chembfn-webui 0.5.0__py3-none-any.whl → 1.0.0__py3-none-any.whl

chembfn_webui/bin/app.py

@@ -10,7 +10,7 @@ from functools import partial
 from typing import Tuple, List, Dict, Union
 
 sys.path.append(str(Path(__file__).parent.parent))
-from rdkit.Chem import Draw, MolFromSmiles
+from rdkit.Chem import Draw, MolFromSmiles  # type: ignore
 from mol2chemfigPy3 import mol2chemfig
 import gradio as gr
 import torch
@@ -18,13 +18,19 @@ from selfies import decoder
 from bayesianflow_for_chem import ChemBFN, MLP, EnsembleChemBFN
 from bayesianflow_for_chem.data import (
     VOCAB_KEYS,
-    AA_VOCAB_KEYS,
+    FASTA_VOCAB_KEYS,
     load_vocab,
     smiles2vec,
-    aa2vec,
+    fasta2vec,
     split_selfies,
 )
-from bayesianflow_for_chem.tool import sample, inpaint, adjust_lora_, quantise_model_
+from bayesianflow_for_chem.tool import (
+    sample,
+    inpaint,
+    optimise,
+    adjust_lora_,
+    quantise_model_,
+)
 from lib.utilities import (
     find_model,
     find_vocab,
@@ -176,11 +182,12 @@ def run(
     temperature: float,
     prompt: str,
     scaffold: str,
+    template: str,
     sar_control: str,
     exclude_token: str,
     quantise: str,
     jited: str,
-) -> Tuple[Union[List, None], List[str], str, str, str]:
+) -> Tuple[Union[List, None], List[str], str, gr.TextArea, str]:
     """
     Run generation or inpainting.
 
@@ -195,6 +202,7 @@ def run(
     :param temperature: sampling temperature while ODE-solver used
     :param prompt: prompt string
     :param scaffold: molecular scaffold
+    :param template: molecular template
     :param sar_control: semi-autoregressive behaviour flags
     :param exclude_token: unwanted tokens
     :param quantise: `"on"` or `"off"`
@@ -210,6 +218,7 @@ def run(
     :type temperature: float
     :type prompt: str
     :type scaffold: str
+    :type template: str
     :type sar_control: str
     :type exclude_token: str
     :type quantise: str
@@ -237,8 +246,8 @@ def run(
         img_fn = lambda x: [Draw.MolToImage(MolFromSmiles(i), (500, 500)) for i in x]
         chemfig_fn = lambda x: [mol2chemfig(i, "-r", inline=True) for i in x]
     if token_name == "FASTA":
-        vocab_keys = AA_VOCAB_KEYS
-        tokeniser = aa2vec
+        vocab_keys = FASTA_VOCAB_KEYS
+        tokeniser = fasta2vec
         trans_fn = lambda x: x
         img_fn = lambda _: None  # senseless to provide dumb 2D images
         chemfig_fn = lambda _: [""]  # senseless to provide very long Chemfig code
@@ -346,11 +355,14 @@ def run(
     if not allowed_tokens:
         allowed_tokens = "all"
     scaffold = scaffold.strip()
-    if not scaffold:
-        mols = sample(
+    template = template.strip()
+    if scaffold:
+        x = [1] + tokeniser(scaffold)
+        x = x + [0 for _ in range(lmax - len(x))]
+        x = torch.tensor([x], dtype=torch.long).repeat(batch_size, 1)
+        mols = inpaint(
             bfn,
-            batch_size,
-            lmax,
+            x,
             step,
             y,
             guidance_strength,
@@ -361,11 +373,13 @@ def run(
         mols = trans_fn(mols)
         imgs = img_fn(mols)
         chemfigs = chemfig_fn(mols)
-    else:
-        x = [1] + tokeniser(scaffold)
+        if template:
+            _message.append(f"Molecular template {template} ignored.")
+    elif template:
+        x = [1] + tokeniser(scaffold) + [2]
         x = x + [0 for _ in range(lmax - len(x))]
         x = torch.tensor([x], dtype=torch.long).repeat(batch_size, 1)
-        mols = inpaint(
+        mols = optimise(
             bfn,
             x,
             step,
@@ -378,6 +392,21 @@ def run(
         mols = trans_fn(mols)
         imgs = img_fn(mols)
         chemfigs = chemfig_fn(mols)
+    else:
+        mols = sample(
+            bfn,
+            batch_size,
+            lmax,
+            step,
+            y,
+            guidance_strength,
+            vocab_keys=vocab_keys,
+            method=_method,
+            allowed_tokens=allowed_tokens,
+        )
+        mols = trans_fn(mols)
+        imgs = img_fn(mols)
+        chemfigs = chemfig_fn(mols)
     n_mol = len(mols)
     with open(cache_dir / "results.csv", "w", encoding="utf-8", newline="") as rf:
         rf.write("\n".join(mols))
@@ -388,7 +417,7 @@ def run(
         imgs,
         mols,
         "\n\n".join(chemfigs),
-        "\n".join(_message),
+        gr.TextArea("\n".join(_message), label="message", lines=len(_message)),
         str(cache_dir / "results.csv"),
     )
 
@@ -437,8 +466,9 @@ with gr.Blocks(title="ChemBFN WebUI") as app:
                     label="prompt", lines=12, html_attributes=HTML_STYLE
                 )
                 scaffold = gr.Textbox(label="scaffold", html_attributes=HTML_STYLE)
+                template = gr.Textbox(label="template", html_attributes=HTML_STYLE)
                 gr.Markdown("")
-                message = gr.TextArea(label="message")
+                message = gr.TextArea(label="message", lines=2)
             with gr.Tab(label="result viewer"):
                 with gr.Tab(label="result"):
                     btn_download = gr.File(label="download", visible=False)
@@ -527,6 +557,7 @@ with gr.Blocks(title="ChemBFN WebUI") as app:
             temperature,
             prompt,
             scaffold,
+            template,
             sar_control,
             exclude_token,
             quantise,
@@ -578,7 +609,12 @@ def main() -> None:
     :return:
     :rtype: None
     """
-    parser = argparse.ArgumentParser()
+    parser = argparse.ArgumentParser(
+        description="A web-based visualisation tool for ChemBFN method.",
+        epilog=f"ChemBFN WebUI {__version__}, developed in Hiroshima University by chemists for chemists. "
+        "Visit https://augus1999.github.io/bayesian-flow-network-for-chemistry/ for more details.",
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+    )
     parser.add_argument(
         "--public", default=False, help="open to public", action="store_true"
     )

chembfn_webui/cache/results.csv

@@ -1 +1 @@
-CCOCC(=O)N1CCC[C@@H](C2CC2)CC1
+CN1CCOCC1c1cccc(C(=O)Nc2ccnn2C(C)C)c1

chembfn_webui/lib/version.py

@@ -4,5 +4,5 @@
 Version info.
 """
 
-__version__ = "0.5.0"
+__version__ = "1.0.0"
 __author__ = "Nianze A. TAO"

{chembfn_webui-0.5.0.dist-info → chembfn_webui-1.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chembfn_webui
-Version: 0.5.0
+Version: 1.0.0
 Summary: WebUI for ChemBFN
 Home-page: https://github.com/Augus1999/ChemBFN-WebUI
 Author: Nianze A. Tao
@@ -20,7 +20,7 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: bayesianflow_for_chem>=1.3.0
+Requires-Dist: bayesianflow_for_chem>=2.2.2
 Requires-Dist: mol2chemfigPy3>=1.5.11
 Requires-Dist: gradio>=5.32.1
 Requires-Dist: torch>=2.7.0
@@ -111,6 +111,13 @@ $ set CHEMBFN_WEBUI_MODEL_DIR={YOUR/MODEL/DIR}
 $ chembfn
 ```
 
+V. use an external directory to hold the model files (Notebook, Google Colab)
+```python
+import os
+os.environ["CHEMBFN_WEBUI_MODEL_DIR"] = "{YOUR/MODEL/DIR}"
+!chembfn --public
+```
+
 ### 4. Write the prompt
 
 * Leave prompt blank for unconditional generation.

{chembfn_webui-0.5.0.dist-info → chembfn_webui-1.0.0.dist-info}/RECORD

@@ -1,16 +1,16 @@
 chembfn_webui/__init__.py,sha256=AXUdd_PrlfVO56losFUP7A8XrqCDPylwRbTpe_WG3Uc,87
-chembfn_webui/bin/app.py,sha256=orp5NVtfaWsCBuRf0zeHF4rbp-pM7tmbADFe2TpiT9E,20327
+chembfn_webui/bin/app.py,sha256=fqIP5O5aojwZmw2-eHBcuFm4YuQBIEuwOMTvDzW7jcA,21632
 chembfn_webui/cache/cache_file_here.txt,sha256=hi60T_q6Cf5WPtXuwe4CqjiWpaUqrczsmGMhKIUL--M,28
-chembfn_webui/cache/results.csv,sha256=Imc71En80Z3q8eRLotoJodjt2a0ANXEnaW9AtixonSE,30
+chembfn_webui/cache/results.csv,sha256=xdSOWM1GGGJEFS1Y4sfCjA-9-66AECEo6El59_yW1hw,37
 chembfn_webui/lib/utilities.py,sha256=ALPw-Evjd9DdsU_RQA6Zp2Gc6XnRR7Y_5fZrqG9azWo,7460
-chembfn_webui/lib/version.py,sha256=xnlttoStlxHbeTjkYt4O4vV6VJJVvJfpLP4B3VtYQG4,138
+chembfn_webui/lib/version.py,sha256=Mbvn1j2C-hWCKICax3XLfU-P0Q3j0oPQ4GQXoDFJ3fs,138
 chembfn_webui/model/base_model/place_base_model_here.txt,sha256=oa8_ILaAlWpTXICVDi-Y46_OahV7wB6Che6gbiEIh-c,39
 chembfn_webui/model/lora/place_lora_folder_here.txt,sha256=YYOo0Cj278DyRcgVrCLa1f2Q-cqgNeMnelaLiA3Fuic,69
 chembfn_webui/model/standalone_model/place_standalone_model_folder_here.txt,sha256=Dp42UscfI0Zp3SnvRv5vOfWiJZnxdY7rG3jo0kf86VM,80
 chembfn_webui/model/vocab/place_vocabulary_file_here.txt,sha256=fLOINvZP2022oE7RsmfDjgyaw2yMi7glmdu_cTwmo88,28
-chembfn_webui-0.5.0.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-chembfn_webui-0.5.0.dist-info/METADATA,sha256=OBP7aik3KBU7k8AnslVBbbn9WkvslWiEe24SkfTyJTI,5710
-chembfn_webui-0.5.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-chembfn_webui-0.5.0.dist-info/entry_points.txt,sha256=fp8WTPybvwpeYKrUhTi456wwZbmCMJXN1TeFGpR1SlY,55
-chembfn_webui-0.5.0.dist-info/top_level.txt,sha256=VdWt3Z7jhbB0pQO_mkRawnU5s75SBT9BV8fGaAIJTDI,14
-chembfn_webui-0.5.0.dist-info/RECORD,,
+chembfn_webui-1.0.0.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+chembfn_webui-1.0.0.dist-info/METADATA,sha256=iRpNEXoJZRG42fMjyHwsmcUJ5jV0MrGgWUMkZrqUb3s,5897
+chembfn_webui-1.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+chembfn_webui-1.0.0.dist-info/entry_points.txt,sha256=fp8WTPybvwpeYKrUhTi456wwZbmCMJXN1TeFGpR1SlY,55
+chembfn_webui-1.0.0.dist-info/top_level.txt,sha256=VdWt3Z7jhbB0pQO_mkRawnU5s75SBT9BV8fGaAIJTDI,14
+chembfn_webui-1.0.0.dist-info/RECORD,,