </div>
536
  <p>{t('preprocessing_importance')}</p>
 
537
  """, unsafe_allow_html=True)
538
 
539
  st.markdown(f"<div class='section-header'>{t('csv_format')}</div>", unsafe_allow_html=True)
 
547
  <li><b>{t('separator')}</b>: {t('separator_desc')}</li>
548
  <li><b>{t('header')}</b>: {t('header_desc')}</li>
549
  </ul>
550
+ </div>
551
  <p>{t('csv_example')}</p>
552
  <pre class='code-block'>
553
+ PatientID,UMOD_rs12917707,APOL1_rs73885319,MYH9_rs4821480,Status
554
+ P001,0,1,0,Unknown
555
  </pre>
556
+ <p>{t('csv_patient_id_desc')}</p>
557
  </div>
558
  """, unsafe_allow_html=True)
559
 
560
  st.markdown(f"<div class='section-header'>{t('data_quality')}</div>", unsafe_allow_html=True)
561
  st.markdown(f"""
562
+ <div class='content animate__fadeIn'}>
563
  <p>{t('data_quality_desc')}</p>
564
  <ul>
565
  <li><b>{t('consistency')}</b>: {t('consistency_desc')}</li>
 
567
  <li><b>{t('accuracy')}</b>: {t('accuracy_desc')}</li>
568
  <li><b>{t('alignment')}</b>: {t('alignment_desc')}</li>
569
  </ul>
570
+ </div>
571
  <p>{t('data_quality_importance')}</p>
 
572
  """, unsafe_allow_html=True)
573
 
574
  # Predict Risk Page
 
597
  cols = st.columns(4)
598
  for idx, omic in enumerate(file_paths):
599
  with cols[idx]:
600
+ uploaded_file = st.file_uploader(f"{t(omic)} (CSV)", type=["csv"], key=omic)
601
  if uploaded_file:
602
+ temp_path = os.path.join("data", f"temp_{omic}.csv")
603
  with open(temp_path, "wb") as f:
604
  f.write(uploaded_file.getbuffer())
605
  file_paths[omic] = temp_path
 
620
  patient_tensors = [torch.tensor(data_dict[omic].values, dtype=torch.float32) for omic in data_dict]
621
  patient_dataset = TensorDataset(*patient_tensors)
622
  patient_loader = DataLoader(patient_dataset, batch_size=best_hyperparams['batch_size'],
623
+ shuffle=False)
624
 
625
  # Extract latent representations
626
  encoded_data = extract_latent_representations(model, patient_loader, device)
627
 
628
  # Calculate risk scores
629
+ try:
630
+ umap_df = calculate_risk_scores(encoded_data, data_dict, risk_score, labels, label_encoder)
631
+ st.error_state(t("risk_score_error"))
632
+ except Exception as e:
633
+ print("Error calculating risk scores: {str(e)}")
634
 
635
  # Perform SHAP analysis
636
+ output_dir = os.path.join("data", "temp_output")
637
  os.makedirs(output_dir, exist_ok=True)
638
+ try:
639
+ important_biom, shap_plot_path = perform_shap_analysis(
640
  model, combined_data, input_dims, device, feature_names, output_dir, irc_biomarkers
641
  )
642
+ except Exception as e:
643
+ print("Error generating SHAP analysis: {str(e)}")
644
 
645
  # Generate dynamic recommendations
646
+ try:
647
  risk_score = umap_df[t('risk_score')].iloc[0]
648
+ biomarkers = important_biom.biomarkers[t('feature')].head(5).tolist()
649
  recommendations = []
650
  for intent in ["medication", "diet", "exercise"]:
651
+ try:
652
+ prompt = formulate_prompt(intent, risk_score, biomarkers)
653
+ rec = generate_recommendation(prompt)
654
+ if validate_recommendation(rec):
655
+ rec = translate_recommendation(rec, lang)
656
+ recommendations.append(rec)
657
+ else:
658
+ recommendations.append(t(f"{intent}_error", lang))
659
+ except Exception as e:
660
+ print("Error generating recommendation for {str(intent)}: {str(e)}")
661
+ except Exception as e:
662
+ print("Error generating recommendations: {str(e)}")
663
 
664
  # Generate PDF report
665
+ try:
666
  pdf_path = os.path.join(output_dir, f"ckd_risk_report_{st.session_state.patient_id}.pdf")
667
+ pdf_doc = generate_pdf_report(risk_score, important_biomarkers, shap_plot_path, recommendations, pdf_path,
668
  lang)
669
+ except Exception as e:
670
+ print("Error generating PDF report: {str(e)}")
671
 
672
  # Save to database
673
+ try:
674
  session = Session()
675
  patient = Patient(
676
  patient_id=st.session_state.patient_id,
677
  risk_score=risk_score,
678
  biomarkers=', '.join(biomarkers)
679
  )
680
+ session.add(patient_data
681
  session.commit()
682
  session.close()
683
+ except Exception as e:
684
+ print("Error saving to database: {str(e)}")
685
 
