Upload 8 files

.dockerignore

@@ -0,0 +1 @@
+**/.git

.gitignore

@@ -0,0 +1,131 @@
+**/__pycache__
+/mhnreact/.ipynb_checkpoints/
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

LICENSE

@@ -0,0 +1,23 @@
+NeurIPS | 2021 License
+
+Copyright (c) 2021, by the authors
+All rights reserved.
+
+Source code is for reviewing purpose only.
+
+Redistribution of the source code is not permitted.
+
+Use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+

README.md

@@ -1,12 +1 @@
----
-title: MHN React
-emoji: 👀
-colorFrom: indigo
-colorTo: red
-sdk: gradio
-sdk_version: 3.4.1
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# mhn-react-app

app.py

@@ -0,0 +1,61 @@
+import gradio as gr
+from mhnreact.inspect import list_models, load_clf
+from rdkit.Chem import rdChemReactions as Reaction
+from rdkit.Chem.Draw import rdMolDraw2D
+from PIL import Image, ImageDraw
+from ssretro_template import ssretro
+
+
+def get_output(p):
+    rxn = Reaction.ReactionFromSmarts(p, useSmiles=False)
+    d = rdMolDraw2D.MolDraw2DCairo(800, 200)
+    d.DrawReaction(rxn, highlightByReactant=False)
+    d.FinishDrawing()
+    text = d.GetDrawingText()
+
+    return text
+
+def ssretro_prediction(molecule):
+
+    model_fn = list_models()[0]
+    retro_clf = load_clf(model_fn)
+
+    outputs = ssretro(molecule, retro_clf)
+    predict, txt = [], []
+    for pred in outputs:
+        txt.append(f'predicted top-{pred["template_rank"]-1}, prob: {pred["prob"]:2.1f}%; {pred["reaction"]}')
+        predict.append(get_output(pred["reaction"]))
+
+    return predict, txt
+
+
+def mhn_react_backend(mol):
+
+    output_dir = "outputs"
+    formatter = "03d"
+    images = []
+
+    predictions, comments = ssretro_prediction(mol)
+
+    for i in range(len(predictions)):
+        output_im = f"{str(output_dir)}/{format(i, formatter)}.png"
+
+        with open(output_im, "wb") as fh:
+            fh.write(predictions[i])
+        fh.close()
+
+        img = Image.open(output_im)
+        I1 = ImageDraw.Draw(img)
+
+        I1.text((20, 10), comments[i], fill=(30, 0, 44))
+
+        images.append(img)
+        img.save(output_im)
+
+    return images
+
+
+demo = gr.Interface(fn=mhn_react_backend, inputs="text", outputs="gallery")
+demo.launch()
+
+

env.yml

@@ -0,0 +1,24 @@
+name: mhnreact_env
+channels:
+  - bioconda
+  - conda-forge
+  - defaults
+dependencies:
+  # change to your cuda version
+  - cudatoolkit=10.2
+  - torch==1.6
+  - torchvision==0.7
+  - pandas=1.0.5
+  - pip=20.1.1=py_1
+  - python=3.7
+  - rdkit=2021.03.1 #2020.03.4
+    # optionally
+  - ipython
+  - jupyterlab
+  - pip:
+    - numpy==1.19
+    - scikit-learn==0.23.1
+    - scipy==1.4
+    - hydra-core
+    - tqdm
+    - rdchiral==1.1.0

requirements.txt

@@ -0,0 +1,16 @@
+numpy~=1.23.2
+pandas~=1.4.4
+scipy~=1.9.1
+joblib~=1.1.0
+sklearn~=0.0
+scikit-learn~=1.1.2
+requests~=2.28.1
+rdchiral~=1.1.0
+setuptools~=60.2.0
+gradio~=3.3.1
+Pillow~=9.2.0
+matplotlib~=3.5.3
+torch~=1.12.1
+wandb~=0.13.2
+tqdm~=4.64.1
+swifter~=1.3.4

ssretro_template.py

@@ -0,0 +1,93 @@
+from rdkit.Chem import AllChem
+from mhnreact.data import load_dataset_from_csv
+from mhnreact.molutils import convert_smiles_to_fp
+from rdchiral.main import rdchiralRun, rdchiralReaction, rdchiralReactants
+import torch
+
+reaction_superclass_names = {
+    1: 'Heteroatom alkylation and arylation',
+    2: 'Acylation and related processes',
+    3: 'C-C bond formation',
+    4: 'Heterocycle formation',  # TODO check
+    5: 'Protections',
+    6: 'Deprotections',
+    7: 'Reductions',
+    8: 'Oxidations',
+    9: 'Functional group interconversoin (FGI)',
+    10: 'Functional group addition (FGA)'
+}
+
+def getTemplateApplicabilityMatrix(t, fp_size=8096, fp_type='pattern'):
+    only_left_side_of_templates = list(map(lambda k: k.split('>>')[0], t.values()))
+    return convert_smiles_to_fp(only_left_side_of_templates, is_smarts=True, which=fp_type, fp_size=fp_size)
+
+
+def FPF(smi, templates, fp_size=8096, fp_type='pattern'):
+    """Fingerprint-Filter for applicability"""
+    tfp = getTemplateApplicabilityMatrix(templates, fp_size=fp_size, fp_type=fp_type)
+    if not isinstance(smi, list):
+        smi = [smi]
+    mfp = convert_smiles_to_fp(smi, which=fp_type, fp_size=fp_size)
+    applicable = ((tfp & mfp).sum(1) == (tfp.sum(1)))
+    return applicable
+
+
+def ssretro(target_smiles: str, clf, num_paths=5, try_max_temp=10, viz=False, use_FPF=False):
+    """single-step-retrosynthesis"""
+    X, y, t, test_reactants_can = load_dataset_from_csv('data/USPTO_50k_MHN_prepro.csv.gz', ssretroeval=True)
+    if hasattr(clf, 'templates'):
+        if clf.X is None:
+            clf.X = clf.template_encoder(clf.templates)
+    preds = clf.forward_smiles([target_smiles])
+
+    if use_FPF:
+        appl = FPF(target_smiles, t)
+        preds = preds * torch.tensor(appl)
+    preds = clf.softmax(preds)
+
+    idxs = preds.argsort().detach().numpy().flatten()[::-1]
+    preds = preds.detach().numpy().flatten()
+
+    try:
+        prod_rct = rdchiralReactants(target_smiles)
+    except:
+        print('target_smiles', target_smiles, 'not computebale')
+        return []
+    reactions = []
+
+    i = 0
+    while len(reactions) < num_paths and (i < try_max_temp):
+        resu = []
+        while (not len(resu)) and (i < try_max_temp):  # continue
+            # print(i, end='  \r')
+            try:
+                rxn = rdchiralReaction(t[idxs[i]])
+                resu = rdchiralRun(rxn, prod_rct, keep_mapnums=True, combine_enantiomers=True, return_mapped=True)
+            except:
+                resu = ['err']
+            i += 1
+
+        if len(resu) == 2:  # if there is a result
+            res, mapped_res = resu
+
+            rs = [AllChem.MolToSmiles(prod_rct.reactants) + '>>' + k[0] for k in list(mapped_res.values())]
+            for r in rs:
+                di = {
+                    # 'template_used': t[idxs[i]],
+                    # 'template_idx': idxs[i],
+                    'template_rank': i + 1,  # get the acutal rank, not the one without non-executable
+                    'reaction': r,
+                    # 'reaction_canonical': canonicalize_template(r),
+                    'prob': preds[idxs[i]] * 100
+                    # 'template_class': reaction_superclass_names[
+                    #   df[df.reaction_smarts == t[idxs[i]]]["class"].unique()[0]]
+                }
+                # di['template_num_train_samples'] = (y['train'] == di['template_idx']).sum()
+                reactions.append(di)
+            if viz:
+                for r in rs:
+                    print('with template #', idxs[i], t[idxs[i]])
+                    # smarts2svg(r, useSmiles=True, highlightByReactant=True);
+
+    return reactions
+