update

README.md

@@ -1,5 +1,5 @@
 ---
-title: GT4SD - MoLeR
+title: GT4SD - Polymer Blocks
 emoji: 💡
 colorFrom: green
 colorTo: blue
@@ -9,7 +9,7 @@ app_file: app.py
 pinned: false
 python_version: 3.8.13
 pypi_version: 20.2.4
-duplicated_from: jannisborn/gt4sd-moler
+duplicated_from: jannisborn/gt4sd-paccmann-gp
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,39 +1,31 @@
 import logging
 import pathlib
-
 import gradio as gr
 import pandas as pd
-from gt4sd.algorithms.generation.moler import MoLeR, MoLeRDefaultGenerator
+from gt4sd.algorithms.generation.polymer_blocks import (
+    PolymerBlocksGenerator,
+    PolymerBlocks,
+)
 
 from gt4sd.algorithms.registry import ApplicationsRegistry
+
 from utils import draw_grid_generate
 
 logger = logging.getLogger(__name__)
 logger.addHandler(logging.NullHandler())
 
-TITLE = "MoLeR"
 
+def run_inference(algorithm_version: str, length: float, number_of_samples: int):
 
-def run_inference(
-    algorithm_version: str,
-    scaffolds: str,
-    beam_size: int,
-    number_of_samples: int,
-    seed: int,
-):
-    config = MoLeRDefaultGenerator(
+    config = PolymerBlocksGenerator(
         algorithm_version=algorithm_version,
-        scaffolds=scaffolds,
-        beam_size=beam_size,
-        num_samples=4,
-        seed=seed,
-        num_workers=1,
+        batch_size=32,
+        generated_length=length,
     )
-    model = MoLeR(configuration=config)
+    model = PolymerBlocks(config)
     samples = list(model.sample(number_of_samples))
 
-    seed_mols = [] if scaffolds == "" else scaffolds.split(".")
-    return draw_grid_generate(seed_mols, samples)
+    return draw_grid_generate(samples=samples, n_cols=5, seeds=[])
 
 
 if __name__ == "__main__":
@@ -42,7 +34,9 @@ if __name__ == "__main__":
     all_algos = ApplicationsRegistry.list_available()
     algos = [
         x["algorithm_version"]
-        for x in list(filter(lambda x: TITLE in x["algorithm_name"], all_algos))
+        for x in list(
+            filter(lambda x: "PolymerBlocks" in x["algorithm_name"], all_algos)
+        )
     ]
 
     # Load metadata
@@ -59,19 +53,19 @@ if __name__ == "__main__":
 
     demo = gr.Interface(
         fn=run_inference,
-        title="MoLeR (MOlecule-LEvel Representation)",
+        title="Polymer Blocks",
         inputs=[
             gr.Dropdown(algos, label="Algorithm version", value="v0"),
-            gr.Textbox(
-                label="Scaffolds",
-                placeholder="CC(C#C)N(C)C(=O)NC1=CC=C(Cl)C=C1",
-                lines=1,
+            gr.Slider(
+                minimum=5,
+                maximum=400,
+                value=100,
+                label="Maximal sequence length",
+                step=1,
             ),
-            gr.Slider(minimum=1, maximum=5, value=1, step=1, label="Beam_size"),
             gr.Slider(
                 minimum=1, maximum=50, value=10, label="Number of samples", step=1
             ),
-            gr.Number(value=42, label="Seed", precision=0),
         ],
         outputs=gr.HTML(label="Output"),
         article=article,

model_cards/article.md

@@ -1,37 +1,36 @@
 # Model documentation & parameters
 
-**Algorithm Version**: Which model checkpoint to use (trained on different datasets).
+**Algorithm Version**: Which model version to use.
 
-**Scaffolds**: One or multiple scaffolds (or seed molecules), provided as '.'-separated SMILES. If empty, no scaffolds are used.
+**Maximal sequence length**: The maximal number of SMILES tokens in the generated molecule.
 
 **Number of samples**: How many samples should be generated (between 1 and 50).
 
-**Beam size**: Beam size used in beam search decoding (the higher the slower but better).
 
-**Seed**: The random seed used for initialization.
 
+# Model card -- PolymerBlocks
 
-# Model card
+**Model Details**: *PolymerBlocks* is a sequence-based molecular generator tuned to generate blocks of polymers (e.g., catalysts and monomers). The model relies on a Variational Autoencoder architecture as described in [Born et al. (2021; *iScience*)](https://www.sciencedirect.com/science/article/pii/S2589004221002376)
 
-**Model Details**: MoLeR is a graph-based molecular generative model that can be conditioned (primed) on scaffolds. The model decorates scaffolds with realistic structural motifs.
+**Developers**: Matteo Manica and colleagues from IBM Research.
 
-**Developers**: Krzysztof Maziarz and co-authors from Microsoft Research and Novartis (full reference at bottom).
+**Distributors**: Original authors' code integrated into GT4SD.
 
-**Distributors**: Developer's code wrapped and distributed by GT4SD Team (2023) from IBM Research.
+**Model date**: Not yet published.
 
-**Model date**: Released around March 2022.
+**Model version**: Only initial model version.
 
-**Model version**: Model provided by original authors, see [their GitHub repo](https://github.com/microsoft/molecule-generation).
+**Model type**: A sequence-based molecular generator tuned to generate blocks of polymers (e.g., catalysts and monomers).
 
-**Model type**: An encoder-decoder-based GNN for molecular generation.
+**Information about training algorithms, parameters, fairness constraints or other applied approaches, and features**: 
+N.A.
 
-**Information about training algorithms, parameters, fairness constraints or other applied approaches, and features**: Trained by the original authors with the default parameters provided [on GitHub](https://github.com/microsoft/molecule-generation).
-
-**Paper or other resource for more information**: [Learning to Extend Molecular Scaffolds with Structural Motifs (ICLR 2022)](https://openreview.net/forum?id=ZTsoE8G3GG).
+**Paper or other resource for more information**: 
+TBD
 
 **License**: MIT
 
-**Where to send questions or comments about the model**: Open an issue on original author's [GitHub repository](https://github.com/microsoft/molecule-generation).
+**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.
 
@@ -39,11 +38,9 @@
 
 **Out-of-scope use cases**: Production-level inference, producing molecules with harmful properties.
 
-**Factors**: Not applicable.
-
-**Metrics**: Validation loss on decoding correct molecules. Evaluated on several downstream tasks.
+**Metrics**: N.A.
 
-**Datasets**: 1.5M drug-like molecules from GuacaMol benchmark. Finetuning on 20 molecular optimization tasks from GuacaMol.
+**Datasets**: N.A.
 
 **Ethical Considerations**: Unclear, please consult with original authors in case of questions.
 
@@ -52,14 +49,12 @@
 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
-@inproceedings{maziarz2021learning,
-  author={Krzysztof Maziarz and Henry Richard Jackson{-}Flux and Pashmina Cameron and
-    Finton Sirockin and Nadine Schneider and Nikolaus Stiefl and Marwin H. S. Segler and Marc Brockschmidt},
-  title     = {Learning to Extend Molecular Scaffolds with Structural Motifs},
-  booktitle = {The Tenth International Conference on Learning Representations, {ICLR}},
-  year      = {2022}
+@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

@@ -1,6 +1,6 @@
 <img align="right" src="https://raw.githubusercontent.com/GT4SD/gt4sd-core/main/docs/_static/gt4sd_logo.png" alt="logo" width="120" >
 
-MoLeR ([Maziarz et al., (2022), *ICLR*](https://openreview.net/forum?id=ZTsoE8G3GG)) is a graph-based molecular generative model that can be conditioned (primed) on scaffolds. This model is provided and distributed by the **GT4SD** (Generative Toolkit for Scientific Discovery).
+*PolymerBlocks* is a sequence-based molecular generator tuned to generate blocks of polymers (e.g., catalysts and monomers). The model relies on a Variational Autoencoder architecture as described in [Born et al. (2021; *iScience*)](https://www.sciencedirect.com/science/article/pii/S2589004221002376)
 
 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

@@ -1,5 +1 @@
-v0,,1,4,0
-v0,CC(=O)NC1=NC2=CC(OCC3=CC=CN(CC4=CC=C(Cl)C=C4)C3=O)=CC=C2N1,1,10,0
-v0,C12C=CC=NN1C(C#CC1=C(C)C=CC3C(NC4=CC(C(F)(F)F)=CC=C4)=NOC1=3)=CN=2.CCO,3,5,5
-
-
+v0,100,10

requirements.txt

@@ -8,7 +8,7 @@ torch-sparse
 torch-geometric
 torchvision==0.13.1
 torchaudio==0.12.1
-gt4sd>=1.0.0
+gt4sd>=1.0.5
 molgx>=0.22.0a1
 molecule_generation
 nglview

utils.py

@@ -1,21 +1,17 @@
-import json
 import logging
-import os
 from collections import defaultdict
-from typing import Dict, List, Tuple
+from typing import List
 
 import mols2grid
 import pandas as pd
-from rdkit import Chem
-from terminator.selfies import decoder
 
 logger = logging.getLogger(__name__)
 logger.addHandler(logging.NullHandler())
 
 
 def draw_grid_generate(
-    seeds: List[str],
     samples: List[str],
+    seeds: List[str] = [],
     n_cols: int = 3,
     size=(140, 200),
 ) -> str: