Related papers: ReacLLaMA: Merging chemical and textual information in chemical reactivity AI models

ReacLLaMA: Merging chemical and textual information in chemical reactivity AI models

URL: http://arxiv.org/abs/2401.17267v1
Date: Tue, 30 Jan 2024 18:57:08 GMT
Title: ReacLLaMA: Merging chemical and textual information in chemical reactivity AI models
Authors: Aline Hartgers, Ramil Nugmanov, Kostiantyn Chernichenko, Joerg Kurt Wegner
Abstract summary: 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. Herein incorporation of procedural text with the aim to augment the Graphormer reactivity model and improve its accuracy is presented.
Score: 0.0
License: http://creativecommons.org/licenses/by-sa/4.0/
Abstract: 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.