A Generative Artificial Intelligence Copilot for Biomedical Nanoengineering

The recent success of large language models (LLMs) in performing natural language processing tasks has increased interest in applying generative artificial intelligence (AI) to scientific research. However, a common problem of LLMs is their tendency to produce inaccurate and sometimes "hallucinated" outputs. Here, we established a generative AI tool, NanoSafari, to automatically extract knowledge from the biomedical nanoscience literature and address scientific queries. We developed the Grouped Iterative Validation based Information Extraction (GIVE) method to extract contextual information on nanoparticle characteristics from >20,000 published articles and established a database that was incorporated into the generative LLM to provide accurate nanomaterial design parameters. Blinded evaluation by biomedical nanoscientists showed that NanoSafari outperformed the baseline model in providing more reliable parameters for nanomaterial design tasks, as further validated by bench experiments. Together, these findings demonstrate the utility of AI-based methods for automated learning from "real-world" published work to provide accurate and reliable scientific references for biomaterial and bioengineering applications.

Authors

Institutions

Publication Details

Journal
ACS Nano
Published
2025-05-14
DOI
https://doi.org/10.1021/acsnano.5c03454
Citations
9
Primary Topic
3D Printing in Biomedical Research
Type
article
Field-Weighted Citation Impact
6.07
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A Generative Artificial Intelligence Copilot for Biomedical Nanoengineering

Yue Teng, Weiye Deng, Seong Dong Jeong, Adam Grippin et al.
9 citations
ACS Nano
3D Printing in Biomedical Research
6.07
article

A Generative Artificial Intelligence Copilot for Biomedical Nanoengineering

Yue Teng, Weiye Deng, Seong Dong Jeong, Adam Grippin, Jinjun Qian, Lesheng Teng, Benjamin R. Schrank, Yifan Ma, Shiyan Dong, Annette Wu, Guan Huang, Hongyu Wang, Stefan Wilhelm, Wilson Poon, Yuanyuan Lin, Wen Jiang, Yifan Wang, Ye Bi, Haitao Song, Yixiang Zhang, Zikai Wang, JongHoon Ha, Mengyu Chang, Jared L. Edwards
article en
9 citations

Abstract

The recent success of large language models (LLMs) in performing natural language processing tasks has increased interest in applying generative artificial intelligence (AI) to scientific research. However, a common problem of LLMs is their tendency to produce inaccurate and sometimes "hallucinated" outputs. Here, we established a generative AI tool, NanoSafari, to automatically extract knowledge from the biomedical nanoscience literature and address scientific queries. We developed the Grouped Iterative Validation based Information Extraction (GIVE) method to extract contextual information on nanoparticle characteristics from >20,000 published articles and established a database that was incorporated into the generative LLM to provide accurate nanomaterial design parameters. Blinded evaluation by biomedical nanoscientists showed that NanoSafari outperformed the baseline model in providing more reliable parameters for nanomaterial design tasks, as further validated by bench experiments. Together, these findings demonstrate the utility of AI-based methods for automated learning from "real-world" published work to provide accurate and reliable scientific references for biomaterial and bioengineering applications.

ACS NanoVol. 19(20)
The University of Texas MD Anderson Cancer Center (US), The University of Texas at El Paso (US), Chinese University of Hong Kong (HK), Jilin University (CN), Institute for Biomedical Engineering (CH), Beijing Academy of Artificial Intelligence (CN), Experimental Station (US), Changchun University of Chinese Medicine (CN), Jilin Medical University (CN), Sigma Research (United States) (US), OU Health Stephenson Cancer Center, University of Oklahoma (US)
Openalex Percentile: Top 3%
3D Printing in Biomedical Research
6.07
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.