Guardado en:
Detalles Bibliográficos
Autores principales: Hartgers, Aline, Nugmanov, Ramil, Chernichenko, Kostiantyn, Wegner, Joerg Kurt
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2401.17267
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917578479239168
author Hartgers, Aline
Nugmanov, Ramil
Chernichenko, Kostiantyn
Wegner, Joerg Kurt
author_facet Hartgers, Aline
Nugmanov, Ramil
Chernichenko, Kostiantyn
Wegner, Joerg Kurt
contents Chemical reactivity models are developed to predict chemical reaction outcomes in the form of classification (success/failure) or regression (product yield) tasks. The vast majority of the reported models are trained solely on chemical information such as reactants, products, reagents, and solvents, but not on the details of a synthetic protocol. Herein incorporation of procedural text with the aim to augment the Graphormer reactivity model and improve its accuracy is presented. Two major approaches are used: training an adapter Graphormer model that is provided with a GPT-2-derived latent representation of the text procedure (ReacLLaMA-Adapter) and labeling an unlabeled part of a dataset with the LLaMA 2 model followed by training the Graphormer on an extended dataset (Zero-Shot Labeling ReacLLaMA). Both methodologies enhance the discernment of unpromising reactions, thereby providing more accurate models with improved specificity.
format Preprint
id arxiv_https___arxiv_org_abs_2401_17267
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ReacLLaMA: Merging chemical and textual information in chemical reactivity AI models
Hartgers, Aline
Nugmanov, Ramil
Chernichenko, Kostiantyn
Wegner, Joerg Kurt
Machine Learning
Quantitative Methods
Chemical reactivity models are developed to predict chemical reaction outcomes in the form of classification (success/failure) or regression (product yield) tasks. The vast majority of the reported models are trained solely on chemical information such as reactants, products, reagents, and solvents, but not on the details of a synthetic protocol. Herein incorporation of procedural text with the aim to augment the Graphormer reactivity model and improve its accuracy is presented. Two major approaches are used: training an adapter Graphormer model that is provided with a GPT-2-derived latent representation of the text procedure (ReacLLaMA-Adapter) and labeling an unlabeled part of a dataset with the LLaMA 2 model followed by training the Graphormer on an extended dataset (Zero-Shot Labeling ReacLLaMA). Both methodologies enhance the discernment of unpromising reactions, thereby providing more accurate models with improved specificity.
title ReacLLaMA: Merging chemical and textual information in chemical reactivity AI models
topic Machine Learning
Quantitative Methods
url https://arxiv.org/abs/2401.17267