Spaces:
Sleeping
Sleeping
Fix Gradio cache cleanup breaking update_image
Browse files- codes/gradio_utils.py +528 -253
codes/gradio_utils.py
CHANGED
|
@@ -10,20 +10,54 @@ import pickle
|
|
| 10 |
import pandas as pd
|
| 11 |
import xgboost as xgb
|
| 12 |
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
os.remove(f.name)
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
markdown_text = """
|
| 28 |
**Feature Category Explanations**
|
| 29 |
|
|
@@ -62,128 +96,200 @@ cancer_types_to_consider = ['Acute Myeloid Leukemia', 'Bladder Urothelial Carcin
|
|
| 62 |
|
| 63 |
all_features = pd.read_csv('./data/onconpc_features.csv').drop('Unnamed: 0', axis=1).columns.tolist()
|
| 64 |
|
| 65 |
-
def get_preds(patients_file, samples_file, mutations_file, cna_file, tumor_id):
|
| 66 |
-
|
| 67 |
"""
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
|
| 73 |
Args:
|
| 74 |
-
patients_file:
|
| 75 |
-
samples_file:
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
|
| 80 |
Returns:
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
|
|
|
|
|
|
| 84 |
"""
|
| 85 |
-
#
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
#
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
|
|
|
|
|
|
|
| 94 |
else:
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
|
| 121 |
-
|
| 122 |
-
|
| 123 |
-
|
| 124 |
-
|
| 125 |
-
|
| 126 |
-
|
| 127 |
-
|
| 128 |
-
|
| 129 |
-
|
| 130 |
-
|
| 131 |
-
raise gr.Error(
|
| 132 |
-
|
| 133 |
-
|
| 134 |
-
|
| 135 |
-
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
|
| 142 |
-
|
| 143 |
-
|
| 144 |
-
|
| 145 |
-
|
| 146 |
-
|
| 147 |
-
|
| 148 |
-
|
| 149 |
-
|
| 150 |
-
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
|
| 155 |
-
|
| 156 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 157 |
)
|
| 158 |
-
sample_id = tumor_id
|
| 159 |
-
features = df_features_genie_final
|
| 160 |
-
|
| 161 |
-
# load fully trained OncoNPC model
|
| 162 |
-
xgb_onconpc = xgb.Booster()
|
| 163 |
-
xgb_onconpc.load_model('./model/xgboost_v1.7.6_OncoNPC_full.json')
|
| 164 |
-
|
| 165 |
-
# predict primary sites of CUP tumors
|
| 166 |
-
predictions = utils.get_xgboost_latest_cancer_type_preds(xgb_onconpc,
|
| 167 |
-
features,
|
| 168 |
-
cancer_types_to_consider)
|
| 169 |
-
|
| 170 |
-
# get SHAP values for CUP tumors
|
| 171 |
-
warnings.filterwarnings('ignore')
|
| 172 |
-
shaps = utils.obtain_shap_values_with_latest_xgboost(xgb_onconpc, df_features_genie_final)
|
| 173 |
-
|
| 174 |
|
| 175 |
-
|
| 176 |
-
|
| 177 |
-
#
|
| 178 |
-
|
| 179 |
-
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
|
| 183 |
-
|
| 184 |
-
result = get_top3(predictions, tumor_id), gr.Markdown(markdown_text), results[tumor_id]['explanation_plot']
|
| 185 |
-
cleanup([patients_file, samples_file, mutations_file, cna_file])
|
| 186 |
-
return result
|
| 187 |
|
| 188 |
def parse_inputs(age, gender, CNA_events, mutations):
|
| 189 |
# Normalization of age input
|
|
@@ -272,55 +378,91 @@ def parse_inputs(age, gender, CNA_events, mutations):
|
|
| 272 |
# Return the data as a DataFrame
|
| 273 |
return pd.DataFrame([data])
|
| 274 |
|
| 275 |
-
def get_preds_min_info(age, gender, CNA_events, mutations, output=
|
| 276 |
"""
|
| 277 |
-
|
|
|
|
|
|
|
|
|
|
| 278 |
|
| 279 |
-
|
| 280 |
-
|
| 281 |
-
|
| 282 |
-
|
| 283 |
-
|
| 284 |
-
|
|
|
|
| 285 |
|
| 286 |
Returns:
|
| 287 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 288 |
"""
|
| 289 |
-
|
| 290 |
-
|
| 291 |
-
|
| 292 |
-
|
| 293 |
-
# Parse input features
|
| 294 |
features = parse_inputs(age, gender, CNA_events, mutations)
|
| 295 |
-
|
| 296 |
-
|
| 297 |
-
|
| 298 |
-
|
| 299 |
-
|
| 300 |
-
|
| 301 |
-
|
| 302 |
-
|
| 303 |
-
|
| 304 |
-
|
| 305 |
-
#
|
| 306 |
-
|
| 307 |
-
|
| 308 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 309 |
shaps = utils.obtain_shap_values_with_latest_xgboost(xgb_onconpc, features)
|
| 310 |
|
| 311 |
-
#
|
| 312 |
query_ids = [0]
|
| 313 |
-
|
| 314 |
-
|
| 315 |
-
|
| 316 |
-
|
| 317 |
-
|
| 318 |
-
|
|
|
|
|
|
|
| 319 |
|
| 320 |
-
#
|
| 321 |
-
|
| 322 |
-
|
| 323 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 324 |
|
| 325 |
def get_top3(predictions, tumor_sample_id):
|
| 326 |
"""
|
|
@@ -378,27 +520,77 @@ def extract_sample_ids(samples_file):
|
|
| 378 |
sample_ids = df['SAMPLE_ID'].unique().tolist()
|
| 379 |
return gr.Dropdown(choices=sample_ids)
|
| 380 |
|
| 381 |
-
def update_image(target):
|
| 382 |
-
|
| 383 |
-
|
| 384 |
-
global predictions
|
| 385 |
-
|
| 386 |
-
shaps_cup = utils.obtain_shap_values_with_latest_xgboost(xgb_onconpc, features) # get shap values
|
| 387 |
|
| 388 |
-
|
| 389 |
-
|
| 390 |
-
|
| 391 |
-
|
| 392 |
-
|
| 393 |
-
|
| 394 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 395 |
shap_pred_sample_df = shap_pred_cancer_df.loc[sample_id]
|
|
|
|
|
|
|
|
|
|
| 396 |
probability = predictions.loc[sample_id][target]
|
| 397 |
-
|
| 398 |
-
#
|
| 399 |
-
|
| 400 |
-
|
| 401 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 402 |
return explanation_plot
|
| 403 |
|
| 404 |
def show_row(value):
|
|
@@ -432,102 +624,185 @@ def show_row(value):
|
|
| 432 |
|
| 433 |
def launch_gradio(server_name, server_port):
|
| 434 |
"""
|
| 435 |
-
|
|
|
|
| 436 |
|
| 437 |
Args:
|
| 438 |
-
|
| 439 |
-
|
| 440 |
|
| 441 |
-
|
| 442 |
-
|
| 443 |
"""
|
| 444 |
-
|
| 445 |
-
|
| 446 |
-
|
| 447 |
-
|
| 448 |
-
|
| 449 |
-
|
| 450 |
-
|
| 451 |
-
|
| 452 |
-
|
| 453 |
-
|
| 454 |
-
|
| 455 |
-
|
| 456 |
-
|
| 457 |
-
|
| 458 |
-
|
| 459 |
-
|
| 460 |
-
|
| 461 |
-
|
| 462 |
-
|
| 463 |
-
|
| 464 |
-
|
| 465 |
-
|
| 466 |
-
|
| 467 |
-
|
| 468 |
-
|
| 469 |
-
- SBS24: Aflatoxin exposure
|
| 470 |
-
- See more details in [COSMIC](https://cancer.sanger.ac.uk/signatures/sbs/).
