Evaluation of GPT-3 for Anti-Cancer Drug Sensitivity Prediction

TL;DR

This paper explores GPT-3's ability to predict anti-cancer drug sensitivity using pharmacogenomics data, assessing zero-shot and fine-tuning methods to improve precision oncology treatments.

Contribution

It is the first to evaluate GPT-3's performance in drug sensitivity prediction with structured pharmacogenomics data across multiple tissue types.

Findings

GPT-3 can predict drug response using SMILES and genomic features.

Zero-shot and fine-tuning approaches show promising results.

Potential to enhance personalized cancer treatment protocols.

Abstract

In this study, we investigated the potential of GPT-3 for the anti-cancer drug sensitivity prediction task using structured pharmacogenomics data across five tissue types and evaluated its performance with zero-shot prompting and fine-tuning paradigms. The drug's smile representation and cell line's genomic mutation features were predictive of the drug response. The results from this study have the potential to pave the way for designing more efficient treatment protocols in precision oncology.