Large Language Models for Accessible Reporting of Bioinformatics Analyses in Interdisciplinary Contexts
Yu, Lijia, Kim, Daniel, Cao, Yue, Shu, Matthew Wei Shun, Shen, Maya, Liang, Xiaoqi, Gu, Jasmine, Jayakumar, Rojashree, Ding, Wenze, Yang, Fei, Zhang, Xumou, Kim, Jinman, Yang, Pengyi, Yang, Jean Yee Hwa npj Systems Biology and Applications
· Springer Nature
· 2026-11-05
· DOI: 10.1038/s41540-026-00849-2
Аннотация
Health and life scientists frequently rely on quantitative experts to perform complex data analyses, yet interpretation of these results often becomes a bottleneck due to communication barriers across disciplines. Large Language Models (LLMs) have the potential to act as intermediaries that translate analytical outputs into accessible scientific narratives, but their ability to reliably interpret outputs from real-world biomedical data analyses across disciplines remains unclear. In this study, we investigate how state-of-the-art LLMs behave when integrated into real bioinformatics analysis workflows as report-generation assistants for interdisciplinary teams. We evaluated LLM-generated summaries using both automated and human evaluation frameworks to ensure holistic evaluation. Automated assessment employed multiple-choice questions designed using Bloom’s taxonomy to assess multiple levels of understanding, while human evaluation tasked scientists to score summaries for factual consistency, lack of harmfulness, comprehensiveness, and coherence. All generally produced readable and largely safe summaries, confirming their value for first-pass translation of technical analyses; however frequently misinterpreted visualisations, produced verbose summaries and rarely offered novel insights beyond what was already contained in the analytics. Our findings suggest that LLMs are best suited for easing interdisciplinary communication rather than replacing domain expertise and human oversight remains essential to guarantee accuracy, interpretative depth, and the generation of genuinely novel scientific insights.
Yu, Lijia, Kim, Daniel, Cao, Yue et al. Large Language Models for Accessible Reporting of Bioinformatics Analyses in Interdisciplinary Contexts. // npj Systems Biology and Applications. – 2026. – DOI: 10.1038/s41540-026-00849-2. – URL: https://doi.org/10.1038/s41540-026-00849-2
Yu, Lijia, Kim, Daniel, Cao, Yue, Shu, Matthew Wei Shun, Shen, Maya, Liang, Xiaoqi, Gu, Jasmine, Jayakumar, Rojashree, Ding, Wenze, Yang, Fei, Zhang, Xumou, Kim, Jinman, Yang, Pengyi, Yang, & Jean Yee Hwa (2026). Large Language Models for Accessible Reporting of Bioinformatics Analyses in Interdisciplinary Contexts. npj Systems Biology and Applications. https://doi.org/10.1038/s41540-026-00849-2
Yu, et al. “Large Language Models for Accessible Reporting of Bioinformatics Analyses in Interdisciplinary Contexts.” npj Systems Biology and Applications, 2026. doi:10.1038/s41540-026-00849-2.
@article{Yu2026,
title = {Large Language Models for Accessible Reporting of Bioinformatics Analyses in Interdisciplinary Contexts},
author = {Yu and Lijia and Kim and Daniel and Cao and Yue and Shu and Shun, Matthew Wei and Shen and Maya and Liang and Xiaoqi and Gu and Jasmine and Jayakumar and Rojashree and Ding and Wenze and Yang and Fei and Zhang and Xumou and Kim and Jinman and Yang and Pengyi and Yang and Hwa, Jean Yee},
journal = {npj Systems Biology and Applications},
year = {2026},
doi = {10.1038/s41540-026-00849-2},
url = {https://doi.org/10.1038/s41540-026-00849-2}
}
Polyamines, namely putrescine, spermidine and spermine, are essential polycations. Their homeostasis is governed by a nonlinear network of biosynthesis, catabolism, transport, and feedback control. We present an 18-variable ordinary...
Microbial growth is constrained by physicochemical and spatial limitations that shape how cells utilize available nutrients. Over evolutionary timescales, evolution has shaped protein allocation to optimize growth across diverse...
Targeted therapies are increasingly utilized across cancer types, yet their efficacy in triple-negative breast cancer (TNBC) remains limited due to the disease’s high heterogeneity and aggressive nature. In a heterogeneous tumor,...
Understanding the mechanical behavior of immune cells as they migrate through the complex environment of solid tumors may be crucial for improving immunotherapy strategies. In this work, we present a particle-based model that captures...
The tumor-stroma local interfaces (TSLIs) are functionally critical, dynamic regions that influence cancer progression, invasiveness, and anti-tumor immunity. Transcriptional programs and intercellular interactions suggest that some...