|
| 471 |
-
|
| 472 |
-
**Age/Sex**: Patient age at the time of sequencing and biological sex.
|
| 473 |
-
|
| 474 |
-
**SHAP Values**: impact on OncoNPC prediction
|
| 475 |
-
- larger magnitude indicates greater impact
|
| 476 |
-
"""
|
| 477 |
-
manual_input_description = 'In this option, you will manually enter patient and tumor data including age at sequencing, sex, copy number alterations (CNA) events, and somatic mutations.'
|
| 478 |
-
csv_description = 'In this option, you can directly upload relevant CSV files, including clinical patient, clinical sample, mutations, and CNA data from [cBioPortal](https://www.cbioportal.org) or [AACR GENIE](https://www.aacr.org/professionals/research/aacr-project-genie/). Please see the example data in this [link](https://github.com/itmoon7/onconpc/tree/main/data/mock_n_3_data) <br> Note that column names `Tumor_Sample_Barcode` and `SAMPLE_ID` both refer to the sample identifier column and should be the same.'
|
| 479 |
-
|
| 480 |
-
with gr.Blocks(css=".markdown-box { border: 1px solid #E0E0E0; border-radius: 8px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.05); padding: 15px; margin-bottom: 20px; }") as demo:
|
| 481 |
-
|
| 482 |
-
d = gr.Dropdown(label='Select your preferred input method for tumor data to visualize predictions made by OncoNPC', choices=["Manual Inputs", "CSV File"])
|
| 483 |
|
|
|
|
| 484 |
with gr.Row(visible=False) as r3:
|
| 485 |
-
gr.Markdown(csv_description,elem_classes="markdown-box")
|
| 486 |
with gr.Row(visible=False) as r4:
|
| 487 |
-
gr.Markdown(manual_input_description,elem_classes="markdown-box")
|
| 488 |
|
|
|
|
|
|
|
|
|
|
| 489 |
with gr.Row(visible=False) as r1:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 490 |
with gr.Column():
|
| 491 |
-
gr.Markdown("**Clinical Patient Data File:**
|
| 492 |
patients_file = gr.File(label="Upload clinical patients data")
|
| 493 |
-
|
|
|
|
| 494 |
samples_file = gr.File(label="Upload clinical samples data")
|
| 495 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 496 |
mutations_file = gr.File(label="Upload mutations data")
|
| 497 |
-
|
|
|
|
| 498 |
cna_file = gr.File(label="Upload CNA data")
|
| 499 |
-
|
| 500 |
-
|
|
|
|
|
|
|
|
|
|
| 501 |
|
| 502 |
with gr.Column():
|
| 503 |
predictions_output = gr.Textbox(label="Top 3 Predicted Cancer Types")
|
| 504 |
-
category_explanation = gr.Markdown(markdown_text,elem_classes="markdown-box")
|
| 505 |
-
|
| 506 |
-
|
| 507 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 508 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 509 |
samples_file.change(extract_sample_ids, inputs=samples_file, outputs=tumor_sample_id)
|
| 510 |
-
submit_button.click(get_preds, inputs=[patients_file, samples_file, mutations_file, cna_file, tumor_sample_id], outputs=[predictions_output, category_explanation, image])
|
| 511 |
-
output_selector.change(update_image, inputs=output_selector, outputs=[image])
|
| 512 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 513 |
with gr.Row(visible=False) as r2:
|
|
|
|
|
|
|
|
|
|
| 514 |
with gr.Column():
|
| 515 |
age = gr.Number(label="Age")
|
| 516 |
gender = gr.Radio(choices=["Male", "Female"], label="Sex")
|
| 517 |
-
cna_events = gr.Textbox(lines=7, placeholder="Copy Number Alterations\n\nPlease enter the name of each gene followed by its corresponding CNA level. If you are entering data for multiple genes, separate each gene and its CNA level with a vertical bar '|'.\n\nFor example: RAF1 2 | PPARG 2", label="Genes with CNA Events")
|
| 518 |
-
mutations = gr.Textbox(lines=7, placeholder="Somatic Mutations\n\nPlease enter the gene name, chromosome number, position of the variant, allele in the reference genome, and alternate allele. If you are entering data for multiple genes, separate each set of information with a vertical bar '|'.\n\nFor example: ERBB2, chr17, 37868208, C, T | CDKN1A, chr6, 36651880, -, GTCAGAACCGGCTGGGGATGTCC", label="Mutations")
|
| 519 |
-
submit_button = gr.Button("Submit")
|
| 520 |
-
with gr.Column():
|
| 521 |
-
predictions_output = gr.Textbox(label="Top 3 Predicted Cancer Types")
|
| 522 |
-
category_explanation = gr.Markdown(markdown_text,elem_classes="markdown-box")
|
| 523 |
-
image = gr.Image(label="Image Display")
|
| 524 |
-
output_selector = gr.Dropdown(choices=cancer_types_to_consider, label="Output Options", filterable=True)
|
| 525 |
-
gr.Markdown('For more details regarding OncoNPC feature processing, OncoNPC performance, and clinical implications of OncoNPC predictions, please see our [manuscript](https://www.nature.com/articles/s41591-023-02482-6).', elem_classes="markdown-box")
|
| 526 |
|
| 527 |
-
|
| 528 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 529 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 530 |
d.change(show_row, d, [r1, r2])
|
| 531 |
d.change(show_row, d, [r3, r4])
|
| 532 |
-
|
| 533 |
-
|
|
|
|
|
|
| 10 |
import pandas as pd
|
| 11 |
import xgboost as xgb
|
| 12 |
|
| 13 |
+
|
| 14 |
+
def cleanup_files(uploaded_files=None):
|
| 15 |
+
"""
|
| 16 |
+
Remove uploaded temporary files from disk without touching any session/model state.
