ReacLLaMA: Merging chemical and textual information in chemical reactivity AI models
A Hartgers, R Nugmanov, K Chernichenko… - arXiv preprint arXiv …, 2024 - arxiv.org
A Hartgers, R Nugmanov, K Chernichenko, JK Wegner
arXiv preprint arXiv:2401.17267, 2024•arxiv.orgChemical 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 …
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 …
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.
arxiv.org