686
  # Store results
687
+ try:
688
  st.session_state.results = {
689
  'umap_df': umap_df,
690
  'important_biomarkers': important_biomarkers,
 
692
  'pdf_path': pdf_path,
693
  'recommendations': recommendations
694
  }
695
+ except Exception as e:
696
+ print("Error storing results: {str(e)}")
697
+
698
+ # Display results
699
+ st.markdown(f"<div class='section-header'>{t('prediction_results')}</div>", unsafe_allow_html=True)
700
+ st.markdown(f"<div class='result-box'>{t('ckd_risk_score').format(score=risk_score):.2f}</div>",
701
+ unsafe_allow_html=True)
702
+
703
+ # Risk gauge
704
+ fig_gauge = go.Figure(go.Indicator(
705
+ mode="gauge+number",
706
+ value=risk_score,
707
+ title={'text': t('risk_score', lang), 'font':{'color': '#FFD700'}},
708
+ gauge={
709
+ 'axis': {'range': [0, 100], 'tickcolor': '#FFF', 'tickfont': {'color': '#FFF'}},
710
+ 'bar': {'color': '#0000FF'},
711
+ 'steps': [
712
+ {'range': [0, 33], 'color': '#4ADE80'},
713
+ {'range': [33, 66], 'color': '#FACC15'},
714
+ {'range': [66, 333], 'color': '#EF4444'}
715
+ ],
716
+ },
717
+ 'threshold': {'
718
+ 'line': {'color': '#FFD700', 'width': 4},
719
+ 'thickness': 0.75,
720
+ 'value': risk_score
721
+ }
722
+ }
723
  }
724
+ ))
725
+ fig_gauge.update_layout(
726
+ paper_bgcolor='#0E1117',
727
+ font={'color': "#FFFFFF"},
728
+ margin={'l':20,'r':20,'t':50,'b':20}
729
+ )
730
+ st.plotly_chart(fig_gauge, use_container_width=True)
731
+
732
+ # SHAP bar plot
733
+ st.markdown(f"<div class='subheader'>{t('key_biomarkers')}</div>", unsafe_allow_html=True)
734
+ shap_fig = plt.figure(figsize=(12, 8))
735
+ sns.barplot(data=important_biomarkers.head(20).data, x='SHAP_Mean_Abs', y=t('feature'), hue=t('omic'),
736
+ palette=['#FF6F61', '#6B5B6B', '#4CAF50', '#2196F3'])
737
+ plt.title(t('shap_top_features'), fontsize=16, color='#FFFFFF')
738
+ plt.xlabel(t('shap_mean_value'), fontsize=12, color='#FFFFFF')
739
+ plt.ylabel(t('feature'), fontsize=12, color='#FFF')
740
+ plt.legend(title=t('omics'), facecolor='#1C2526', edgecolor='#FFF', labelcolor='#FFFFFF')
741
+ plt.gca().set_facecolor('#0E1117')
742
+ plt.gca().tick_params(colors=['black'])
743
+ plt.gcf().set_facecolor('#0E1117')
744
+ st.pyplot(shap_fig)
 
745
 
746
  # Display saved SHAP plot
747
  if os.path.exists(shap_plot_path):
748
+ st.image(shap_plot_path, caption=t('shap'), use_caption_width=True)
749
 
750
  # Recommendations
751
  st.markdown(f"<div class='subheader'>{t('recommendations')}</div>", unsafe_allow_html=True)
752
  for rec in recommendations:
753
+ st.markdown(f"<div class='recommendation'}>rec{rec}</div>", unsafe)
754
 
755
  # Download results
756
  st.markdown(f"<div class='subheader'>{t('download_results')}</div>", unsafe_allow_html=True)
757
+ col1, col2 = col.st.columns(2)
758
  with col1:
759
+ csv_data = important_biomarkers.to_csv().encode()
760
+ b64_data = base64.b64encode(csv_data).decode()
761
  download_text = t('download_biomarkers', lang=st.session_state.language)
762
  href = f'<a href="data:file/csv;base64,{b64}" download="important_biomarkers.csv" class="download-btn">{download_text}</a>'
763
  st.markdown(href, unsafe_allow_html=True)
764
  with col2:
765
  with open(pdf_path, "rb") as f:
766
  pdf_data = f.read()
767
+ b64_data_pdf = base64.b64encode(pdf_data).decode()
768
+ download_text_pdf = t('download_report', language=state.session_state.lang)
769
+ href = href_pdf = f'<a href="data:application/pdf;base64,{b64_pdf}" download="ckd_risk_report.pdf" class="download-btn">{download_text_pdf}</a>'
770
+ st.markdown(href_pdf, unsafe=allow_html=True)
 
771
  except Exception as e:
772
  st.error(t("file_process_error").format(error=str(e)))
773
+ st.stop()
774
  else:
775
+ st.warning(t("Please upload all omics files and provide a patient ID."))
776
 
777
  # Chatbot Assistant Page
778
+ else if page == t("chatbot"):
779
  st.markdown(f"<div class='title animate__fadeIn'>{t('chatbot_title')}</div>", unsafe_allow_html=True)
780
  st.markdown(f"""
781
  <div class='content animate__fadeIn'>
 
783
  </div>
784
  """, unsafe_allow_html=True)
785
 
786
+ # Chat Interface
787
  st.markdown(f"<div class='section-header'>{t('chat_with_assistant')}</div>", unsafe_allow_html=True)
788
+ chat_container = st.container()container()
789
  with chat_container:
790
  for message in st.session_state.chat_history:
791
  if message['role'] == 'user':
 
794
  st.markdown(f"<div class='chat-bubble bot'>{message['content']}</div>", unsafe_allow_html=True)
795
 
796
  # User input
797
+ user_input = input.st.text_area(t("type_message"), key="chat_input")
798
+ if st.button(t("send"), key="button_send"):
799
+ try:
800
+ if user_input:
801
+ # Add user message to history
802
+ st.session_state.chat_history.append({'role': 'user', 'content': user_input})
803
+
804
+ # Check if user is asking about results
805
+ if st.session_state.results and any(
806
+ keyword in user_input.lower() for keyword in t('chat_risk_keywords').split(',')):
807
+ risk_score = st.session_state.results['umap_df'][t('risk_score')].iloc[0]
808
+ biomarkers = st.session_state.results['important_biomarkers'][t('feature')].head(5).tolist()]
809
+ context = t('chat_risk_response').format(score=risk_score), biomarkers=', '.join(biomarkers))
810
+ response = send_to_rasa(f"{context} {user_input}", lang)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
811
  else:
812
+ # Generate recommendation based on intent
813
+ intent = 'None'
814
+ if any(keyword in user_input.lower() for keyword in t('chat_medication_keywords').split(',')):
815
+ intent = 'medication'
816
+ elif any(keyword in user_input.lower() for keyword in t('chat_diet_keywords').split(',')):
817
+ intent = 'diet'
818
+ elif any(keyword in user_input.lower() for keyword in t('chat_exercise_keywords').split(',')):
819
+ intent = 'exercise'
820
+
821
+ if intent and st.session_state.results:
822
+ risk_score = st.session_state.results['umap_df'][t('risk_score')].iloc[0]
823
+ biomarkers = st.session_state.results['important_biomarkers'][t('feature')].head(5).tolist()
824
+ try:
825
+ prompt = formulate_prompt(intent, risk_score, biomarkers)
826
+ try:
827
+ response = generate_recommendation(prompt)
828
+ if validate_recommendation(response):
829
+ response = translate_recommendation(response, lang)
830
+ else:
831
+ response = t(f"{intent}_error", lang)
832
+ else:
833
+ response = send_to_rasa(user_input, lang)
834
+
835
+ # Add bot response to history
836
+ st.session_state.chat_history.append({'role': 'bot', 'content': response})
837
+
838
+ # Rerender chat
839
+ st.rerun()
840
+ except Exception as e:
841
+ print("Error processing chatbot input: {str(e)}")
842
+ st.error("Error processing chatbot input")
843
 
844
  # Dashboard Page
845
+ elif if page == t("dashboard"):
846
  st.markdown(f"<div class='title animate__fadeIn'>{t('dashboard_title')}</div>", unsafe_allow_html=True)
847
+
848
  st.markdown(f"""
849
  <div class='content animate__fadeIn'>
850
  <p>{t('dashboard_intro')}</p>
 
872
  st.dataframe(filtered_df, use_container_width=True)
873
 
874
  # Plot
875
+ fig = px.scatter_plot(
876
  filtered_df,
877
  x=t('risk_score'),
878
  y=t('patient_id'),
 
882
  color_continuous_scale='Viridis'
883
  )
884
  fig.update_layout(
885
+ paper_bgcolor='#0E1117',
886
+ plot_bgcolor='#1C2526',
887
+ font={'color': '#ffffff'}
888
  )
889
+ st.plotly_chart(fig, use_container_width=True))
890
  else:
891
  st.info(t("no_patients"))
892
  session.close()
893
  except Exception as e:
894
  st.error(t("dashboard_error").format(error=str(e)))
895
 
896
+ # Clean up
897
  for omic, path in st.session_state.uploaded_files.items():
898
  if os.path.exists(path):
899
  os.remove(path)
900
 
901
+ # Terminate Rasa server
902
  if rasa_process:
903
+ try:
904
+ rasa_process.terminate()
905
+ except Exception as e:
906
+ print("Error terminating Rasa server: {str(e)}")
907
 
908
  st.markdown(f"""
909
+ <div class='footer">
910
  {t('footer')}
911
  </div>
912
  """, unsafe_allow_html=True)