Bioinformatics Illustrations Decoded by ChatGPT: The Good, The Bad, and The Ugly

Abstract

Emerging studies underscore the promising capabilities of large language model-based chatbots in conducting fundamental bioinformatics data analyses. The recent feature of accepting image-inputs by ChatGPT motivated us to explore its efficacy in deciphering bioinformatics illustrations. Our evaluation with examples in cancer research, including sequencing data analysis, multimodal network-based drug repositioning, and tumor clonal evolution, revealed that ChatGPT can proficiently explain different plot types and apply biological knowledge to enrich interpretations. However, it struggled to provide accurate interpretations when quantitative analysis of visual elements was involved. Furthermore, while the chatbot can draft figure legends and summarize findings from the figures, stringent proofreading is imperative to ensure the accuracy and reliability of the content.

ChatGPT in medicine: prospects and challenges: a review article

“…Additionally, ChatGPT can also help improve research efficiency 37 . ChatGPT has the powerful ability to collect and summarize information, which can help researchers keep abreast of the latest progression in related fields.…”

Robodoc: a conversational-AI based app for medical conversations

“…Large language model-based chatbots like ChatGPT are also being explored in conducting bioinformatics data analyses, such as deciphering bioinformatics illustrations and applying biological knowledge Wang et al (2023). Additionally, there are efforts to evaluate the use of chatbots for answering questions related to COVID-19 using language models like GPT-2 and different approaches for filtering relevant responses Oniani and Wang (2020).…”