hi

app.py

@@ -3,7 +3,7 @@ import pandas as pd
 import gradio as gr
 from transformers import PreTrainedTokenizerFast, BertForMaskedLM
 from datasets import load_dataset
-import xgboost_infer
+import infer
 
 embeddings_train = load_dataset("LofiAmazon/BOLD-Embeddings-Ecolayers-Amazon", split='train').to_pandas()
 
@@ -43,20 +43,23 @@ def preprocess():
 
 def predict_genus():
     data = preprocess()
-    out = xgboost_infer.infer_dna(data)
+    out = infer.infer_dna(data)
     
     results = []
 
-    genuses = xgboost_infer.infer()
+    genuses = infer.infer()
         
     results.append({
         "sequence": dna_df['nucraw'],
         # "predictions": pd.concat([dna_genuses, envdna_genuses], axis=0)
-        'predictions': genuses
-})
+        'predictions': genuses})
     
     return results
 
+def tsne():
+
+    return plots
+
 
 with gr.Blocks() as demo:
     # Header section
@@ -88,6 +91,13 @@ with gr.Blocks() as demo:
     
     with gr.Tab('DNA Embedding Space Similarity Visualizer'):
         gr.Markdown("If the highest genus probability is very low for your DNA sequence, we can still examine the DNA embedding of the sequence in relation to known samples for clues.")
+        with gr.Column():
+            gr.Markdown("Plot of your DNA sequence among other known species clusters.")
+
+        with gr.Column():
+            gr.Markdown("Plot of the five most common species at your sample coordinate.")
+
+
 
 
 demo.launch()