Update model_cards/article.md

model_cards/article.md

@@ -4,15 +4,15 @@
 
 ### Property
 The supported properties are:
-  - `Metal NonMetal Classifier`: Predicted by a RF model (WHICH? )
-  - `Metal Semiconductor Classifier`: Classifying whether a metal could be a semiconductor. Predicted with CGCNN (ToDo: Add Ref!)
-  - `Poisson Ratio`:  ToDo: Description + Reference
-  - `Shear Moduli` ...
-  - `Bulk Moduli`
-  - `Fermi Energy`
-  - `Band Gap`
-  - `Absolute Energy`
-  - `Formation Energy`
+  - `Metal NonMetal Classifier`: Classifying whether a crystal could be metal or nonmetal using a [RandomForest classifier](https://www.nature.com/articles/s41524-022-00850-3)
+  - `Metal Semiconductor Classifier`: Classifying whether a crystal could be metal or semiconductor using the [CGCNN framework](https://link.aps.org/doi/10.1103/PhysRevLett.120.145301).
+  - `Poisson Ratio`:  Predicted using the [CGCNN framework](https://link.aps.org/doi/10.1103/PhysRevLett.120.145301).
+  - `Shear Moduli`:  Predicted using the [CGCNN framework](https://link.aps.org/doi/10.1103/PhysRevLett.120.145301).
+  - `Bulk Moduli`:  Predicted using the [CGCNN framework](https://link.aps.org/doi/10.1103/PhysRevLett.120.145301).
+  - `Fermi Energy`:  Predicted using the [CGCNN framework](https://link.aps.org/doi/10.1103/PhysRevLett.120.145301).
+  - `Band Gap`:  Predicted using the [CGCNN framework](https://link.aps.org/doi/10.1103/PhysRevLett.120.145301).
+  - `Absolute Energy`:  Predicted using the [CGCNN framework](https://link.aps.org/doi/10.1103/PhysRevLett.120.145301).
+  - `Formation Energy`:  Predicted using the [CGCNN framework](https://link.aps.org/doi/10.1103/PhysRevLett.120.145301).
 
 
 ### Input file for crystal model
@@ -24,46 +24,45 @@ The file with information about the metal. Dependent on the property you want to
 
 # Model card - CGCNN
 
-**Model Details**: The [Regression Transformer](https://arxiv.org/abs/2202.01338) is a multitask Transformer that reformulates regression as a conditional sequence modeling task. This yields a dichotomous language model that seamlessly integrates property prediction with property-driven conditional generation.
+**Model Details**: Eight CGCNN models trained to predict various properties for crystals. 
 
-**Developers**: Jannis Born and Matteo Manica from IBM Research.
+**Developers**: [CGCNN's](https://github.com/txie-93/cgcnn) developers.
 
 **Distributors**: Original authors' code wrapped and distributed by GT4SD Team (2023) from IBM Research.
 
-**Model date**: Preprint released in 2022, currently under review at *Nature Machine Intelligence*.
+**Model date**: 2018.
 
 **Algorithm version**: Models trained and distributed by the original authors.
-- **Molecules: QED**: Model trained on 1.6M molecules (SELFIES) from ChEMBL and their QED scores.
-- **Molecules: Solubility**: QED model finetuned on the ESOL dataset from [Delaney et al (2004), *J. Chem. Inf. Comput. Sci.*](https://pubs.acs.org/doi/10.1021/ci034243x) to predict water solubility. Model trained on augmented SELFIES.
-- **Molecules: USPTO**: Model trained on 2.8M [chemical reactions](https://figshare.com/articles/dataset/Chemical_reactions_from_US_patents_1976-Sep2016_/5104873) from the US patent office. The model used SELFIES and a synthetic property (total molecular weight of all precursors).
-- **Molecules: Polymer**: Model finetuned on 600 ROPs (ring-opening polymerizations) with monomer-catalyst pairs. Model used three properties: conversion (`<conv>`), PDI (`<pdi>`) and Molecular Weight (`<molwt>`). Model trained with augmented SELFIES, optimized only to generate catalysts, given a monomer and the property constraints. See the example for details.
-- **Molecules: Cosmo_acdl**: Model finetuned on 56k molecules with two properties (*pKa_ACDL* and *pKa_COSMO*). Model used augmented SELFIES.
-- **Molecules: Pfas**: Model finetuned on ~1k PFAS (Perfluoroalkyl and Polyfluoroalkyl Substances) molecules with 9 properties including some experimentally measured ones (biodegradability, LD50 etc) and some synthetic ones (SCScore, molecular weight). Model trained on augmented SELFIES.
-- **Molecules: Logp_and_synthesizability**: Model trained on 2.9M molecules (SELFIES) from PubChem with **two** synthetic properties, the logP (partition coefficient) and the [SCScore by Coley et al. (2018); *J. Chem. Inf. Model.*](https://pubs.acs.org/doi/full/10.1021/acs.jcim.7b00622?casa_token=JZzOrdWlQ_QAAAAA%3A3_ynCfBJRJN7wmP2gyAR0EWXY-pNW_l-SGwSSU2SGfl5v5SxcvqhoaPNDhxq4THberPoyyYqTZELD4Ck)
-- **Molecules: Crippen_logp**: Model trained on 2.9M molecules (SMILES) from PubChem, but *only* on logP (partition coefficient).
-- **Proteins: Stability**: Model pretrained on 2.6M peptides from UniProt with the Boman index as property. Finetuned on the [**Stability**](https://www.science.org/doi/full/10.1126/science.aan0693) dataset from the [TAPE benchmark](https://proceedings.neurips.cc/paper/2019/hash/37f65c068b7723cd7809ee2d31d7861c-Abstract.html) which has ~65k samples.
-
-**Model type**: A Transformer-based language model that is trained on alphanumeric sequence to simultaneously perform sequence regression or conditional sequence generation.
+- **Metal Semiconductor Classifier**: Model trained to classify whether a crystal could be metal or semiconductor using instances from this [database](https://aip.scitation.org/doi/10.1063/1.4812323) that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals..
+- **Poisson Ratio**: Model to predict the Poisson ratio trained on 2041 instances from this [database](https://aip.scitation.org/doi/10.1063/1.4812323) that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals.
+- **Shear Moduli**: Model to predict the Shear moduli trained on 2041 instances from this [database](https://aip.scitation.org/doi/10.1063/1.4812323) that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals. Unit log(GPa).
+- **Bulk Moduli**: Model to predict the Bulk moduli trained on 2041 instances from this [database](https://aip.scitation.org/doi/10.1063/1.4812323) that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals. Unit log(GPa).
+- **Fermi Energy**: Model to predict the Fermi energy trained on 28046 instances from this [database](https://aip.scitation.org/doi/10.1063/1.4812323) that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals. Unit eV.
+- **Band Gap**: Model to predict the Band Gap trained on 16458 instances from this [database](https://aip.scitation.org/doi/10.1063/1.4812323) that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals. Unit eV.
+- **Absolute Energy**: Model to predict the Absolute energy trained on 28046 instances from this [database](https://aip.scitation.org/doi/10.1063/1.4812323) that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals. Unit eV/atom.
+- **Formation Energy**: Model to predict the formation energy trained on 28046 instances from this [database](https://aip.scitation.org/doi/10.1063/1.4812323) that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals. Unit eV/atom.
+  
+**Model type**: Crystal Graph Convolutional Neural Networks (CGCNN) that take an arbitary crystal structure to predict material properties.
 
 **Information about training algorithms, parameters, fairness constraints or other applied approaches, and features**: 
-All models are trained with an alternated training scheme that alternated between optimizing the cross-entropy loss on the property tokens ("regression") or the self-consistency objective on the molecular tokens. See the [Regression Transformer](https://arxiv.org/abs/2202.01338) paper for details.
+See the [CGCNN](https://link.aps.org/doi/10.1103/PhysRevLett.120.145301) paper for details.
 
 **Paper or other resource for more information**: 
-The [Regression Transformer](https://arxiv.org/abs/2202.01338) paper. See the [source code](https://github.com/IBM/regression-transformer) for details.
+The [CGCNN](https://link.aps.org/doi/10.1103/PhysRevLett.120.145301) paper. See the [source code](https://github.com/txie-93/cgcnn) for details.
 
 **License**: MIT
 
-**Where to send questions or comments about the model**: Open an issue on [GT4SD repository](https://github.com/GT4SD/gt4sd-core).
+**Where to send questions or comments about the model**: Open an issue on [CGCNN](https://github.com/txie-93/cgcnn) repo.
 
-**Intended Use. Use cases that were envisioned during development**: Chemical research, in particular drug discovery.
+**Intended Use. Use cases that were envisioned during development**: Materials research.
 
-**Primary intended uses/users**: Researchers and computational chemists using the model for model comparison or research exploration purposes.
+**Primary intended uses/users**: Researchers using the model for model comparison or research exploration purposes.
 
 **Out-of-scope use cases**: Production-level inference, producing molecules with harmful properties.
 
-**Factors**: Not applicable.
+**Factors**: N.A.
 
-**Metrics**: High predictive power for the properties of that specific algorithm version.
+**Metrics**: N.A.
 
 **Datasets**: Different ones, as described under **Algorithm version**.
 
@@ -82,10 +81,18 @@ ToDo...
 # Citation
 
 ```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}
+@article{PhysRevLett.120.145301,
+  title = {Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties},
+  author = {Xie, Tian and Grossman, Jeffrey C.},
+  journal = {Phys. Rev. Lett.},
+  volume = {120},
+  issue = {14},
+  pages = {145301},
+  numpages = {6},
+  year = {2018},
+  month = {Apr},
+  publisher = {American Physical Society},
+  doi = {10.1103/PhysRevLett.120.145301},
+  url = {https://link.aps.org/doi/10.1103/PhysRevLett.120.145301}
 }
 ```