rahafahmad89 commited on
Commit
0fd39cf
·
verified ·
1 Parent(s): fc0a86e

Create app.py

Browse files
Files changed (1) hide show
  1. app.py +233 -0
app.py ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # --- bootstrap: force-install deps if Hugging Face didn't ---
2
+ #import sys, subprocess
3
+ #def _need(modname):
4
+ # try: __import__(modname); return False
5
+ # except ImportError: return True
6
+ #def _pip(pkg_spec):
7
+ # subprocess.check_call([sys.executable, "-m", "pip", "install", pkg_spec])
8
+
9
+ #PKGS = [
10
+ # ("joblib", "1.4.2", "joblib"),
11
+ # ("numpy", "1.26.4","numpy"),
12
+ # ("pandas", "2.2.2", "pandas"),
13
+ # ("scikit-learn", "1.4.2", "sklearn"),
14
+ # ("scipy", "1.11.4","scipy"),
15
+ # ("shap", "0.46.0","shap"),
16
+ # ("matplotlib", "3.8.4", "matplotlib"),
17
+ # ("openpyxl", "3.1.5", "openpyxl"),
18
+ # ("pillow", None, "PIL"),
19
+ # ("gradio", "4.44.1","gradio"),
20
+ #]
21
+ #for pkg, ver, mod in PKGS:
22
+ # if _need(mod):
23
+ # _pip(f"{pkg}=={ver}" if ver else pkg)
24
+ # now safe to import everything
25
+ import os, json, io, gzip, joblib, traceback
26
+ import numpy as np, pandas as pd
27
+ import matplotlib; matplotlib.use("Agg")
28
+ import matplotlib.pyplot as plt
29
+ from PIL import Image
30
+ import shap
31
+ import gradio as gr
32
+
33
+ # ---- artifacts in repo root ----
34
+ MODEL_PATH = "model_extratrees_ds4.joblib" # or "model_extratrees_ds4.gz"
35
+ FEATS_PATH = "feature_names.json"
36
+
37
+ # if you uploaded a .gz model, uncomment these two lines and delete the next joblib.load:
38
+ # with gzip.open(MODEL_PATH, "rb") as f:
39
+ # model = joblib.load(f)
40
+ model = joblib.load(MODEL_PATH)
41
+
42
+ with open(FEATS_PATH) as f:
43
+ FEATURES = json.load(f)
44
+
45
+ LABEL_NAME = {0: "Benign", 1: "Pathogenic"}
46
+ THRESHOLD = 0.7
47
+ # accept many spellings, case-insensitive
48
+ ID_CANDIDATES = [
49
+ "#Uploaded_Variation", "#Uploaded_variation", "uploaded_variation",
50
+ "Uploaded_Variation", "Uploaded_variation", "variant_id",
51
+ "Variant_ID", "variation_id", "Variant", "ID", "HGVSc", "HGVSp"
52
+ ]
53
+
54
+ # ---------- helpers ----------
55
+ def _clean_headers(df):
56
+ df.columns = (df.columns.astype(str)
57
+ .str.replace(r'[\u200b\ufeff]', '', regex=True)
58
+ .str.strip())
59
+ return df
60
+
61
+ def _read_table(file):
62
+ name = getattr(file, "name", str(file))
63
+ if name.lower().endswith((".xlsx", ".xls")):
64
+ df = pd.read_excel(name, engine="openpyxl")
65
+ else:
66
+ # NOTE: pandas python engine does not support low_memory
67
+ try:
68
+ df = pd.read_csv(
69
+ name,
70
+ engine="python",
71
+ sep=None, # sniff delimiter
72
+ dtype=str,
73
+ na_values=["", "NA", "N/A"],
74
+ quoting=3,
75
+ on_bad_lines="skip",
76
+ encoding_errors="ignore",
77
+ )
78
+ except Exception:
79
+ df = None
80
+ for sep in [",", "\t", ";", "|"]:
81
+ try:
82
+ df = pd.read_csv(
83
+ name,
84
+ engine="python",
85
+ sep=sep,
86
+ dtype=str,
87
+ na_values=["", "NA", "N/A"],
88
+ quoting=3,
89
+ on_bad_lines="skip",
90
+ encoding_errors="ignore",
91
+ )
92
+ break
93
+ except Exception:
94
+ pass
95
+ if df is None:
96
+ raise
97
+ return _clean_headers(df)
98
+
99
+
100
+ def _coerce_numeric(df):
101
+ for c in df.columns:
102
+ if df[c].dtype.kind in "OUS":
103
+ df[c] = pd.to_numeric(df[c], errors="coerce")
104
+ return df
105
+
106
+ def _prepare(df):
107
+ for c in FEATURES:
108
+ if c not in df.columns:
109
+ df[c] = np.nan
110
+ return _coerce_numeric(df[FEATURES].copy())
111
+
112
+ def _validate_columns(df):
113
+ missing = [c for c in FEATURES if c not in df.columns]
114
+ extra = [c for c in df.columns if c not in FEATURES]
115
+ return missing, extra
116
+
117
+ def _pick_id_series(df):
118
+ # case-insensitive lookup without altering original headers
119
+ norm = {c.lower(): c for c in df.columns}
120
+ for cand in ID_CANDIDATES:
121
+ key = cand.lower()
122
+ if key in norm:
123
+ col = norm[key]
124
+ return df[col].astype(str), col
125
+ # fallback
126
+ return pd.Series(df.index, index=df.index, name="row_index"), "row_index"
127
+
128
+ # ---------- app fns ----------
129
+ def predict_csv(file):
130
+ try:
131
+ if file is None: return None, "No file."
132
+ df = _read_table(file)
133
+ missing, _ = _validate_columns(df)
134
+ if missing: return None, f"Missing {len(missing)} feature(s). First 10: {missing[:10]}"
135
+ X = _prepare(df)
136
+
137
+ proba = model.predict_proba(X)[:, 1]
138
+ pred = (proba > THRESHOLD).astype(int)
139
+
140
+ id_series, id_name = _pick_id_series(df)
141
+ id_label = "Variant ID" if id_name != "row_index" else "Variant ID (#Uploaded_variation not found)"
142
+
143
+ out = pd.DataFrame({
144
+ id_label: id_series.values,
145
+ "Predicted probability (pathogenic)": proba,
146
+ "Predicted class": np.where(pred == 1, LABEL_NAME[1], LABEL_NAME[0]),
147
+ })
148
+
149
+ n = len(out)
150
+ n_path = int((out["Predicted class"] == "Pathogenic").sum())
151
+ n_ben = n - n_path
152
+ txt = (
153
+ f"Processed {n} records at threshold {THRESHOLD:.2f}. "
154
+ f"Pathogenic: {n_path} ({(n_path/n*100):.1f}%). "
155
+ f"Benign: {n_ben} ({(n_ben/n*100):.1f}%). "
156
+ "Model probabilities are supportive only; clinical reporting must follow ACMG/AMP."
157
+ )
158
+ return out, txt
159
+ except Exception:
160
+ return None, "ERROR:\n" + traceback.format_exc()
161
+
162
+ def explain_first_row(file):
163
+ try:
164
+ if file is None: return None, "No file."
165
+ df = _read_table(file)
166
+ missing, _ = _validate_columns(df)
167
+ if missing: return None, f"Missing features for SHAP. First 10: {missing[:10]}"
168
+ X = _prepare(df)
169
+ if X.shape[0] == 0: return None, "No rows."
170
+
171
+ X_imp = pd.DataFrame(model.named_steps["imputer"].transform(X), columns=FEATURES)
172
+ clf = model.named_steps["clf"]
173
+
174
+ bg = X_imp.sample(min(200, len(X_imp)), random_state=0)
175
+ expl = shap.Explainer(clf.predict_proba, bg, feature_names=FEATURES, algorithm="permutation")
176
+ ex = expl(X_imp.iloc[[0]])
177
+ vals = np.array(ex.values)
178
+ vals_1d = vals[0, :, 1] if vals.ndim == 3 else vals[0]
179
+ s = pd.Series(vals_1d, index=FEATURES).sort_values(key=np.abs, ascending=False).head(15)
180
+
181
+ fig = plt.figure(figsize=(7,5))
182
+ ax = fig.add_subplot(111)
183
+ s.iloc[::-1].plot(kind="barh", ax=ax, color="#d63384")
184
+ ax.set_title("SHAP values (Sample #1)")
185
+ fig.tight_layout()
186
+
187
+ # clinical note: map top features to ACMG evidence “families”
188
+ feats = [f.lower() for f in s.index.tolist()]
189
+ acmg_tags = []
190
+ if any("af" in f or "gnomad" in f or "freq" in f for f in feats):
191
+ acmg_tags.append("Population frequency → BA1/BS1 (benign thresholds) context")
192
+ if any("score" in f or "rankscore" in f or "meta" in f or "deleterious" in f for f in feats):
193
+ acmg_tags.append("Computational evidence → PP3 (supporting pathogenic) or BP4 (supporting benign)")
194
+ if any("domain" in f or "hotspot" in f or "pfam" in f for f in feats):
195
+ acmg_tags.append("Protein domain/hotspot → PM1 (moderate) if curated hotspot")
196
+ if any("blosum" in f or "aminoacid" in f or "aa" in f for f in feats):
197
+ acmg_tags.append("Same-residue considerations → PM5 possible with prior pathogenic missense")
198
+
199
+ tag_txt = " | ".join(acmg_tags) if acmg_tags else "Top features map to PP3/BP4 computational evidence."
200
+ note = (
201
+ "Clinical note for row #1: positive bars increase pathogenic probability; negative decrease it. "
202
+ f"ACMG relevance: {tag_txt}. "
203
+ "These signals are supportive only; final classification requires full ACMG/AMP evaluation with thresholds and curated evidence."
204
+ )
205
+ return fig, note
206
+ except Exception:
207
+ return None, "ERROR:\n" + traceback.format_exc()
208
+
209
+ # ---------- UI ----------
210
+ with gr.Blocks(title="Pathogenicity Predictor") as demo:
211
+ gr.HTML("""
212
+ <h1 style='text-align:center; color:#d63384; font-size:28px; margin-top:10px;'>
213
+ Pathogenicity Predictor
214
+ </h1>
215
+ """)
216
+
217
+
218
+
219
+
220
+ inp = gr.File(label="Upload CSV/XLSX containing the trained feature columns")
221
+ with gr.Row():
222
+ btn_pred = gr.Button("Predict")
223
+ btn_expl = gr.Button("Explain Sample #1")
224
+ out_df = gr.Dataframe(label="Predictions")
225
+ out_plot = gr.Plot(label="SHAP (Sample #1)")
226
+ out_txt = gr.Markdown()
227
+ btn_pred.click(fn=predict_csv, inputs=inp, outputs=[out_df, out_txt])
228
+ btn_expl.click(fn=explain_first_row, inputs=inp, outputs=[out_plot, out_txt])
229
+
230
+ if __name__ == "__main__":
231
+ port_env = os.environ.get("GRADIO_SERVER_PORT", "")
232
+ port = int(port_env) if port_env.isdigit() else None
233
+ demo.launch(server_name="0.0.0.0", server_port=port, share=False, debug=True)