|
| 17 |
+
|
| 18 |
+
Args:
|
| 19 |
+
uploaded_files (list | None): Optional list of Gradio `File` objects (or file-like objects)
|
| 20 |
+
that have a `.name` attribute pointing to a local temporary filepath.
|
| 21 |
+
|
| 22 |
+
Returns:
|
| 23 |
+
None
|
| 24 |
+
"""
|
| 25 |
+
# Nothing to do if caller didn't pass any files
|
| 26 |
+
if not uploaded_files:
|
| 27 |
+
return
|
| 28 |
+
|
| 29 |
+
# Best-effort cleanup: never crash the app due to deletion failure.
|
| 30 |
+
for f in uploaded_files:
|
| 31 |
+
try:
|
| 32 |
+
# Gradio may pass `None` for an unfilled upload component
|
| 33 |
+
if f is None:
|
| 34 |
+
continue
|
| 35 |
+
|
| 36 |
+
# Gradio File objects expose the local temp path as `.name`
|
| 37 |
+
if not hasattr(f, "name"):
|
| 38 |
+
continue
|
| 39 |
+
|
| 40 |
+
# Delete the temp file if it still exists
|
| 41 |
+
if os.path.exists(f.name):
|
| 42 |
os.remove(f.name)
|
| 43 |
|
| 44 |
+
except Exception:
|
| 45 |
+
# Never fail the entire UI due to a cleanup issue
|
| 46 |
+
pass
|
| 47 |
+
|
| 48 |
+
def _reset_state(_):
|
| 49 |
+
"""
|
| 50 |
+
Clear per-session cached inference state when upstream inputs change.
|
| 51 |
+
|
| 52 |
+
Args:
|
| 53 |
+
_ (Any): Placeholder input (e.g., the changed Gradio component value). Not used.
|
| 54 |
+
|
| 55 |
+
Returns:
|
| 56 |
+
None: Used to overwrite `gr.State` so the next Submit recomputes features/predictions.
|
| 57 |
+
"""
|
| 58 |
+
# Returning None here is a simple "invalidate cache" signal
|
| 59 |
+
return None
|
| 60 |
+
|
| 61 |
markdown_text = """
|
| 62 |
**Feature Category Explanations**
|
| 63 |
|
|
|
|
| 96 |
|
| 97 |
all_features = pd.read_csv('./data/onconpc_features.csv').drop('Unnamed: 0', axis=1).columns.tolist()
|
| 98 |
|
| 99 |
+
def get_preds(patients_file, samples_file, mutations_file, cna_file, tumor_id, state):
|
|
|
|
| 100 |
"""
|
| 101 |
+
Run OncoNPC inference from uploaded CSV/TXT inputs and return:
|
| 102 |
+
- top-3 predictions,
|
| 103 |
+
- default explanation plot for the selected sample,
|
| 104 |
+
- updated per-session state for later dropdown interactions.
|
| 105 |
|
| 106 |
Args:
|
| 107 |
+
patients_file (gradio.File | None): Uploaded patient file (CSV/TXT) with required columns `PATIENT_ID`, `SEX`.
|
| 108 |
+
samples_file (gradio.File | None): Uploaded sample file (CSV/TXT) with required columns
|
| 109 |
+
`PATIENT_ID`, `AGE_AT_SEQ_REPORT`, `SAMPLE_ID`.
|
| 110 |
+
mutations_file (gradio.File | None): Uploaded mutations file (CSV/TXT) with required columns
|
| 111 |
+
`Tumor_Sample_Barcode`, `Hugo_Symbol`, `Chromosome`, `Start_Position`, `Reference_Allele`, `Tumor_Seq_Allele2`.
|
| 112 |
+
cna_file (gradio.File | None): Uploaded CNA file (CSV/TXT) with required column `Hugo_Symbol`.
|
| 113 |
+
tumor_id (str | int | None): Sample identifier selected by the user.
|
| 114 |
+
state (dict | None): Per-session cache (from `gr.State`). Expected keys:
|
| 115 |
+
- "features": pd.DataFrame (rows=samples, cols=features)
|
| 116 |
+
- "predictions": pd.DataFrame (rows=samples, cols=cancer types + metadata)
|
| 117 |
+
- "sample_id": current sample being interpreted
|
| 118 |
|
| 119 |
Returns:
|
| 120 |
+
tuple:
|
| 121 |
+
(top3_text: str,
|
| 122 |
+
markdown: gr.Markdown,
|
| 123 |
+
explanation_plot_path: str,
|
| 124 |
+
state: dict)
|
| 125 |
"""
|
| 126 |
+
# ------------------------------------------------------------------
|
| 127 |
+
# 0) Decide whether to reuse cached computations
|
| 128 |
+
# ------------------------------------------------------------------
|
| 129 |
+
# If the user is only changing tumor_id (dropdown) and re-submitting,
|
| 130 |
+
# we can reuse previously computed features/predictions and avoid:
|
| 131 |
+
# - re-reading files
|
| 132 |
+
# - recomputing features
|
| 133 |
+
# - recomputing predictions for all samples
|
| 134 |
+
if state is not None and state.get("features") is not None and state.get("predictions") is not None:
|
| 135 |
+
features = state["features"]
|
| 136 |
+
predictions = state["predictions"]
|
| 137 |
else:
|
| 138 |
+
# ------------------------------------------------------------------
|
| 139 |
+
# 1) First-run path: validate uploads exist
|
| 140 |
+
# ------------------------------------------------------------------
|
| 141 |
+
if patients_file is None or samples_file is None or cna_file is None or mutations_file is None:
|
| 142 |
+
raise gr.Error("Please make sure all files have been properly uploaded")
