Update app.py

app.py

@@ -7,15 +7,18 @@ import pandas as pd
 import numpy as np
 from rdkit import Chem
 from rdkit.Chem import AllChem, Draw, MACCSkeys, Descriptors
-from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
-from sklearn.model_selection import cross_val_score
+from rdkit.Chem import PandasTools
+from rdkit.Chem import rdMolDescriptors
 from sklearn.decomposition import PCA
-from sklearn.cluster import KMeans
+from sklearn.manifold import TSNE
+from umap import UMAP
+from sklearn.cluster import KMeans, DBSCAN
 import matplotlib.pyplot as plt
 import seaborn as sns
 import io
 from PIL import Image
 import chardet
+from ydata_profiling import ProfileReport
 
 # =========== 功能1: 分子資料導入/轉換 ===========
 def robust_read_csv(file):
@@ -48,6 +51,121 @@ def mol_img(smiles, size=(160,160)):
         return Image.new("RGB", size, (250,250,250))
     return Draw.MolToImage(mol, size=size)
 
+### 支援多格式匯入
+def load_table(file):
+    if file is None: return pd.DataFrame()
+    if hasattr(file, "name") and file.name.endswith(('.xls', '.xlsx')):
+        return pd.read_excel(file, engine="openpyxl")
+    elif hasattr(file, "name") and file.name.endswith('.sdf'):
+        # 用 PandasTools 支援 SDF
+        return PandasTools.LoadSDF(file.name)
+    else:
+        # CSV with encoding detect
+        pos = file.tell() if hasattr(file, "tell") else 0
+        raw = file.read(4096)
+        enc = chardet.detect(raw)["encoding"] or "utf-8"
+        file.seek(pos)
+        return pd.read_csv(file, encoding=enc)
+
+def smiles_to_mol(smiles):
+    try:
+        return Chem.MolFromSmiles(smiles)
+    except:
+        return None
+
+### 批量分子圖
+def batch_mol_imgs(smiles_list):
+    imgs = []
+    for smi in smiles_list:
+        imgs.append(mol_img(smi))
+    # 拼圖
+    n = len(imgs)
+    grid = Draw.MolsToGridImage([smiles_to_mol(s) for s in smiles_list[:25] if smiles_to_mol(s)],
+                                molsPerRow=5, subImgSize=(160, 160))
+    buf = io.BytesIO()
+    grid.save(buf, format='PNG')
+    buf.seek(0)
+    return Image.open(buf)
+
+### 特徵、描述子與官能基計數
+def calc_features(df, fp_types, desc_types, func_groups, smarts_dict=None):
+    # ECFP4, MACCS, RDKitFP
+    if 'ecfp4' in fp_types:
+        df['ecfp4'] = df['smiles'].apply(lambda s: np.array(AllChem.GetMorganFingerprintAsBitVect(Chem.MolFromSmiles(s), 2, nBits=2048)) if Chem.MolFromSmiles(s) else np.zeros(2048))
+    if 'maccs' in fp_types:
+        df['maccs'] = df['smiles'].apply(lambda s: np.array(MACCSkeys.GenMACCSKeys(Chem.MolFromSmiles(s))) if Chem.MolFromSmiles(s) else np.zeros(167))
+    if 'rdkitfp' in fp_types:
+        df['rdkitfp'] = df['smiles'].apply(lambda s: np.array(rdMolDescriptors.GetRDKitFingerprintAsBitVect(Chem.MolFromSmiles(s), maxPath=5)) if Chem.MolFromSmiles(s) else np.zeros(2048))
+
+    # 部分描述子
+    for desc in desc_types:
+        try:
+            if hasattr(Descriptors, desc):
+                df[desc] = df['smiles'].apply(lambda s: getattr(Descriptors, desc)(Chem.MolFromSmiles(s)) if Chem.MolFromSmiles(s) else np.nan)
+        except Exception: continue
+
+    # 官能基/SMARTS
