Update app.py

app.py

@@ -10,22 +10,22 @@ import hashlib
 import time
 import threading
 
+# ===== 永久存储路径 =====
+BASE_DIR = "/mount/src/peptide-screening"
+
 # ===== 页面设置 =====
 st.set_page_config(page_title="多肽虚拟筛选工具", layout="wide")
 st.title("多肽虚拟筛选工具")
 
 # ===== 防休眠机制 =====
 def keep_alive():
-    """每隔一段时间在后台执行一次轻量操作，防止应用被云平台冻结"""
     while True:
-        time.sleep(300)  # 每5分钟
+        time.sleep(300)
         try:
-            # 对内存中一个极小的数据进行一次无意义的访问，只是为了表明“我还活着”
             _ = st.session_state.get("_", None)
         except Exception:
             pass
 
-# 启动后台保活线程
 if "alive_thread" not in st.session_state:
     alive_thread = threading.Thread(target=keep_alive, daemon=True)
     alive_thread.start()
@@ -177,11 +177,9 @@ def get_content(src_name):
 st.subheader("开始筛选")
 
 if st.button("开始筛选", type="primary"):
-    # 加载模型
     tok, mod = load_model()
 
-    # 拉取蛋白数据（优先读本地缓存）
-    food_cache_file = "food_cache.pkl"
+    food_cache_file = os.path.join(BASE_DIR, "food_cache.pkl")
     if os.path.exists(food_cache_file):
         with open(food_cache_file, "rb") as f:
             FOOD = pickle.load(f)
@@ -193,13 +191,11 @@ if st.button("开始筛选", type="primary"):
                 pickle.dump(FOOD, f)
         st.success(f"已获取并缓存 {len(FOOD)} 条蛋白序列")
 
-    # 虚拟酶切
     allp = []
     for name, seq in FOOD.items():
         for p in cut(seq, CUT, min_len, max_len):
             allp.append({"src": name, "p": p})
 
-    # 去重（按物种简称 + 肽段序列）
     seen = set()
     unip = []
     for x in allp:
@@ -214,9 +210,8 @@ if st.button("开始筛选", type="primary"):
             unip.append(x)
     st.info(f"酶切并去重后共 {len(unip)} 条候选肽")
 
-    # AI打分（智能缓存）
     cache_key = get_cache_key()
-    score_cache_file = f"score_cache_{cache_key}.pkl"
+    score_cache_file = os.path.join(BASE_DIR, f"score_cache_{cache_key}.pkl")
 
     if os.path.exists(score_cache_file):
         with open(score_cache_file, "rb") as f:
@@ -241,19 +236,15 @@ if st.button("开始筛选", type="primary"):
             pickle.dump(res, f)
         st.success(f"已完成打分并缓存")
 
-    # 含量标注
     for x in res:
         x["content_pct"] = get_content(x["src"])
 
-    # 过滤
     filtered_res = [x for x in res if x["content_pct"] >= content_threshold]
     if filtered_res:
         res = filtered_res
 
-    # 排序
     res.sort(key=lambda x: x["score"], reverse=True)
 
-    # 显示Top结果（限制显示行数，避免内存溢出）
     st.subheader("结构相似度排名")
     df_top = pd.DataFrame(res[:top_n])
     show_cols = ["src", "p", "score"]
@@ -263,7 +254,6 @@ if st.button("开始筛选", type="primary"):
     st.caption(f"显示前 {min(top_n, max_display_rows)} 条结果（共 {top_n} 条）")
     st.dataframe(df_top[show_cols].head(max_display_rows), width='stretch')
 
-    # 下载按钮
     csv_top = df_top.to_csv(index=False).encode("utf-8-sig")
     st.download_button("下载Top结果CSV", csv_top, "out_top.csv", "text/csv")
 
@@ -271,7 +261,6 @@ if st.button("开始筛选", type="primary"):
     csv_all = df_all.to_csv(index=False).encode("utf-8-sig")
     st.download_button("下载全部结果CSV", csv_all, "out_all.csv", "text/csv")
 
-    # 物种统计（全部候选肽）
     st.subheader("物种贡献统计（全部候选肽）")
     species_counts = {}
     for x in res: