Update app.py

app.py

@@ -4,6 +4,7 @@ import numpy as np
 import pandas as pd
 import sklearn
 import xgboost
+import shap
 seed=42
 
 data = pd.read_csv("annotations_dataset.csv")
@@ -60,12 +61,33 @@ A machine learning pipeline for predicting disease-causing genes post-genome-wid
 
 collect_genes = lambda x : [str(i) for i in re.split(",|, ", x) if i != ""]
 
-input_genes = st.text_input("List of HGNC Genes (enter comma separated)")
-gene_list = collect_genes(input_genes)
+input_gene_list = st.text_input("Input list of HGNC genes (enter comma separated):")
+gene_list = collect_genes(input_gene_list)
+explainer = shap.TreeExplainer(xgb)
 
 if len(gene_list) > 1:
     df = df_total[df_total.index.isin(gene_list)]
     st.dataframe(df)
+    shap_values = explainer.shap_values(df)
+    summary_plot = shap.summary_plot(shap_values, df)
+    st.caption("SHAP Summary Plot of All Input Genes")
+    components.html(summary_plot, height = output_height, width = output_width, scrolling = True)
+
+else:
+    pass
+
+
+input_gene = st.text_input("Input individual HGNC gene:")
+df2 = df_total[df_total.index == input_gene]
+st.dataframe(df2)
+if len(input_gene) == 1:
+    shap_values = explainer.shap_values(df2)
+    shap.initjs()
+    force_plot = shap.force_plot(
+    explainer.expected_value,
+    shap_values.values,
+    df2)
+    components.html(force_plot, height = output_height, width = output_width, scrolling = True)
 else:
     pass