Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2309.09355 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917751606476800 |
|---|---|
| author | Shermukhamedov, Shokirbek Mamurjonova, Dilorom Probst, Michael |
| author_facet | Shermukhamedov, Shokirbek Mamurjonova, Dilorom Probst, Michael |
| contents | We introduce the elEmBERT model for chemical classification tasks. It is based on deep learning techniques, such as a multilayer encoder architecture. We demonstrate the opportunities offered by our approach on sets of organic, inorganic and crystalline compounds. In particular, we developed and tested the model using the Matbench and Moleculenet benchmarks, which include crystal properties and drug design-related benchmarks. We also conduct an analysis of vector representations of chemical compounds, shedding light on the underlying patterns in structural data. Our model exhibits exceptional predictive capabilities and proves universally applicable to molecular and material datasets. For instance, on the Tox21 dataset, we achieved an average precision of 96%, surpassing the previously best result by 10%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_09355 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Structure to Property: Chemical Element Embeddings and a Deep Learning Approach for Accurate Prediction of Chemical Properties Shermukhamedov, Shokirbek Mamurjonova, Dilorom Probst, Michael Chemical Physics Materials Science Machine Learning Atomic and Molecular Clusters Quantitative Methods We introduce the elEmBERT model for chemical classification tasks. It is based on deep learning techniques, such as a multilayer encoder architecture. We demonstrate the opportunities offered by our approach on sets of organic, inorganic and crystalline compounds. In particular, we developed and tested the model using the Matbench and Moleculenet benchmarks, which include crystal properties and drug design-related benchmarks. We also conduct an analysis of vector representations of chemical compounds, shedding light on the underlying patterns in structural data. Our model exhibits exceptional predictive capabilities and proves universally applicable to molecular and material datasets. For instance, on the Tox21 dataset, we achieved an average precision of 96%, surpassing the previously best result by 10%. |
| title | Structure to Property: Chemical Element Embeddings and a Deep Learning Approach for Accurate Prediction of Chemical Properties |
| topic | Chemical Physics Materials Science Machine Learning Atomic and Molecular Clusters Quantitative Methods |
| url | https://arxiv.org/abs/2309.09355 |