rahafahmad89's picture
Update app.py
03ff7f7 verified
Raw History Blame Contribute Delete
9.54 kB
# --- bootstrap: force-install deps if Hugging Face didn't ---
#import sys, subprocess
#def _need(modname):
# try: __import__(modname); return False
# except ImportError: return True
#def _pip(pkg_spec):
# subprocess.check_call([sys.executable, "-m", "pip", "install", pkg_spec])
#PKGS = [
# ("joblib", "1.4.2", "joblib"),
# ("numpy", "1.26.4","numpy"),
# ("pandas", "2.2.2", "pandas"),
# ("scikit-learn", "1.4.2", "sklearn"),
# ("scipy", "1.11.4","scipy"),
# ("shap", "0.46.0","shap"),
# ("matplotlib", "3.8.4", "matplotlib"),
# ("openpyxl", "3.1.5", "openpyxl"),
# ("pillow", None, "PIL"),
# ("gradio", "4.44.1","gradio"),
#]
#for pkg, ver, mod in PKGS:
# if _need(mod):
# _pip(f"{pkg}=={ver}" if ver else pkg)
# now safe to import everything
import os, json, io, gzip, joblib, traceback
import numpy as np, pandas as pd
import matplotlib; matplotlib.use("Agg")
import matplotlib.pyplot as plt
from PIL import Image
import shap
import gradio as gr
import gradio as gr
# --- PATCH: gradio_client json schema parser fails on boolean schemas ---
try:
import gradio_client.utils as _gcu
# Patch the low-level parser used by json_schema_to_python_type
if hasattr(_gcu, "_json_schema_to_python_type"):
_orig = _gcu._json_schema_to_python_type
def _patched(schema, defs=None):
# JSON Schema allows boolean schemas (True/False). Treat them as "Any".
if isinstance(schema, bool):
return "Any"
return _orig(schema, defs)
_gcu._json_schema_to_python_type = _patched
except Exception:
pass
# ---- artifacts in repo root ----
MODEL_PATH = "model_extratrees_ds4.joblib" # or "model_extratrees_ds4.gz"
FEATS_PATH = "feature_names.json"
# if you uploaded a .gz model, uncomment these two lines and delete the next joblib.load:
# with gzip.open(MODEL_PATH, "rb") as f:
# model = joblib.load(f)
model = joblib.load(MODEL_PATH)
with open(FEATS_PATH) as f:
FEATURES = json.load(f)
LABEL_NAME = {0: "Benign", 1: "Pathogenic"}
THRESHOLD = 0.7
# accept many spellings, case-insensitive
ID_CANDIDATES = [
"#Uploaded_Variation", "#Uploaded_variation", "uploaded_variation",
"Uploaded_Variation", "Uploaded_variation", "variant_id",
"Variant_ID", "variation_id", "Variant", "ID", "HGVSc", "HGVSp"
]
# ---------- helpers ----------
def _clean_headers(df):
df.columns = (df.columns.astype(str)
.str.replace(r'[\u200b\ufeff]', '', regex=True)
.str.strip())
return df
def _read_table(file):
name = getattr(file, "name", str(file))
if name.lower().endswith((".xlsx", ".xls")):
df = pd.read_excel(name, engine="openpyxl")
else:
# NOTE: pandas python engine does not support low_memory
try:
df = pd.read_csv(
name,
engine="python",
sep=None, # sniff delimiter
dtype=str,
na_values=["", "NA", "N/A"],
quoting=3,
on_bad_lines="skip",
encoding_errors="ignore",
)
except Exception:
df = None
for sep in [",", "\t", ";", "|"]:
try:
df = pd.read_csv(
name,
engine="python",
sep=sep,
dtype=str,
na_values=["", "NA", "N/A"],
quoting=3,
on_bad_lines="skip",
encoding_errors="ignore",
)
break
except Exception:
pass
if df is None:
raise
return _clean_headers(df)
def _coerce_numeric(df):
for c in df.columns:
if df[c].dtype.kind in "OUS":
df[c] = pd.to_numeric(df[c], errors="coerce")
return df
def _prepare(df):
for c in FEATURES:
if c not in df.columns:
df[c] = np.nan
return _coerce_numeric(df[FEATURES].copy())
def _validate_columns(df):
missing = [c for c in FEATURES if c not in df.columns]
extra = [c for c in df.columns if c not in FEATURES]
return missing, extra
def _pick_id_series(df):
# case-insensitive lookup without altering original headers
norm = {c.lower(): c for c in df.columns}
for cand in ID_CANDIDATES:
key = cand.lower()
if key in norm:
col = norm[key]
return df[col].astype(str), col
# fallback
return pd.Series(df.index, index=df.index, name="row_index"), "row_index"
# ---------- app fns ----------
def predict_csv(file):
try:
if file is None: return None, "No file."