+    if smarts_dict is None:
+        smarts_dict = {'NO2': '[N+](=O)[O-]', 'OH': '[OX2H]', 'NH2': '[NX3;H2]'}
+    for name, patt in smarts_dict.items():
+        patt_obj = Chem.MolFromSmarts(patt)
+        df[name+'_count'] = df['smiles'].apply(lambda s: Chem.MolFromSmiles(s).GetSubstructMatches(patt_obj) if Chem.MolFromSmiles(s) and patt_obj else [])
+        df[name+'_count'] = df[name+'_count'].apply(lambda l: len(l) if isinstance(l, (list, tuple)) else 0)
+    return df
+
+
+### 降維/分群/群代表分子
+def apply_dim_red(df, use, method='PCA'):
+    X = np.stack(df[use].to_numpy())
+    if method == 'PCA':
+        pc = PCA(n_components=2).fit_transform(X)
+    elif method == 'UMAP':
+        pc = UMAP(n_components=2, random_state=42).fit_transform(X)
+    elif method == 'tSNE':
+        pc = TSNE(n_components=2, random_state=42).fit_transform(X)
+    else:
+        raise ValueError('Unknown method')
+    return pc
+
+def plot_scatter(pc, labels, title):
+    fig, ax = plt.subplots(figsize=(5,4))
+    scatter = ax.scatter(pc[:,0], pc[:,1], c=labels, cmap='tab10', alpha=0.7)
+    plt.xlabel("Dim1"); plt.ylabel("Dim2"); plt.title(title)
+    plt.colorbar(scatter)
+    buf = io.BytesIO()
+    plt.tight_layout()
+    plt.savefig(buf, format='png')
+    buf.seek(0)
+    plt.close(fig)
+    return Image.open(buf)
+
+def clustering(df, use, method='KMeans', n_clusters=3):
+    X = np.stack(df[use].to_numpy())
+    if method == 'KMeans':
+        labels = KMeans(n_clusters=n_clusters, random_state=42).fit_predict(X)
+    elif method == 'DBSCAN':
+        labels = DBSCAN(eps=3, min_samples=2).fit_predict(X)
+    else:
+        raise ValueError('Unknown clustering')
+    return labels
+
+def cluster_reps(df, cluster_labels, use):
+    reps = []
+    for cl in np.unique(cluster_labels):
+        cluster_df = df[cluster_labels==cl]
+        idx = np.random.choice(cluster_df.index, 1)[0]
+        reps.append(cluster_df.loc[idx]['smiles'])
+    return reps
+
+### EDA報表
+def eda_report(df):
+    profile = ProfileReport(df, title="EDA報告", minimal=True)
+    buf = io.BytesIO()
+    profile.to_file(buf)
+    buf.seek(0)
+    return buf
+
+
 # =========== 功能2: 分子指紋/描述子生成 ===========
 def ecfp4_fp(smiles, nbits=2048):
     mol = Chem.MolFromSmiles(smiles)
@@ -150,78 +268,88 @@ with gr.Blocks(title="Cheminformatics Platform") as demo:
     feat_state = gr.State()
     model_state = gr.State()
 
-    # --- 分子資料導入 ---
+    ## 1. 資料導入與批次結構圖
     with gr.Tab("1️⃣ 資料導入/結構圖"):
-        file = gr.File(label="上傳CSV", file_types=[".csv"])
-        df_preview = gr.Dataframe(label="資料預覽 (前10筆)")
-        smiles_input = gr.Textbox(label="分子SMILES預覽")
-        mol_image = gr.Image(label="分子結構圖")
-
-        def on_upload(f):
-            df = load_csv(f)
-            return df.head(10), df
-
-        file.upload(on_upload, file, [df_preview, data_state])
-        smiles_input.change(lambda s: mol_img(s), smiles_input, mol_image)
-
-    # --- 分子特徵生成 ---
-    with gr.Tab("2️⃣ 特徵計算/描述子"):
-        feat_btn = gr.Button("生成特徵/描述子")
-        feat_preview = gr.Dataframe(label="特徵/描述子預覽 (前5筆)")
-
-        def on_feat(state_df):
