update

app.py

@@ -1,13 +1,16 @@
 import logging
+import os
 import pathlib
+import tempfile
 from typing import List, Optional
 
-from rdkit import Chem
-from tqdm import tqdm
 import gradio as gr
-from submission import submission
 import pandas as pd
+from rdkit import Chem
+from tqdm import tqdm
+
 from configuration import GENE_EXPRESSION_METADATA
+from submission import submission
 
 logger = logging.getLogger(__name__)
 logger.addHandler(logging.NullHandler())
@@ -26,13 +29,16 @@ def run_inference(
     omic_path: Optional[str],
     confidence: bool,
 ):
+
+    print(smiles)
+    print(smiles_path)
     # Read SMILES
     if not isinstance(smiles_path, (str, type(None))):
         raise TypeError(
             f"SMILES file pass has to be None or str, not {type(smiles_path)}"
         )
     if smiles is None and smiles_path is None:
-        raise TypeError(f"Pass either single SMILES or a file")
+        raise TypeError("Pass either single SMILES or a file")
     elif smiles is not None:
         smiles = [smiles]
     elif smiles_path is not None:
@@ -70,13 +76,11 @@ def run_inference(
             results[f"epistemic_confidence_{smi}"] = (
                 result["aleatoric_confidence"].squeeze().round(3)
             )
-    print(results)
     predicted_df = pd.DataFrame(results)
 
     # Prepare DF to visualize
     if omic_path is None:
-        df = GENE_EXPRESSION_METADATA
-        print(df.columns)
+        df = GENE_EXPRESSION_METADATA.copy()
         df.drop(
             [
                 "histology",
@@ -96,7 +100,11 @@ def run_inference(
         [df["cell_line"], predicted_df, df.drop(["cell_line"], axis=1)], axis=1
     )
 
-    return result_df, result_df
+    # Save to temporary dir
+    temp_path = os.path.join(tempfile.gettempdir(), "paccmann_result.csv")
+    result_df.to_csv(temp_path)
+
+    return temp_path, result_df.head(25)
 
 
 if __name__ == "__main__":
@@ -104,10 +112,11 @@ if __name__ == "__main__":
     # Load metadata
     metadata_root = pathlib.Path(__file__).parent.joinpath("model_cards")
 
-    examples = pd.read_csv(
-        metadata_root.joinpath("examples.csv"), header=None, sep="|"
-    ).fillna("")
-
+    examples = [
+        ["COc1cc(O)c2c(c1)C=CCC(O)C(O)C(=O)C=CCC(C)OC2=O", "", "", False],
+        ["COC1=C(C=C2C(=C1)N=CN=C2NC3=CC(=C(C=C3)F)Cl)OCCCN4CCOCC4", "", "", True],
+        ["", metadata_root.joinpath("molecules.smi"), "", False],
+    ]
     with open(metadata_root.joinpath("article.md"), "r") as f:
         article = f.read()
     with open(metadata_root.joinpath("description.md"), "r") as f:
@@ -124,17 +133,20 @@ if __name__ == "__main__":
             ),
             gr.File(
                 file_types=[".smi", ".tsv"],
-                label="List of SMILES (tab-separated file with SMILES in first column)",
+                label="Tab-separated file with SMILES in 1st column)",
             ),
             gr.File(
                 file_types=[".csv"],
-                label="Transcriptomics data with cell lines in rows and genes in columns",
+                label="Transcriptomics data file",
             ),
             gr.Radio(choices=[True, False], label="Estimate confidence", value=False),
         ],
-        outputs=[gr.DataFrame(label="Output"), gr.File()],
+        outputs=[
+            gr.File(label="Download full results"),
+            gr.DataFrame(label="Preview of results for 25 cell lines"),
+        ],
         article=article,
         description=description,
-        # examples=examples.values.tolist(),
+        examples=examples,
     )
     demo.launch(debug=True, show_error=True)