KFU. Card publication. HyFactor: A Novel Open-Source, Graph-Based Architecture for Chemical Structure Generation

KAZAN
FEDERAL UNIVERSITY

- RUS
- 中文
- ES

HYFACTOR: A NOVEL OPEN-SOURCE, GRAPH-BASED ARCHITECTURE FOR CHEMICAL STRUCTURE GENERATION

Form of presentation

Articles in international journals and collections

Year of publication

2022

��

��

Authors, employees of KFU

Madzhidov Timur Ismailovich, author

Bibliographic description in the original language

Akhmetshin T. HyFactor: A Novel Open-Source, Graph-Based Architecture for Chemical Structure Generation / Akhmetshin T., Lin A., Mazitov D., Zabolotna Yu., Ziaikin E., Madzhidov T., Varnek A. // Journal of Chemical Information and Modeling. - 2022. - Vol. 62, Is. 15. - P. 3524-3534.

Annotation

Graph-based architectures are becoming increasingly popular as a tool for structure generation. Here, we introduce novel open-source architecture HyFactor in which, similar to the InChI linear notation, the number of hydrogens attached to the heavy atoms was considered instead of the bond types. HyFactor was benchmarked on the ZINC 250K, MOSES, and ChEMBL data sets against conventional graph-based architecture ReFactor, representing our implementation of the reported DEFactor architecture in the literature. On average, HyFactor models contain some 20% less fitting parameters than those of ReFactor. The two architectures display similar validity, uniqueness, and reconstruction rates. Compared to the training set compounds, HyFactor generates more similar structures than ReFactor. This could be explained by the fact that the latter generates many open-chain analogues of cyclic structures in the training set. It has been demonstrated that the reconstruction error of heavy molecules can be significantly reduced using the data augmentation technique. The codes of HyFactor and ReFactor as well as all models obtained in this study are publicly available from our GitHub repository: https://github.com/Laboratoire-de-Chemoinformatique/HyFactor.

Keywords

Chemical structure,Embedding,Layers,Molecular structure,Molecules

The name of the journal

Journal of Chemical Information and Modeling

URL

https://pubs.acs.org/doi/10.1021/acs.jcim.2c00744

Please use this ID to quote from or refer to the card

https://repository.kpfu.ru/eng/?p_id=281120&p_lang=2

Full metadata record

Field DC	Value	Language
dc.contributor.author	Madzhidov Timur Ismailovich	ru_RU
dc.date.accessioned	2022-01-01T00:00:00Z	ru_RU
dc.date.available	2022-01-01T00:00:00Z	ru_RU
dc.date.issued	2022	ru_RU
dc.identifier.citation	Akhmetshin T. HyFactor: A Novel Open-Source, Graph-Based Architecture for Chemical Structure Generation / Akhmetshin T., Lin A., Mazitov D., Zabolotna Yu., Ziaikin E., Madzhidov T., Varnek A. // Journal of Chemical Information and Modeling. - 2022. - Vol. 62, Is. 15. - P. 3524-3534.	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/eng/?p_id=281120&p_lang=2	ru_RU
dc.description.abstract	Journal of Chemical Information and Modeling	ru_RU
dc.description.abstract	Graph-based architectures are becoming increasingly popular as a tool for structure generation. Here, we introduce novel open-source architecture HyFactor in which, similar to the InChI linear notation, the number of hydrogens attached to the heavy atoms was considered instead of the bond types. HyFactor was benchmarked on the ZINC 250K, MOSES, and ChEMBL data sets against conventional graph-based architecture ReFactor, representing our implementation of the reported DEFactor architecture in the literature. On average, HyFactor models contain some 20% less fitting parameters than those of ReFactor. The two architectures display similar validity, uniqueness, and reconstruction rates. Compared to the training set compounds, HyFactor generates more similar structures than ReFactor. This could be explained by the fact that the latter generates many open-chain analogues of cyclic structures in the training set. It has been demonstrated that the reconstruction error of heavy molecules can be significantly reduced using the data augmentation technique. The codes of HyFactor and ReFactor as well as all models obtained in this study are publicly available from our GitHub repository: https://github.com/Laboratoire-de-Chemoinformatique/HyFactor.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	Chemical structure	ru_RU
dc.subject	Embedding	ru_RU
dc.subject	Layers	ru_RU
dc.subject	Molecular structure	ru_RU
dc.subject	Molecules	ru_RU
dc.title	HyFactor: A Novel Open-Source, Graph-Based Architecture for Chemical Structure Generation	ru_RU
dc.type	Articles in international journals and collections	ru_RU