Chemical Reaction Prediction

Course Project on Natural Language Processing

This is the final project for the graduate level course Natural Language Processing with Representation Learning. The project is based on Chemformer (Irwin et al., 2022) and LlasMol (Yu et al., 2024). Instead of exploring the capacity of LLM in performing such task, we shifted our focus to the finetuning process of small LMs as well as dataset construction for training. The strong motive for this shifted goal/focus is because of the limited resources one may have in real-world scenarios. In this project, we first popose a data construction pipeline when time and chemical resources are rather limited. Then, we tried out various finetunning methods on a Bart-based pretrained small scale LM and acquire a good enough performance comparing to a full parameter finetunning. We tested our model on the dataset we constructed as well as the original dataset.

Report

Repo

Huggingface

References

2024

  1. LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset
    Botao Yu, Frazier N. Baker, Ziqi Chen, and 2 more authors
    2024

2022

  1. Chemformer: a pre-trained transformer for computational chemistry
    Ross Irwin, Spyridon Dimitriadis, Jiazhen He, and 1 more author
    Machine Learning: Science and Technology, Jan 2022