df = _read_table(file)
missing, _ = _validate_columns(df)
if missing: return None, f"Missing {len(missing)} feature(s). First 10: {missing[:10]}"
X = _prepare(df)
proba = model.predict_proba(X)[:, 1]
pred = (proba > THRESHOLD).astype(int)
id_series, id_name = _pick_id_series(df)
id_label = "Variant ID" if id_name != "row_index" else "Variant ID (#Uploaded_variation not found)"
out = pd.DataFrame({
id_label: id_series.values,
"Predicted probability (pathogenic)": proba,
"Predicted class": np.where(pred == 1, LABEL_NAME[1], LABEL_NAME[0]),
})
n = len(out)
n_path = int((out["Predicted class"] == "Pathogenic").sum())
n_ben = n - n_path
txt = (
f"Processed {n} records at threshold {THRESHOLD:.2f}. "
f"Pathogenic: {n_path} ({(n_path/n*100):.1f}%). "
f"Benign: {n_ben} ({(n_ben/n*100):.1f}%). "
"Model probabilities are supportive only; clinical reporting must follow ACMG/AMP."
)
return out, txt
except Exception:
return None, "ERROR:\n" + traceback.format_exc()
def explain_first_row(file):
try:
if file is None: return None, "No file."
df = _read_table(file)
missing, _ = _validate_columns(df)
if missing: return None, f"Missing features for SHAP. First 10: {missing[:10]}"
X = _prepare(df)
if X.shape[0] == 0: return None, "No rows."
X_imp = pd.DataFrame(model.named_steps["imputer"].transform(X), columns=FEATURES)
clf = model.named_steps["clf"]
bg = X_imp.sample(min(200, len(X_imp)), random_state=0)
expl = shap.Explainer(clf.predict_proba, bg, feature_names=FEATURES, algorithm="permutation")
ex = expl(X_imp.iloc[[0]])
vals = np.array(ex.values)
vals_1d = vals[0, :, 1] if vals.ndim == 3 else vals[0]
s = pd.Series(vals_1d, index=FEATURES).sort_values(key=np.abs, ascending=False).head(15)
fig = plt.figure(figsize=(7,5))
ax = fig.add_subplot(111)
s.iloc[::-1].plot(kind="barh", ax=ax, color="#d63384")
ax.set_title("SHAP values (Sample #1)")
fig.tight_layout()
# clinical note: map top features to ACMG evidence “families”
feats = [f.lower() for f in s.index.tolist()]
acmg_tags = []
if any("af" in f or "gnomad" in f or "freq" in f for f in feats):
acmg_tags.append("Population frequency → BA1/BS1 (benign thresholds) context")
if any("score" in f or "rankscore" in f or "meta" in f or "deleterious" in f for f in feats):
acmg_tags.append("Computational evidence → PP3 (supporting pathogenic) or BP4 (supporting benign)")
if any("domain" in f or "hotspot" in f or "pfam" in f for f in feats):
acmg_tags.append("Protein domain/hotspot → PM1 (moderate) if curated hotspot")
if any("blosum" in f or "aminoacid" in f or "aa" in f for f in feats):
acmg_tags.append("Same-residue considerations → PM5 possible with prior pathogenic missense")
tag_txt = " | ".join(acmg_tags) if acmg_tags else "Top features map to PP3/BP4 computational evidence."
note = (
"Clinical note for row #1: positive bars increase pathogenic probability; negative decrease it. "
f"ACMG relevance: {tag_txt}. "
"These signals are supportive only; final classification requires full ACMG/AMP evaluation with thresholds and curated evidence."
)
return fig, note
except Exception:
return None, "ERROR:\n" + traceback.format_exc()
# ---------- UI ----------
with gr.Blocks(title="Pathogenicity Predictor") as demo:
gr.HTML("""
<h1 style='text-align:center; color:#d63384; font-size:28px; margin-top:10px;'>
Pathogenicity Predictor
</h1>
""")
inp = gr.File(label="Upload CSV/XLSX containing the trained feature columns")
with gr.Row():
btn_pred = gr.Button("Predict")
btn_expl = gr.Button("Explain Sample #1")
out_df = gr.Dataframe(label="Predictions")
out_plot = gr.Plot(label="SHAP (Sample #1)")
out_txt = gr.Markdown()
btn_pred.click(fn=predict_csv, inputs=inp, outputs=[out_df, out_txt])
btn_expl.click(fn=explain_first_row, inputs=inp, outputs=[out_plot, out_txt])
if __name__ == "__main__":
port_env = os.environ.get("GRADIO_SERVER_PORT", "") or os.environ.get("PORT", "")
port = int(port_env) if str(port_env).isdigit() else 7860
demo.queue()
demo.launch(server_name="0.0.0.0", server_port=port, share=False, debug=True)