-            if state_df is None:
-                return pd.DataFrame(), None
-            feat_df = add_fps_and_desc(state_df.copy())
-            return feat_df.head(5), feat_df
-
-        feat_btn.click(on_feat, data_state, [feat_preview, feat_state])
-
-    # --- 資料探索 ---
-    with gr.Tab("3️⃣ 資料集分析 (EDA)"):
-        desc_type = gr.Dropdown(['MolWt', 'TPSA'], label="選擇描述子", value="MolWt")
-        eda_btn = gr.Button("生成描述子分布圖")
-        eda_plot = gr.Image(label="分布圖")
-        eda_btn.click(lambda d, feat_df: plot_desc_dist(feat_df, d) if feat_df is not None else Image.new("RGB", (400,200), (255,255,255)),
-                      [desc_type, feat_state], eda_plot)
-
-    # --- 分群與PCA ---
-    with gr.Tab("4️⃣ 分群/降維可視化"):
-        pca_btn = gr.Button("PCA 分布圖")
-        pca_plot = gr.Image(label="PCA分佈")
-        nclus = gr.Slider(2, 8, 3, 1, label="分群數")
-        km_btn = gr.Button("KMeans 分群圖")
-        km_plot = gr.Image(label="KMeans分群")
-        pca_btn.click(lambda feat_df: pca_2d(feat_df) if feat_df is not None else Image.new("RGB", (400,200), (255,255,255)), feat_state, pca_plot)
-        km_btn.click(lambda n, feat_df: kmeans_clusters(feat_df, n) if feat_df is not None else Image.new("RGB", (400,200), (255,255,255)),
-                     [nclus, feat_state], km_plot)
-
-    # --- 建模/預測 ---
-    with gr.Tab("5️⃣ 建模/交叉驗證/預測"):
-        train_btn = gr.Button("訓練模型 (RF, 5-fold)")
-        model_status = gr.Markdown("模型狀態")
-        smiles_pred = gr.Textbox(label="預測SMILES")
-        y_pred = gr.Textbox(label="預測值/類別")
-
-        def handle_train(feat_df):
-            if feat_df is None:
-                return "請先進行特徵生成", None
-            model, scores = train_model(feat_df)
-            return f"模型交叉驗證: {np.round(scores,3)}", model
-
-        train_btn.click(handle_train, feat_state, [model_status, model_state])
-
-        def handle_predict(s, model):
-            if model is None:
-                return "請先訓練模型", ""
-            try:
-                pred = predict_single(model, s)
-                return "已預測", str(pred)
-            except Exception as e:
-                return f"預測失敗: {e}", ""
-
-        smiles_pred.change(handle_predict, [smiles_pred, model_state], [model_status, y_pred])
-
-    gr.Markdown("---\n> 建議完整流程：1️⃣資料導入 → 2️⃣特徵生成 → 3️⃣EDA探索 → 4️⃣分群 → 5️⃣建模預測")
+        up = gr.File(label="上傳分子檔 (csv/xlsx/sdf)", file_types=[".csv", ".xlsx", ".sdf"])
+        df_view = gr.Dataframe(label="資料預覽 (前15筆)")
+        mol_grid = gr.Image(label="分子結構圖(前25筆)")
+        up.upload(lambda f: load_table(f).head(15) if f else pd.DataFrame(), up, df_view)
+        up.upload(lambda f: batch_mol_imgs(load_table(f)['smiles'].values[:25]) if f else None, up, mol_grid)
+
+    ## 2. 特徵與官能基
+    with gr.Tab("2️⃣ 特徵/描述子/官能基計算"):
+        fp_types = gr.CheckboxGroup(['ecfp4','maccs','rdkitfp'], label="指紋選擇", value=["ecfp4"])
+        desc_types = gr.CheckboxGroup(['MolWt','TPSA','NumHDonors','NumHAcceptors','LogP'], label="描述子")
+        func_smart = gr.Textbox(label="官能基SMARTS, 逗號分隔 (如 [N+](=O)[O-], [OX2H], [NX3;H2] )")
+        file2 = gr.File(label="再次選擇分子檔")