|
| 143 |
+
|
| 144 |
+
# ------------------------------------------------------------------
|
| 145 |
+
# 2) Read uploaded files into DataFrames
|
| 146 |
+
# ------------------------------------------------------------------
|
| 147 |
+
# NOTE: Gradio stores uploads as temp files; access path via `.name`.
|
| 148 |
+
if patients_file.name.endswith(".txt"):
|
| 149 |
+
patients_df = pd.read_csv(patients_file.name, sep="\t")
|
| 150 |
+
elif patients_file.name.endswith(".csv"):
|
| 151 |
+
patients_df = pd.read_csv(patients_file.name)
|
| 152 |
+
else:
|
| 153 |
+
raise gr.Error("Patients file must be .txt or .csv")
|
| 154 |
+
|
| 155 |
+
if samples_file.name.endswith(".txt"):
|
| 156 |
+
samples_df = pd.read_csv(samples_file.name, sep="\t")
|
| 157 |
+
elif samples_file.name.endswith(".csv"):
|
| 158 |
+
samples_df = pd.read_csv(samples_file.name) # BUGFIX: was patients_file in original code
|
| 159 |
+
else:
|
| 160 |
+
raise gr.Error("Samples file must be .txt or .csv")
|
| 161 |
+
|
| 162 |
+
if mutations_file.name.endswith(".txt"):
|
| 163 |
+
mutations_df = pd.read_csv(mutations_file.name, sep="\t")
|
| 164 |
+
elif mutations_file.name.endswith(".csv"):
|
| 165 |
+
mutations_df = pd.read_csv(mutations_file.name)
|
| 166 |
+
else:
|
| 167 |
+
raise gr.Error("Mutations file must be .txt or .csv")
|
| 168 |
+
|
| 169 |
+
if cna_file.name.endswith(".txt"):
|
| 170 |
+
cna_df = pd.read_csv(cna_file.name, sep="\t")
|
| 171 |
+
elif cna_file.name.endswith(".csv"):
|
| 172 |
+
cna_df = pd.read_csv(cna_file.name)
|
| 173 |
+
else:
|
| 174 |
+
raise gr.Error("CNA file must be .txt or .csv")
|
| 175 |
+
|
| 176 |
+
# ------------------------------------------------------------------
|
| 177 |
+
# 3) Validate the selected tumor_id
|
| 178 |
+
# ------------------------------------------------------------------
|
| 179 |
+
if tumor_id is None or str(tumor_id).strip() == "":
|
| 180 |
+
raise gr.Error("Tumor Sample ID cannot be empty")
|
| 181 |
+
|
| 182 |
+
# ------------------------------------------------------------------
|
| 183 |
+
# 4) Validate expected columns (fail fast with friendly errors)
|
| 184 |
+
# ------------------------------------------------------------------
|
| 185 |
+
patients_columns = {"PATIENT_ID", "SEX"}
|
| 186 |
+
if not patients_columns.issubset(set(patients_df.columns)):
|
| 187 |
+
raise gr.Error(
|
| 188 |
+
f"Patients File: Expected columns {sorted(patients_columns)}, "
|
| 189 |
+
f"Received {patients_df.columns.to_list()}"
|
| 190 |
+
)
|
| 191 |
+
|
| 192 |
+
samples_columns = {"PATIENT_ID", "AGE_AT_SEQ_REPORT", "SAMPLE_ID"}
|
| 193 |
+
if not samples_columns.issubset(set(samples_df.columns)):
|
| 194 |
+
raise gr.Error(
|
| 195 |
+
f"Samples File: Expected columns {sorted(samples_columns)}, "
|
| 196 |
+
f"Received {samples_df.columns.to_list()}"
|
| 197 |
+
)
|
| 198 |
+
|
| 199 |
+
mutations_columns = {
|
| 200 |
+
"Tumor_Sample_Barcode",
|
| 201 |
+
"Hugo_Symbol",
|
| 202 |
+
"Chromosome",
|
| 203 |
+
"Start_Position",
|
| 204 |
+
"Reference_Allele",
|
| 205 |
+
"Tumor_Seq_Allele2",
|
| 206 |
+
}
|
| 207 |
+
if not mutations_columns.issubset(set(mutations_df.columns)):
|
| 208 |
+
raise gr.Error(
|
| 209 |
+
f"Mutations File: Expected columns {sorted(mutations_columns)}, "
|
| 210 |
+
f"Received {mutations_df.columns.to_list()}"
|
| 211 |
+
)
|
| 212 |
+
|
| 213 |
+
cna_columns = {"Hugo_Symbol"}
|
| 214 |
+
if not cna_columns.issubset(set(cna_df.columns)):
|
| 215 |
+
raise gr.Error(
|
| 216 |
+
f"CNA File: Expected columns {sorted(cna_columns)}, "
|
| 217 |
+
f"Received {cna_df.columns.to_list()}"
|
| 218 |
+
)
|
| 219 |
+
|
| 220 |
+
# ------------------------------------------------------------------
|
| 221 |
+
# 5) Build OncoNPC feature matrix from raw inputs
|
| 222 |
+
# ------------------------------------------------------------------
|
| 223 |
+
# `features` should end up indexed by sample IDs compatible with tumor_id dropdown.
|
| 224 |
+
df_features_genie_final, _ = utils.get_onconpc_features_from_raw_data(
|
| 225 |
+
patients_df,
|
| 226 |
+
samples_df,
|
| 227 |
+
mutations_df,
|
| 228 |
+
cna_df,
|
| 229 |
+
features_onconpc_path="./data/features_onconpc.pkl",
|
| 230 |
+
combined_cohort_age_stats_path="./data/combined_cohort_age_stats.pkl",
|
| 231 |
+
mut_sig_weights_filepath="./data/mutation_signatures/sigProfiler*.csv",
|
| 232 |
+
)
|
| 233 |
+
features = df_features_genie_final
|
| 234 |
+
|
| 235 |
+
# ------------------------------------------------------------------
|
| 236 |
+
# 6) Predict for all samples
|
| 237 |
+
# ------------------------------------------------------------------
|
| 238 |
+
# We assume `xgb_onconpc` is loaded at module scope.
|
| 239 |
+
predictions = utils.get_xgboost_latest_cancer_type_preds(
|
| 240 |
+
xgb_onconpc,
|
| 241 |
+
features,
|
| 242 |
+
cancer_types_to_consider,
|
| 243 |
+
)
|
| 244 |
+
|
| 245 |
+
# ------------------------------------------------------------------
|
| 246 |
+
# 7) Cache these in session state so dropdown interactions work
|
| 247 |
+
# ------------------------------------------------------------------
|
| 248 |
+
state = {"features": features, "predictions": predictions}
|
| 249 |
+
|
| 250 |
+
# ------------------------------------------------------------------
|
| 251 |
+
# 8) Optional: delete temp uploaded files now that they're read into memory
|
| 252 |
+
# ------------------------------------------------------------------
|
| 253 |
+
# This prevents disk bloat on Spaces.
|
| 254 |
+
cleanup_files([patients_file, samples_file, mutations_file, cna_file])
|
| 255 |
+
|
| 256 |
+
# ------------------------------------------------------------------
|
| 257 |
+
# 9) Set the sample being interpreted for this session
|
| 258 |
+
# ------------------------------------------------------------------
|
| 259 |
+
if tumor_id not in state["features"].index:
|
| 260 |
+
raise gr.Error(f"Tumor Sample ID {tumor_id} not found in computed features index.")
|
| 261 |
+
state["sample_id"] = tumor_id
|
| 262 |
+
|
| 263 |
+
# ------------------------------------------------------------------
|
| 264 |
+
# 10) Compute SHAP + generate a plot for the currently selected sample
|
| 265 |
+
# ------------------------------------------------------------------
|
| 266 |
+
# IMPORTANT: Only compute SHAP for one sample to keep this lightweight and fast.
|
| 267 |
+
warnings.filterwarnings("ignore")
|
| 268 |
+
features_one = state["features"].loc[[tumor_id]]
|
| 269 |
+
shaps = utils.obtain_shap_values_with_latest_xgboost(xgb_onconpc, features_one)
|
| 270 |
+
|
| 271 |
+
# Keep predictions consistent with `features_one`
|
| 272 |
+
preds_one = state["predictions"].loc[[tumor_id]]
|
| 273 |
+
|
| 274 |
+
# `results` is a dict keyed by query_id; each entry includes explanation_plot path
|
| 275 |
+
results = utils.get_onconpc_prediction_explanations(
|
| 276 |
+
[tumor_id],
|
| 277 |
+
preds_one,
|
| 278 |
+
shaps,
|
| 279 |
+
features_one,
|
| 280 |
+
cancer_types_to_consider,
|
| 281 |
+
save_plot=True,
|
| 282 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 283 |
|
| 284 |
+
# ------------------------------------------------------------------
|
| 285 |
+
# 11) Return UI outputs + updated state
|
| 286 |
+
# ------------------------------------------------------------------
|
| 287 |
+
return (
|
| 288 |
+
get_top3(state["predictions"], tumor_id),
|
| 289 |
+
gr.Markdown(markdown_text),
|
| 290 |
+
results[tumor_id]["explanation_plot"],
|
| 291 |
+
state,
|
| 292 |
+
)
|
|
|
|
|
|
|
|
|
|
| 293 |
|
| 294 |
def parse_inputs(age, gender, CNA_events, mutations):
|
| 295 |
# Normalization of age input
|
|
|
|
| 378 |
# Return the data as a DataFrame
|
| 379 |
return pd.DataFrame([data])
|
| 380 |
|
| 381 |
+
def get_preds_min_info(age, gender, CNA_events, mutations, state, output="Top Prediction"):
|
| 382 |
"""
|
| 383 |
+
Run OncoNPC inference from manual inputs and return:
|
| 384 |
+
- top-3 predictions,
|
| 385 |
+
- default explanation plot (top prediction) for the manual sample,
|
| 386 |
+
- updated per-session state.
|
| 387 |
|
| 388 |
+
Args:
|
| 389 |
+
age (int | float): Age at sequencing/report; standardized using cohort stats.
|
| 390 |
+
gender (str): "Male" or "Female".
|
| 391 |
+
CNA_events (str): CNA event string like "RAF1 2 | PPARG 2".
|
| 392 |
+
mutations (str): Mutation string like "ERBB2, chr17, 378..., C, T | ...".
|
| 393 |
+
state (dict | None): Per-session cache (from `gr.State`). Will be overwritten.
|
| 394 |
+
output (str): Reserved for future output selection. Currently unused.
