Duplicate from jannisborn/gt4sd-advanced-manufacturing

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+__pycache__/

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2022 Generative Toolkit 4 Scientific Discovery
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,15 @@
+---
+title: GT4SD - Advanced Manufacturing
+emoji: 💡
+colorFrom: green
+colorTo: blue
+sdk: gradio
+sdk_version: 3.9.1
+app_file: app.py
+pinned: false
+python_version: 3.8.13
+pypi_version: 20.2.4
+duplicated_from: jannisborn/gt4sd-advanced-manufacturing
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,102 @@
+import logging
+import pathlib
+import gradio as gr
+import pandas as pd
+from gt4sd.algorithms.controlled_sampling.advanced_manufacturing import (
+    CatalystGenerator,
+    AdvancedManufacturing,
+)
+from gt4sd.algorithms.registry import ApplicationsRegistry
+
+from utils import draw_grid_generate
+
+logger = logging.getLogger(__name__)
+logger.addHandler(logging.NullHandler())
+
+
+def run_inference(
+    algorithm_version: str,
+    target_binding_energy: float,
+    primer_smiles: str,
+    length: float,
+    number_of_points: int,
+    number_of_steps: int,
+    number_of_samples: int,
+):
+
+    config = CatalystGenerator(
+        algorithm_version=algorithm_version,
+        number_of_points=number_of_points,
+        number_of_steps=number_of_steps,
+        generated_length=length,
+        primer_smiles=primer_smiles,
+    )
+    model = AdvancedManufacturing(config, target=target_binding_energy)
+    samples = list(model.sample(number_of_samples))
+    seeds = [] if primer_smiles == "" else [primer_smiles]
+
+    return draw_grid_generate(samples=samples, n_cols=5, seeds=seeds)
+
+
+if __name__ == "__main__":
+
+    # Preparation (retrieve all available algorithms)
+    all_algos = ApplicationsRegistry.list_available()
+    algos = [
+        x["algorithm_version"]
+        for x in list(
+            filter(lambda x: "AdvancedManufact" in x["algorithm_name"], all_algos)
+        )
+    ]
+
+    # Load metadata
+    metadata_root = pathlib.Path(__file__).parent.joinpath("model_cards")
+
+    examples = pd.read_csv(metadata_root.joinpath("examples.csv"), header=None).fillna(
+        ""
+    )
+    print("Examples: ", examples.values.tolist())
+
+    with open(metadata_root.joinpath("article.md"), "r") as f:
+        article = f.read()
+    with open(metadata_root.joinpath("description.md"), "r") as f:
+        description = f.read()
+
+    demo = gr.Interface(
+        fn=run_inference,
+        title="Advanced Manufacturing",
+        inputs=[
+            gr.Dropdown(
+                algos,
+                label="Algorithm version",
+                value="v0",
+            ),
+            gr.Slider(minimum=1, maximum=100, value=10, label="Target binding energy"),
+            gr.Textbox(
+                label="Primer SMILES",
+                placeholder="FP(F)F.CP(C)c1ccccc1.[Au]",
+                lines=1,
+            ),
+            gr.Slider(
+                minimum=5,
+                maximum=400,
+                value=100,
+                label="Maximal sequence length",
+                step=1,
+            ),
+            gr.Slider(
+                minimum=16, maximum=128, value=32, label="Number of points", step=1
+            ),
+            gr.Slider(
+                minimum=16, maximum=128, value=50, label="Number of steps", step=1
+            ),
+            gr.Slider(
+                minimum=1, maximum=50, value=10, label="Number of samples", step=1
+            ),
+        ],
+        outputs=gr.HTML(label="Output"),
+        article=article,
+        description=description,
+        # examples=examples.values.tolist(),
+    )
+    demo.launch(debug=True, show_error=True)

model_cards/article.md

@@ -0,0 +1,68 @@
+# Model documentation & parameters
+
+**Algorithm Version**: Which model version to use.
+
+**Target binding energy**: The desired binding energy.
+
+**Primer SMILES**: A SMILES string used to prime the generation.
+
+**Maximal sequence length**: The maximal number of SMILES tokens in the generated molecule.
+
+**Number of points**: Number of points to sample with the Gaussian Process.
+
+**Number of steps**: Number of optimization steps in the Gaussian Process optimization.
+
+**Number of samples**: How many samples should be generated (between 1 and 50).
+
+
+
+# Model card -- AdvancedManufacturing
+
+**Model Details**: *AdvancedManufacturing* is a sequence-based molecular generator tuned to generate catalysts. The model relies on a recurrent Variational Autoencoder with a binding-energy predictor trained on the latent code. The framework uses Gaussian Processes for generating targeted molecules.
+
+**Developers**: Oliver Schilter and colleagues from IBM Research.
+
+**Distributors**: Original authors' code integrated into GT4SD.
+
+**Model date**: Not yet published.
+
+**Model version**: Different types of models trained on NCCR data using SMILES or SELFIES, potentially also with augmentation.
+
+**Model type**: A sequence-based molecular generator tuned to generate catalysts. The model relies on a recurrent Variational Autoencoder with a binding-energy predictor trained on the latent code. The framework uses Gaussian Processes for generating targeted molecules.
+
+**Information about training algorithms, parameters, fairness constraints or other applied approaches, and features**: 
+N.A.
+
+**Paper or other resource for more information**: 
+TBD
+
+**License**: MIT
+
+**Where to send questions or comments about the model**: Open an issue on [GT4SD repository](https://github.com/GT4SD/gt4sd-core).
+
+**Intended Use. Use cases that were envisioned during development**: Chemical research, in particular drug discovery.
+
+**Primary intended uses/users**: Researchers and computational chemists using the model for model comparison or research exploration purposes.
+
+**Out-of-scope use cases**: Production-level inference, producing molecules with harmful properties.
+
+**Metrics**: N.A.
+
+**Datasets**: Data provided through NCCR.
+
+**Ethical Considerations**: Unclear, please consult with original authors in case of questions.
+
+**Caveats and Recommendations**: Unclear, please consult with original authors in case of questions.
+
+Model card prototype inspired by [Mitchell et al. (2019)](https://dl.acm.org/doi/abs/10.1145/3287560.3287596?casa_token=XD4eHiE2cRUAAAAA:NL11gMa1hGPOUKTAbtXnbVQBDBbjxwcjGECF_i-WC_3g1aBgU1Hbz_f2b4kI_m1in-w__1ztGeHnwHs)
+
+## Citation
+TBD, temporarily please cite:
+```bib
+@article{manica2022gt4sd,
+  title={GT4SD: Generative Toolkit for Scientific Discovery},
+  author={Manica, Matteo and Cadow, Joris and Christofidellis, Dimitrios and Dave, Ashish and Born, Jannis and Clarke, Dean and Teukam, Yves Gaetan Nana and Hoffman, Samuel C and Buchan, Matthew and Chenthamarakshan, Vijil and others},
+  journal={arXiv preprint arXiv:2207.03928},
+  year={2022}
+}
+```

model_cards/description.md

@@ -0,0 +1,6 @@
+<img align="right" src="https://raw.githubusercontent.com/GT4SD/gt4sd-core/main/docs/_static/gt4sd_logo.png" alt="logo" width="120" >
+
+*AdvancedManufacturing* is a sequence-based molecular generator tuned to generate catalysts. The model relies on a Variational Autoencoder with a binding-energy predictor trained on the latent code. The framework uses Gaussian Processes for generating targeted molecules.
+
+For **examples** and **documentation** of the model parameters, please see below.
+Moreover, we provide a **model card** ([Mitchell et al. (2019)](https://dl.acm.org/doi/abs/10.1145/3287560.3287596?casa_token=XD4eHiE2cRUAAAAA:NL11gMa1hGPOUKTAbtXnbVQBDBbjxwcjGECF_i-WC_3g1aBgU1Hbz_f2b4kI_m1in-w__1ztGeHnwHs)) at the bottom of this page.

model_cards/examples.csv

@@ -0,0 +1,2 @@
+v0,10,,100,10,50,10
+v0,10,FP(F)F.CP(C)c1ccccc1.[Au],100,10,50,10

requirements.txt

@@ -0,0 +1,29 @@
+-f https://download.pytorch.org/whl/cpu/torch_stable.html
+-f https://data.pyg.org/whl/torch-1.12.1+cpu.html
+# pip==20.2.4
+torch==1.12.1
+torch-scatter
+torch-spline-conv
+torch-sparse
+torch-geometric
+torchvision==0.13.1
+torchaudio==0.12.1
+gt4sd>=1.0.5
+molgx>=0.22.0a1
+molecule_generation
+nglview
+PyTDC==0.3.7
+gradio==3.12.0
+markdown-it-py>=2.1.0
+mols2grid>=0.2.0
+numpy==1.23.5
+pandas>=1.0.0
+terminator @ git+https://github.com/IBM/regression-transformer@gt4sd
+guacamol_baselines @ git+https://github.com/GT4SD/guacamol_baselines.git@v0.0.2
+moses @ git+https://github.com/GT4SD/moses.git@v0.1.0
+paccmann_chemistry @ git+https://github.com/PaccMann/paccmann_chemistry@0.0.4
+paccmann_generator @ git+https://github.com/PaccMann/paccmann_generator@0.0.2
+paccmann_gp @ git+https://github.com/PaccMann/paccmann_gp@0.1.1
+paccmann_omics @ git+https://github.com/PaccMann/paccmann_omics@0.0.1.1
+paccmann_predictor @ git+https://github.com/PaccMann/paccmann_predictor@sarscov2
+reinvent_models @ git+https://github.com/GT4SD/reinvent_models@v0.0.1

utils.py

@@ -0,0 +1,48 @@
+import logging
+from collections import defaultdict
+from typing import List
+
+import mols2grid
+import pandas as pd
+
+logger = logging.getLogger(__name__)
+logger.addHandler(logging.NullHandler())
+
+
+def draw_grid_generate(
+    samples: List[str],
+    seeds: List[str] = [],
+    n_cols: int = 3,
+    size=(140, 200),
+) -> str:
+    """
+    Uses mols2grid to draw a HTML grid for the generated molecules
+
+    Args:
+        samples: The generated samples.
+        n_cols: Number of columns in grid. Defaults to 5.
+        size: Size of molecule in grid. Defaults to (140, 200).
+
+    Returns:
+        HTML to display
+    """
+
+    result = defaultdict(list)
+    result.update(
+        {
+            "SMILES": seeds + samples,
+            "Name": [f"Seed_{i}" for i in range(len(seeds))]
+            + [f"Generated_{i}" for i in range(len(samples))],
+        },
+    )
+
+    result_df = pd.DataFrame(result)
+    obj = mols2grid.display(
+        result_df,
+        tooltip=list(result.keys()),
+        height=1100,
+        n_cols=n_cols,
+        name="Results",
+        size=size,
+    )
+    return obj.data