Chaining thoughts and LLMs to learn DNA structural biophysics
This work addresses the need for general-purpose AI tools in scientific research, though it appears incremental as it builds on existing LLMs for a specific domain.
The authors tackled the problem of creating a flexible AI scientist for DNA structural biophysics by fine-tuning ChatGPT 3.5-turbo, resulting in enhanced ability to analyze and design DNA sequences and structures through chain-of-thought responses and model chaining.
The future development of an AI scientist, a tool that is capable of integrating a variety of experimental data and generating testable hypotheses, holds immense potential. So far, bespoke machine learning models have been created to specialize in singular scientific tasks, but otherwise lack the flexibility of a general purpose model. Here, we show that a general purpose large language model, chatGPT 3.5-turbo, can be fine-tuned to learn the structural biophysics of DNA. We find that both fine-tuning models to return chain-of-thought responses and chaining together models fine-tuned for subtasks have an enhanced ability to analyze and design DNA sequences and their structures.