files

App.py

@@ -0,0 +1,97 @@
+import streamlit as st
+import os
+import pandas as pd
+import numpy as np
+from sklearn.metrics.pairwise import cosine_similarity, manhattan_distances, euclidean_distances
+
+st.set_page_config(
+    page_title="PhenoGene",
+    page_icon="🧑‍💻",
+    layout="wide",
+    menu_items={
+        'Get Help': 'https://www.ncbi.nlm.nih.gov/research/bionlp/',
+        'About': "PhenoGene v1.0"
+    }
+)
+
+# Constants
+embs = []
+
+# Heading
+st.title('PhenoGene Interactive Demo')
+st.image("https://www.nlm.nih.gov/images/NLMgeneric.jpg")
+with st.expander("About", expanded=True):
+
+    st.write(
+        """     
+-   This Application presents the demo for PhenoGene. Given a list of HPO terms, we compute the similarity with a Gene
+-   Contact: [NLM/NCBI BioNLP Research Group](https://www.ncbi.nlm.nih.gov/research/bionlp/)
+	    """
+    )
+
+    st.markdown("")
+
+
+
+# Gene File, 128 dim embeddings
+gdf = pd.read_csv("data/diff2vec_gene_embd.csv").set_index("gene")
+genes = gdf.index.tolist()
+gene_emb = gdf.values
+gene_emb_data = {}
+for x,y in zip(genes, gene_emb):
+    gene_emb_data[x] = y.reshape(1, 128)
+st.session_state['gene_emb_data'] = gene_emb_data
+
+
+# All HPO embeddings, 128 dim embeddings
+hdf = pd.read_csv("data/diff2vec_hpo_embd.csv").set_index("hpo_id")
+hpos = hdf.index.tolist()
+hpo_emb = hdf.values
+hpo_emb_data = {}
+for x,y in zip(hpos, hpo_emb):
+    hpo_emb_data[x] = y.reshape(1, 128)
+st.session_state['hpo_emb_data'] = hpo_emb_data
+
+@st.cache(allow_output_mutation=True)
+def compute_similarity_with_gene(emb_src, genes, distance_metric='cosine'):
+    data = {}
+    for g in genes:
+        if distance_metric == "Cosine":
+            data[g] = cosine_similarity(emb_src, gene_emb_data[g]).item()
+    df = pd.DataFrame(data=data.items(), columns=['gene', 'cosine']).sort_values(by='cosine', ascending=False).reset_index()
+    return df
+
+@st.cache
+def convert_df(df):
+    # IMPORTANT: Cache the conversion to prevent computation on every rerun
+    return df.to_csv().encode('utf-8')
+
+st.subheader("Enter HPO terms separated by a comma")
+hpo_terms_text = st.text_area('Example: HP_0000006, HP_0000006')
+hpo_terms = list(map(str.strip, hpo_terms_text.split(',')))
+
+st.write("HPO Terms entered: ")
+st.write(hpo_terms)
+
+st.subheader("Hit Compute to calculate similarity to gene")
+metrics = 'Cosine'
+
+if st.button("Compute"):
+    with st.spinner('Computing...'):
+        for h in hpo_terms:
+            if h not in hpo_emb_data.keys():
+                st.error("No Embeddings.")
+                break
+            embs.append(hpo_emb_data[h])
+        embs_mean = np.array(embs).mean(axis=0)
+        result_df = compute_similarity_with_gene(embs_mean, genes, distance_metric=metrics)
+    csv = convert_df(result_df)
+    st.success("Done!")
+    st.dataframe(result_df)
+
+    st.download_button(
+    label="Download results as CSV",
+    data=csv,
+    mime='text/csv',
+)
+