Various fixes and enhancements

app.py

@@ -43,7 +43,7 @@ def load_input_data(file: TextIOWrapper) -> pd.DataFrame:
     df = read_table(file.name)
     string_cols = list(df.select_dtypes(exclude=[np.number]))
     df = gr.Dataframe(value=df, visible=True)
-    return df, gr.Dropdown(choices=string_cols, interactive=True)
+    return df, gr.Dropdown(choices=string_cols, interactive=True, value=string_cols[0])
     
 
 def _clean_split_input(strings: str) -> List[str]:
@@ -95,7 +95,7 @@ def predict_one(
     prediction_df = convert_one(
         strings=strings,
         input_representation=input_representation,
-        output_representation=['id', 'pubhem_name', 'pubchem_id', 'smiles', 'inchikey', "mwt", "clogp"],
+        output_representation=['id', 'pubchem_name', 'pubchem_id', 'smiles', 'inchikey', "mwt", "clogp"],
     )
     species_to_predict = cast(predict, to=list)
     prediction_cols = []
@@ -125,8 +125,14 @@ def predict_one(
         this_col = f"{species}: predicted MIC (µM)"
         prediction_df[this_col] = np.power(10., -prediction) * 1e6
         prediction_cols.append(this_col)
+        this_col = f"{species}: predicted MIC (µg / mL)"
+        prediction_df[this_col] = np.power(10., -prediction) * 1e3 * prediction_df["mwt"]
+        prediction_cols.append(this_col)
 
         for extra_metric in extra_metrics:
+            message = f"Calculating {extra_metric} for species: {species}"
+            print_err(message)
+            gr.Info(message, duration=10)
             # this_modelbox._input_training_data = this_modelbox._input_training_data.remove_columns([this_modelbox._in_key])
             this_col = f"{species}: {extra_metric}"
             prediction_cols.append(this_col)
@@ -143,7 +149,7 @@ def predict_one(
             prediction_df[this_col] = this_extra[this_extra.column_names[-1]]
         
     return gr.DataFrame(
-        prediction_df[['id', 'pubhem_name', 'pubhem_id'] + prediction_cols + ['smiles', 'inchikey', "mwt", "clogp"]],
+        prediction_df[['id', 'pubchem_name', 'pubchem_id'] + prediction_cols + ['smiles', 'inchikey', "mwt", "clogp"]],
         visible=True
     )
 
@@ -352,13 +358,13 @@ with gr.Blocks() as demo:
             label="Download predictions",
             visible=False,
         )
-        with gr.Row():
-            output_line = gr.DataFrame(
-                label="Predictions",
-                interactive=False,
-                visible=False,
-            )
-            drawing = gr.Image(label="Chemical structures")
+        # with gr.Row():
+        output_line = gr.DataFrame(
+            label="Predictions",
+            interactive=False,
+            visible=False,
+        )
+        drawing = gr.Image(label="Chemical structures")
         gr.on(
             [
                 input_line.submit,
@@ -386,7 +392,7 @@ with gr.Blocks() as demo:
             outputs=download_single
         )
 
-    with gr.Tab("Convert a file (max. 1000 rows)"):
+    with gr.Tab("Predict on structures from a file (max. 1000 rows)"):
         input_file = gr.File(
             label="Upload a table of chemical compounds here",
             file_types=[".xlsx", ".csv", ".tsv", ".txt"],
@@ -395,6 +401,7 @@ with gr.Blocks() as demo:
             input_column = gr.Dropdown(
                 label="Input column name",
                 choices=[],
+                allow_custom_value=True,
             )
             input_format = gr.Dropdown(
                 label="Input string format",
@@ -414,6 +421,16 @@ with gr.Blocks() as demo:
             value=list(EXTRA_METRICS)[:2],
             interactive=True,
         )
+        examples = gr.Examples(
+            examples=[
+                ["example-data/stokes2020-eco.csv", "SMILES", "Klebsiella pneumoniae", list(EXTRA_METRICS)[:2]],
+            ],
+            example_labels=[
+                "Stokes J. et al., Cell, 2020"
+            ],
+            inputs=[input_file, input_column, output_species, extra_metric_file],
+            cache_mode="eager",
+        )
         go_button2 = gr.Button(
             value="Predict!",
         )

cache/csv/default-07681b79f1b14d09/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-2aeb4b2b0009691d.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e00fffd11ffc6775768e1aee277cf69a6f1c5fad161f58f81a0c108973e4d5b2
+size 50392

cache/csv/default-07681b79f1b14d09/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-c21a5c6a94888cd5.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d95031e58a0910c4f5a821302d53d4b3d00880add2c55c4665153a96ef998ff3
+size 2840

cache/csv/default-07681b79f1b14d09/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-d64525e5e55b104e.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cefa422d1f5c9834ca49f13b4676ee07e116d35bccb1dda0540e0fd35a96689
+size 50568

cache/csv/default-07681b79f1b14d09/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/csv-train.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d199d8e39ba5208a39ec0649dc34793a832395d8ee53499abc47db093c8f3418
+size 2016

cache/csv/default-07681b79f1b14d09/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/dataset_info.json

@@ -0,0 +1 @@
+{"description": "", "citation": "", "homepage": "", "license": "", "features": {"id": {"dtype": "int64", "_type": "Value"}, "pubchem_name": {"dtype": "string", "_type": "Value"}, "pubchem_id": {"dtype": "int64", "_type": "Value"}, "smiles": {"dtype": "string", "_type": "Value"}, "inchikey": {"dtype": "string", "_type": "Value"}, "mwt": {"dtype": "float64", "_type": "Value"}, "clogp": {"dtype": "float64", "_type": "Value"}, "pmic": {"dtype": "float64", "_type": "Value"}}, "builder_name": "csv", "dataset_name": "csv", "config_name": "default", "version": {"version_str": "0.0.0", "major": 0, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 494, "num_examples": 3, "dataset_name": "csv"}}, "download_checksums": {"/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/demos/mic-predict/./cache/duvida/b6f75c5672dc91ec.csv": {"num_bytes": 559, "checksum": null}}, "download_size": 559, "dataset_size": 494, "size_in_bytes": 1053}

cache/csv/default-0e1961df19e7f428/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-50f84085ae149c32.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af36ececee2d53db3cb5c1c65b60b8990d9bb61213f1ad1fdbb51dd9a1f74476
+size 66808

cache/csv/default-0e1961df19e7f428/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-b34dffbc8678394d.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed6ff94c00e4a4a939b7a4449592e5dce0790db450a59e11d9dfad03a84009b
+size 2984

cache/csv/default-0e1961df19e7f428/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-d8bfea4aba2e94b8.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34812693e78990f2f03d1c778dfc1bdfc7a238035bdc3a751ad011d986f6ee64
+size 66976

cache/csv/default-0e1961df19e7f428/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/csv-train.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d560d49222a8462930d119f6d2a1d9cf246b8c2d4d9542a5ca644aa6018f8d
+size 2128

cache/csv/default-0e1961df19e7f428/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/dataset_info.json

@@ -0,0 +1 @@
+{"description": "", "citation": "", "homepage": "", "license": "", "features": {"id": {"dtype": "int64", "_type": "Value"}, "pubchem_name": {"dtype": "string", "_type": "Value"}, "pubchem_id": {"dtype": "int64", "_type": "Value"}, "smiles": {"dtype": "string", "_type": "Value"}, "inchikey": {"dtype": "string", "_type": "Value"}, "mwt": {"dtype": "float64", "_type": "Value"}, "clogp": {"dtype": "float64", "_type": "Value"}, "pmic": {"dtype": "float64", "_type": "Value"}}, "builder_name": "csv", "dataset_name": "csv", "config_name": "default", "version": {"version_str": "0.0.0", "major": 0, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 593, "num_examples": 4, "dataset_name": "csv"}}, "download_checksums": {"/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/demos/mic-predict/./cache/duvida/efe79ad2617a4f83.csv": {"num_bytes": 658, "checksum": null}}, "download_size": 658, "dataset_size": 593, "size_in_bytes": 1251}

cache/csv/default-1bf129cb42f88409/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-23bb147ad76d70b5.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54aeb9b99f79344b722d9edc55ce199fec0cd7221905c65a5743ed28a9ddda80
+size 2984

cache/csv/default-1bf129cb42f88409/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-48f7855e49c99499.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c337d77d4b11d7dedc8de9ab1dd40c1112495d2ac284e630369352e6beb8bcbe
+size 66808

cache/csv/default-1bf129cb42f88409/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-806cef9cf8bee5aa.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288bbdb5f5c12a1edfc78a4a3944696945f4df8966a97dafc5c327f90350e340
+size 66984

cache/csv/default-1bf129cb42f88409/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/csv-train.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d560d49222a8462930d119f6d2a1d9cf246b8c2d4d9542a5ca644aa6018f8d
+size 2128

cache/csv/default-1bf129cb42f88409/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/dataset_info.json

@@ -0,0 +1 @@
+{"description": "", "citation": "", "homepage": "", "license": "", "features": {"id": {"dtype": "int64", "_type": "Value"}, "pubchem_name": {"dtype": "string", "_type": "Value"}, "pubchem_id": {"dtype": "int64", "_type": "Value"}, "smiles": {"dtype": "string", "_type": "Value"}, "inchikey": {"dtype": "string", "_type": "Value"}, "mwt": {"dtype": "float64", "_type": "Value"}, "clogp": {"dtype": "float64", "_type": "Value"}, "pmic": {"dtype": "float64", "_type": "Value"}}, "builder_name": "csv", "dataset_name": "csv", "config_name": "default", "version": {"version_str": "0.0.0", "major": 0, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 593, "num_examples": 4, "dataset_name": "csv"}}, "download_checksums": {"/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/demos/mic-predict/./cache/duvida/efe79ad2617a4f83.csv": {"num_bytes": 658, "checksum": null}}, "download_size": 658, "dataset_size": 593, "size_in_bytes": 1251}

cache/csv/default-5092df56bc4a09a8/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-1df7ee43301cb031.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e5c508821f1c9e13c2eff2940ebdb56e1b8214ae0b1af4aee1bd9d72c26825
+size 2840

cache/csv/default-5092df56bc4a09a8/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-3ac6f9a1516dfeef.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74e337aade4e5082e66f62572e84bc12132487f3ae60d50e6b583d08d50dbc1d
+size 50560

cache/csv/default-5092df56bc4a09a8/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-f6fe9763b6fe0d1e.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:574570ef0a30b3d2509876b1e7ddb08c60010a7ca335c58f9f8ee4adafed3cdf
+size 50392

cache/csv/default-5092df56bc4a09a8/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/csv-train.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d199d8e39ba5208a39ec0649dc34793a832395d8ee53499abc47db093c8f3418
+size 2016

cache/csv/default-5092df56bc4a09a8/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/dataset_info.json

@@ -0,0 +1 @@
+{"description": "", "citation": "", "homepage": "", "license": "", "features": {"id": {"dtype": "int64", "_type": "Value"}, "pubchem_name": {"dtype": "string", "_type": "Value"}, "pubchem_id": {"dtype": "int64", "_type": "Value"}, "smiles": {"dtype": "string", "_type": "Value"}, "inchikey": {"dtype": "string", "_type": "Value"}, "mwt": {"dtype": "float64", "_type": "Value"}, "clogp": {"dtype": "float64", "_type": "Value"}, "pmic": {"dtype": "float64", "_type": "Value"}}, "builder_name": "csv", "dataset_name": "csv", "config_name": "default", "version": {"version_str": "0.0.0", "major": 0, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 494, "num_examples": 3, "dataset_name": "csv"}}, "download_checksums": {"/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/demos/mic-predict/./cache/duvida/b6f75c5672dc91ec.csv": {"num_bytes": 559, "checksum": null}}, "download_size": 559, "dataset_size": 494, "size_in_bytes": 1053}

cache/csv/default-53b2b16e1030c75e/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-0424f85f112a67b9.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e91f287eec5fe1ecd2aa76063ddb1e1be06264be71be9c702b038ddf7930ab9
+size 488

cache/csv/default-53b2b16e1030c75e/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-7d79a5e5099b00bb.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68956d107fcf98cb600381499871ee3863d898851bf6956d6b16459a607f49f3
+size 66808

cache/csv/default-53b2b16e1030c75e/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-9f78601eb92d2b49.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbcd888032262e93f223dc3d1f5de520af3e2a336383c6e0887756aebd96a7e3
+size 66984

cache/csv/default-53b2b16e1030c75e/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/cache-cbee221c796d5798.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa2eddeff87b208d6c89a7d0f05dee0769cd87463aba77ee105bb5177c7d99d
+size 2984

cache/csv/default-53b2b16e1030c75e/0.0.0/a43390c7ecea6519ff2ce9d10005c8750601c9e456069be5efbd2747df45f420/csv-train.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d560d49222a8462930d119f6d2a1d9cf246b8c2d4d9542a5ca644aa6018f8d
+size 2128