+        feat_preview = gr.Dataframe(label="特徵/描述子預覽 (前10筆)")
+
+        def calc_all_feats(file, fp, desc, smartbox):
+            df = load_table(file)
+            # smartbox 格式處理
+            smarts_dict = {}
+            if smartbox:
+                items = [i.strip() for i in smartbox.split(",") if i.strip()]
+                for idx, smt in enumerate(items):
+                    smarts_dict[f"custom_{idx}"] = smt
+            df = calc_features(df, fp, desc, smarts_dict if smarts_dict else None)
+            return df.head(10)
+        file2.upload(lambda f: load_table(f).head(10) if f else pd.DataFrame(), file2, feat_preview)
+        gr.Button("特徵計算", variant="primary").click(
+            calc_all_feats, [file2, fp_types, desc_types, func_smart], feat_preview
+        )
+
+    ## 3. 資料探索/EDA
+    with gr.Tab("3️⃣ EDA分析/自動報表"):
+        file3 = gr.File(label="選擇分子檔")
+        col_sel = gr.Dropdown(['MolWt','TPSA','NumHDonors','NumHAcceptors','LogP'], label="描述子欄位")
+        eda_img = gr.Image(label="分布圖")
+        eda_btn = gr.Button("產生描述子分布")
+        eda_sum = gr.File(label="下載EDA報表")
+
+        def eda_plot(file, col):
+            df = load_table(file)
+            if col not in df: return None
+            fig, ax = plt.subplots(figsize=(5,3))
+            sns.histplot(df[col].dropna(), ax=ax, bins=30, kde=True)
+            buf = io.BytesIO()
+            plt.tight_layout()
+            plt.savefig(buf, format='png')
+            buf.seek(0)
+            plt.close(fig)
+            return Image.open(buf)
+        eda_btn.click(eda_plot, [file3, col_sel], eda_img)
+        gr.Button("生成EDA報表", variant="primary").click(
+            lambda f: eda_report(load_table(f)) if f else None, file3, eda_sum
+        )
+
+    ## 4. 降維/分群/群代表分子圖
+    with gr.Tab("4️⃣ 降維/分群/結構探索"):
+        file4 = gr.File(label="分子檔")
+        use_fp = gr.Dropdown(['ecfp4','maccs','rdkitfp'], label="降維用指紋")
+        dr_method = gr.Radio(['PCA','UMAP','tSNE'], label="降維方法", value="PCA")
+        cl_method = gr.Radio(['KMeans','DBSCAN'], label="分群方法", value="KMeans")
+        nclus = gr.Slider(2, 8, 3, 1, label="KMeans分群數")
+        dr_img = gr.Image(label="降維視覺化")
+        rep_imgs = gr.Image(label="群代表分子(自動選取，每群1個)")
+
+        def dimred_and_cluster(file, fp, dr, cl, nclu):
+            df = load_table(file)
+            df = calc_features(df, [fp], [], {})
+            pc = apply_dim_red(df, fp, dr)
+            if cl == 'KMeans':
+                labels = KMeans(n_clusters=int(nclu), random_state=42).fit_predict(pc)
+            else:
+                labels = DBSCAN(eps=3, min_samples=2).fit_predict(pc)
+            plotimg = plot_scatter(pc, labels, f"{dr}-{cl}")
+            # 每群代表分子
+            reps = cluster_reps(df, labels, fp)
+            rep_img = batch_mol_imgs(reps)
+            return plotimg, rep_img
+        gr.Button("降維+分群分析", variant="primary").click(
+            dimred_and_cluster, [file4, use_fp, dr_method, cl_method, nclus], [dr_img, rep_imgs]
+        )
+
+    gr.Markdown("---\n> 完整工作流：1️⃣資料導入 → 2️⃣特徵/描述子/官能基 → 3️⃣EDA分析 → 4️⃣降維/分群/結構探索")
 
 demo.launch(share=True)