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

TL;DR

ReacLLaMA introduces methods to incorporate procedural textual information into chemical reactivity models, enhancing their accuracy and ability to identify unpromising reactions by combining chemical data with synthetic protocols.

Contribution

The paper presents novel approaches to integrate procedural text with chemical data in reactivity models, improving prediction accuracy and specificity.

Findings

Enhanced model accuracy with procedural text integration

Improved identification of unpromising reactions

Effective use of GPT-2 and LLaMA 2 models for data augmentation

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.