|
| 395 |
|
| 396 |
Returns:
|
| 397 |
+
tuple:
|
| 398 |
+
(top3_text: str,
|
| 399 |
+
markdown: gr.Markdown,
|
| 400 |
+
explanation_plot_path: str,
|
| 401 |
+
state: dict)
|
| 402 |
"""
|
| 403 |
+
# ------------------------------------------------------------------
|
| 404 |
+
# 1) Parse manual inputs into a single-row feature frame
|
| 405 |
+
# ------------------------------------------------------------------
|
| 406 |
+
# parse_inputs() should produce a DataFrame with one row (the "manual input" sample)
|
|
|
|
| 407 |
features = parse_inputs(age, gender, CNA_events, mutations)
|
| 408 |
+
|
| 409 |
+
# ------------------------------------------------------------------
|
| 410 |
+
# 2) Ensure feature columns match training features exactly (same set + same order)
|
| 411 |
+
# ------------------------------------------------------------------
|
| 412 |
+
all_features_local = (
|
| 413 |
+
pd.read_csv("./data/onconpc_features.csv")
|
| 414 |
+
.drop("Unnamed: 0", axis=1)
|
| 415 |
+
.columns.tolist()
|
| 416 |
+
)
|
| 417 |
+
|
| 418 |
+
# Drop any extra columns not in training feature list
|
| 419 |
+
for c in list(features.columns):
|
| 420 |
+
if c not in all_features_local:
|
| 421 |
+
features = features.drop(c, axis=1)
|
| 422 |
+
|
| 423 |
+
# Add missing columns as zeros
|
| 424 |
+
missing_cols = [c for c in all_features_local if c not in features.columns]
|
| 425 |
+
if missing_cols:
|
| 426 |
+
features = pd.concat([features, pd.DataFrame({c: [0] for c in missing_cols})], axis=1)
|
| 427 |
+
|
| 428 |
+
# Reorder columns to match training
|
| 429 |
+
features = features[all_features_local]
|
| 430 |
+
|
| 431 |
+
# ------------------------------------------------------------------
|
| 432 |
+
# 3) Predict + explain
|
| 433 |
+
# ------------------------------------------------------------------
|
| 434 |
+
predictions = utils.get_xgboost_latest_cancer_type_preds(
|
| 435 |
+
xgb_onconpc, features, cancer_types_to_consider
|
| 436 |
+
)
|
| 437 |
+
|
| 438 |
+
warnings.filterwarnings("ignore")
|
| 439 |
shaps = utils.obtain_shap_values_with_latest_xgboost(xgb_onconpc, features)
|
| 440 |
|
| 441 |
+
# Manual sample id convention: index 0
|
| 442 |
query_ids = [0]
|
| 443 |
+
results = utils.get_onconpc_prediction_explanations(
|
| 444 |
+
query_ids,
|
| 445 |
+
predictions,
|
| 446 |
+
shaps,
|
| 447 |
+
features,
|
| 448 |
+
cancer_types_to_consider,
|
| 449 |
+
save_plot=True,
|
| 450 |
+
)
|
| 451 |
|
| 452 |
+
# ------------------------------------------------------------------
|
| 453 |
+
# 4) Store per-session state used by update_image()
|
| 454 |
+
# ------------------------------------------------------------------
|
| 455 |
+
state = {"features": features, "predictions": predictions, "sample_id": 0}
|
| 456 |
+
|
| 457 |
+
# ------------------------------------------------------------------
|
| 458 |
+
# 5) Return UI outputs + state
|
| 459 |
+
# ------------------------------------------------------------------
|
| 460 |
+
return (
|
| 461 |
+
get_top3(predictions, 0),
|
| 462 |
+
gr.Markdown(markdown_text, elem_classes="markdown-box"),
|
| 463 |
+
results[0]["explanation_plot"],
|
| 464 |
+
state,
|
| 465 |
+
)
|
| 466 |
|
| 467 |
def get_top3(predictions, tumor_sample_id):
|
| 468 |
"""
|
|
|
|
| 520 |
sample_ids = df['SAMPLE_ID'].unique().tolist()
|
| 521 |
return gr.Dropdown(choices=sample_ids)
|
| 522 |
|
| 523 |
+
def update_image(target, state):
|
| 524 |
+
"""
|
| 525 |
+
Regenerate the explanation plot for a different target cancer type using cached state.
|
|
|
|
|
|
|
|
|
|
| 526 |
|
| 527 |
+
Args:
|
| 528 |
+
target (str): Cancer type selected from dropdown; must be in `cancer_types_to_consider`.
|
| 529 |
+
state (dict | None): Per-session state produced by get_preds()/get_preds_min_info().
|
| 530 |
+
|
| 531 |
+
Returns:
|
| 532 |
+
str: Filesystem path to the newly generated explanation plot image for (sample_id, target).
|
| 533 |
+
"""
|
| 534 |
+
# ------------------------------------------------------------------
|
| 535 |
+
# 0) Validate state
|
| 536 |
+
# ------------------------------------------------------------------
|
| 537 |
+
if state is None or state.get("features") is None or state.get("predictions") is None:
|
| 538 |
+
raise gr.Error("Please click Submit first.")
|
| 539 |
+
|
| 540 |
+
features = state["features"]
|
| 541 |
+
predictions = state["predictions"]
|
| 542 |
+
sample_id = state.get("sample_id")
|
| 543 |
+
|
| 544 |
+
if sample_id is None:
|
| 545 |
+
raise gr.Error("Please click Submit first.")
|
| 546 |
+
|
| 547 |
+
if target not in cancer_types_to_consider:
|
| 548 |
+
raise gr.Error(f"Unknown target cancer type: {target}")
|
| 549 |
+
|
| 550 |
+
# ------------------------------------------------------------------
|
| 551 |
+
# 1) Compute SHAP for only the selected sample (fast)
|
| 552 |
+
# ------------------------------------------------------------------
|
| 553 |
+
features_one = features.loc[[sample_id]]
|
| 554 |
+
shaps_cup = utils.obtain_shap_values_with_latest_xgboost(xgb_onconpc, features_one)
|
| 555 |
+
|
| 556 |
+
# In multiclass setting, SHAP is typically indexed by class position
|
| 557 |
+
target_idx = cancer_types_to_consider.index(target)
|
| 558 |
+
|
| 559 |
+
# ------------------------------------------------------------------
|
| 560 |
+
# 2) Build per-feature SHAP vector for this sample and target
|
| 561 |
+
# ------------------------------------------------------------------
|
| 562 |
+
shap_pred_cancer_df = pd.DataFrame(
|
| 563 |
+
shaps_cup[target_idx], # shape ~ (1, n_features) for this single sample
|
| 564 |
+
index=features_one.index, # [sample_id]
|
| 565 |
+
columns=features_one.columns, # feature names
|
| 566 |
+
)
|
| 567 |
shap_pred_sample_df = shap_pred_cancer_df.loc[sample_id]
|
| 568 |
+
feature_sample_df = features_one.loc[sample_id]
|
| 569 |
+
|
| 570 |
+
# Predicted probability for selected target class
|
| 571 |
probability = predictions.loc[sample_id][target]
|
| 572 |
+
|
| 573 |
+
# ------------------------------------------------------------------
|
| 574 |
+
# 3) Generate and save plot
|
| 575 |
+
# ------------------------------------------------------------------
|
| 576 |
+
sample_info = f"Prediction: {target}\nPrediction probability: {probability:.3f}"
|
| 577 |
+
|
| 578 |
+
# Partition features into human-friendly groups for the plot legend
|
| 579 |
+
feature_group_to_features_dict, feature_to_feature_group_dict = utils.partition_feature_names_by_group(
|
| 580 |
+
features_one.columns
|
| 581 |
+
)
|
| 582 |
+
|
| 583 |
+
explanation_plot = utils.get_individual_pred_interpretation(
|
| 584 |
+
shap_pred_sample_df,
|
| 585 |
+
feature_sample_df,
|
| 586 |
+
feature_group_to_features_dict,
|
| 587 |
+
feature_to_feature_group_dict,
|
| 588 |
+
sample_info=sample_info,
|
| 589 |
+
filename=f"{sample_id}_{target}_plot",
|
| 590 |
+
filepath="./others_prediction_explanation",
|
| 591 |
+
save_plot=True,
|
| 592 |
+
)
|
| 593 |
+
|
| 594 |
return explanation_plot
|
| 595 |
|
| 596 |
def show_row(value):
|
|
|
|
| 624 |
|
| 625 |
def launch_gradio(server_name, server_port):
|
| 626 |
"""
|
| 627 |
+
Create and launch the Gradio UI, wiring callbacks with per-session `gr.State`
|
| 628 |
+
so interpretation dropdown changes work without recomputing or relying on deleted temp files.
|
| 629 |
|
| 630 |
Args:
|
| 631 |
+
server_name (str): Server interface to bind (e.g., "0.0.0.0" on Spaces).
|
| 632 |
+
server_port (int): Port number to bind.
|
| 633 |
|
| 634 |
+
Returns:
|
| 635 |
+
None
|
| 636 |
"""
|
| 637 |
+
manual_input_description = (
|
| 638 |
+
"In this option, you will manually enter patient and tumor data including age at sequencing, sex, "
|
| 639 |
+
"copy number alterations (CNA) events, and somatic mutations."
|
| 640 |
+
)
|
| 641 |
+
|
| 642 |
+
csv_description = (
|
| 643 |
+
"In this option, you can directly upload relevant CSV files, including clinical patient, clinical sample, "
|
| 644 |
+
"mutations, and CNA data from [cBioPortal](https://www.cbioportal.org) or "
|
| 645 |
+
"[AACR GENIE](https://www.aacr.org/professionals/research/aacr-project-genie/). "
|
| 646 |
+
"Please see the example data in this [link](https://github.com/itmoon7/onconpc/tree/main/data/mock_n_3_data) <br> "
|
| 647 |
+
"Note that column names `Tumor_Sample_Barcode` and `SAMPLE_ID` both refer to the sample identifier column and should be the same."
|
| 648 |
+
)
|
| 649 |
+
|
| 650 |
+
with gr.Blocks(
|
| 651 |
+
css=(
|
| 652 |
+
".markdown-box { border: 1px solid #E0E0E0; border-radius: 8px; "
|
| 653 |
+
"box-shadow: 0 2px 4px rgba(0, 0, 0, 0.05); padding: 15px; margin-bottom: 20px; }"
|
| 654 |
+
)
|
| 655 |
+
) as demo:
|
| 656 |
+
|
| 657 |
+
# Main selector: choose input mode
|
| 658 |
+
d = gr.Dropdown(
|
| 659 |
+
label="Select your preferred input method for tumor data to visualize predictions made by OncoNPC",
|
| 660 |
+
choices=["Manual Inputs", "CSV File"],
|
| 661 |
+
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 662 |
|
| 663 |
+
# Helper text rows (toggled with the same dropdown)
|
| 664 |
with gr.Row(visible=False) as r3:
|
| 665 |
+
gr.Markdown(csv_description, elem_classes="markdown-box")
|
| 666 |
with gr.Row(visible=False) as r4:
|
| 667 |
+
gr.Markdown(manual_input_description, elem_classes="markdown-box")
|
| 668 |
|
| 669 |
+
# ------------------------------------------------------------------
|
| 670 |
+
# CSV MODE UI (files + sample dropdown)
|
| 671 |
+
# ------------------------------------------------------------------
|
| 672 |
with gr.Row(visible=False) as r1:
|
| 673 |
+
# Per-session cached state for CSV mode.
|
| 674 |
+
# This is what makes dropdown plot changes possible without recomputing.
|
| 675 |
+
state_csv = gr.State(value=None)
|
| 676 |
+
|
| 677 |
with gr.Column():
|
| 678 |
+
gr.Markdown("**Clinical Patient Data File:** Required columns: `PATIENT_ID`, `SEX`.")
|
| 679 |
patients_file = gr.File(label="Upload clinical patients data")
|
| 680 |
+
|
| 681 |
+
gr.Markdown("**Clinical Sample Data File:** Required columns: `PATIENT_ID`, `AGE_AT_SEQ_REPORT`, `SAMPLE_ID`.")
|
| 682 |
samples_file = gr.File(label="Upload clinical samples data")
|
| 683 |
+
|
| 684 |
+
gr.Markdown(
|
| 685 |
+
"**Mutations Data File:** Required columns: `Tumor_Sample_Barcode`, `Hugo_Symbol`, `Chromosome`, "
|
| 686 |
+
"`Start_Position`, `Reference_Allele`, `Tumor_Seq_Allele2`."
|
| 687 |
+
)
|
| 688 |
mutations_file = gr.File(label="Upload mutations data")
|
| 689 |
+
|
| 690 |
+
gr.Markdown("**CNA Data File:** Required column: `Hugo_Symbol`.")
