Saved in:
Bibliographic Details
Main Authors: Shermukhamedov, Shokirbek, Mamurjonova, Dilorom, Probst, Michael
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