Specialising and Analysing Instruction-Tuned and Byte-Level Language Models for Organic Reaction Prediction

TL;DR

This study evaluates the effectiveness of language-pretrained models FlanT5 and ByT5, fine-tuned for organic reaction prediction, demonstrating that pretraining on language data alone can be sufficient for chemistry tasks.

Contribution

It systematically investigates how language models pretrained on general text can be adapted for chemical reaction prediction, highlighting their domain compatibility and efficiency.

Findings

Language models pretrained on text can be effectively fine-tuned for chemistry.

Tokenisation and vocabulary trimming influence performance and speed.

Simple greedy decoding performs competitively with more complex algorithms.

Abstract

Transformer-based encoder-decoder models have demonstrated impressive results in chemical reaction prediction tasks. However, these models typically rely on pretraining using tens of millions of unlabelled molecules, which can be time-consuming and GPU-intensive. One of the central questions we aim to answer in this work is: Can FlanT5 and ByT5, the encode-decoder models pretrained solely on language data, be effectively specialised for organic reaction prediction through task-specific fine-tuning? We conduct a systematic empirical study on several key issues of the process, including tokenisation, the impact of (SMILES-oriented) pretraining, fine-tuning sample efficiency, and decoding algorithms at inference. Our key findings indicate that although being pretrained only on language tasks, FlanT5 and ByT5 provide a solid foundation to fine-tune for reaction prediction, and thus become `chemistry domain compatible' in the process. This suggests that GPU-intensive and expensive pretraining on a large dataset of unlabelled molecules may be useful yet not essential to leverage the power of language models for chemistry. All our models achieve comparable Top-1 and Top-5 accuracy although some variation across different models does exist. Notably, tokenisation and vocabulary trimming slightly affect final performance but can speed up training and inference; The most efficient greedy decoding strategy is very competitive while only marginal gains can be achieved from more sophisticated decoding algorithms. In summary, we evaluate FlanT5 and ByT5 across several dimensions and benchmark their impact on organic reaction prediction, which may guide more effective use of these state-of-the-art language models for chemistry-related tasks in the future.