|
| 691 |
cna_file = gr.File(label="Upload CNA data")
|
| 692 |
+
|
| 693 |
+
# Sample ID dropdown is populated dynamically when samples_file changes
|
| 694 |
+
tumor_sample_id = gr.Dropdown(choices=[], label="Tumor Sample ID")
|
| 695 |
+
|
| 696 |
+
submit_button_csv = gr.Button("Submit")
|
| 697 |
|
| 698 |
with gr.Column():
|
| 699 |
predictions_output = gr.Textbox(label="Top 3 Predicted Cancer Types")
|
| 700 |
+
category_explanation = gr.Markdown(markdown_text, elem_classes="markdown-box")
|
| 701 |
+
|
| 702 |
+
image = gr.Image(label="Image Display")
|
| 703 |
+
|
| 704 |
+
# User selects alternate target cancer type for interpretation plot
|
| 705 |
+
output_selector = gr.Dropdown(
|
| 706 |
+
choices=cancer_types_to_consider,
|
| 707 |
+
label="Output Options",
|
| 708 |
+
filterable=True,
|
| 709 |
+
)
|
| 710 |
|
| 711 |
+
gr.Markdown(
|
| 712 |
+
"For more details regarding OncoNPC feature processing, OncoNPC performance, and clinical implications of OncoNPC predictions, "
|
| 713 |
+
"please see our [manuscript](https://www.nature.com/articles/s41591-023-02482-6).",
|
| 714 |
+
elem_classes="markdown-box",
|
| 715 |
+
)
|
| 716 |
+
|
| 717 |
+
# When samples file changes, parse IDs and populate tumor_sample_id dropdown
|
| 718 |
samples_file.change(extract_sample_ids, inputs=samples_file, outputs=tumor_sample_id)
|
|
|
|
|
|
|
| 719 |
|
| 720 |
+
# If any upstream input changes, invalidate cached state (forces recompute on next submit)
|
| 721 |
+
patients_file.change(_reset_state, inputs=patients_file, outputs=state_csv)
|
| 722 |
+
samples_file.change(_reset_state, inputs=samples_file, outputs=state_csv)
|
| 723 |
+
mutations_file.change(_reset_state, inputs=mutations_file, outputs=state_csv)
|
| 724 |
+
cna_file.change(_reset_state, inputs=cna_file, outputs=state_csv)
|
| 725 |
+
|
| 726 |
+
# Submit: computes features/preds (or reuses cached), generates default plot for selected tumor_id,
|
| 727 |
+
# and returns updated state_csv for later dropdown interactions.
|
| 728 |
+
submit_button_csv.click(
|
| 729 |
+
get_preds,
|
| 730 |
+
inputs=[patients_file, samples_file, mutations_file, cna_file, tumor_sample_id, state_csv],
|
| 731 |
+
outputs=[predictions_output, category_explanation, image, state_csv],
|
| 732 |
+
)
|
| 733 |
+
|
| 734 |
+
# Dropdown: regenerates plot using cached state only (no file reads)
|
| 735 |
+
output_selector.change(
|
| 736 |
+
update_image,
|
| 737 |
+
inputs=[output_selector, state_csv],
|
| 738 |
+
outputs=[image],
|
| 739 |
+
)
|
| 740 |
+
|
| 741 |
+
# ------------------------------------------------------------------
|
| 742 |
+
# MANUAL MODE UI (text inputs)
|
| 743 |
+
# ------------------------------------------------------------------
|
| 744 |
with gr.Row(visible=False) as r2:
|
| 745 |
+
# Per-session cached state for manual mode (separate from CSV mode).
|
| 746 |
+
state_manual = gr.State(value=None)
|
| 747 |
+
|
| 748 |
with gr.Column():
|
| 749 |
age = gr.Number(label="Age")
|
| 750 |
gender = gr.Radio(choices=["Male", "Female"], label="Sex")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 751 |
|
| 752 |
+
cna_events = gr.Textbox(
|
| 753 |
+
lines=7,
|
| 754 |
+
placeholder="Copy Number Alterations\n\nExample: RAF1 2 | PPARG 2",
|
| 755 |
+
label="Genes with CNA Events",
|
| 756 |
+
)
|
| 757 |
+
|
| 758 |
+
mutations = gr.Textbox(
|
| 759 |
+
lines=7,
|
| 760 |
+
placeholder=(
|
| 761 |
+
"Somatic Mutations\n\nExample: ERBB2, chr17, 37868208, C, T | "
|
| 762 |
+
"CDKN1A, chr6, 36651880, -, GTCAGAACCGGCTGGGGATGTCC"
|
| 763 |
+
),
|
| 764 |
+
label="Mutations",
|
| 765 |
+
)
|
| 766 |
+
|
| 767 |
+
submit_button_manual = gr.Button("Submit")
|
| 768 |
|
| 769 |
+
with gr.Column():
|
| 770 |
+
predictions_output_m = gr.Textbox(label="Top 3 Predicted Cancer Types")
|
| 771 |
+
category_explanation_m = gr.Markdown(markdown_text, elem_classes="markdown-box")
|
| 772 |
+
|
| 773 |
+
image_m = gr.Image(label="Image Display")
|
| 774 |
+
|
| 775 |
+
output_selector_m = gr.Dropdown(
|
| 776 |
+
choices=cancer_types_to_consider,
|
| 777 |
+
label="Output Options",
|
| 778 |
+
filterable=True,
|
| 779 |
+
)
|
| 780 |
+
|
| 781 |
+
gr.Markdown(
|
| 782 |
+
"For more details regarding OncoNPC feature processing, OncoNPC performance, and clinical implications of OncoNPC predictions, "
|
| 783 |
+
"please see our [manuscript](https://www.nature.com/articles/s41591-023-02482-6).",
|
| 784 |
+
elem_classes="markdown-box",
|
| 785 |
+
)
|
| 786 |
+
|
| 787 |
+
# Manual submit: compute features/preds for a single sample (id 0) and store in state_manual
|
| 788 |
+
submit_button_manual.click(
|
| 789 |
+
get_preds_min_info,
|
| 790 |
+
inputs=[age, gender, cna_events, mutations, state_manual],
|
| 791 |
+
outputs=[predictions_output_m, category_explanation_m, image_m, state_manual],
|
| 792 |
+
)
|
| 793 |
+
|
| 794 |
+
# Manual dropdown: regenerate plot using manual cached state
|
| 795 |
+
output_selector_m.change(
|
| 796 |
+
update_image,
|
| 797 |
+
inputs=[output_selector_m, state_manual],
|
| 798 |
+
outputs=[image_m],
|
| 799 |
+
)
|
| 800 |
+
|
| 801 |
+
# ------------------------------------------------------------------
|
| 802 |
+
# Toggle which UI rows are visible based on input mode dropdown
|
| 803 |
+
# ------------------------------------------------------------------
|
| 804 |
d.change(show_row, d, [r1, r2])
|
| 805 |
d.change(show_row, d, [r3, r4])
|
| 806 |
+
|
| 807 |
+
# Launch Gradio app
|
| 808 |
+
demo.launch(debug=True, share=False, server_name=server_name, server_port=server_port)
|