Citations 2
Large language models for bioinformatics
Ruan, Wei, Lyu, Yanjun , Zhang, Jing , Cai, Jiazhang , Lu, Yao , Wang, Tao , Liu, Yufang , Fang, Luyang , Liu, Ziyu , Liu, Zhengliang , Li, Yiwei , Wu, Zihao , Chen, Junhao , Jiang, Hanqi, Yang, Zhenyuan, Liang, Shizhe, Zhang, Wei , Ma, Terry, Dou, Yuan , Zhang, Jianli , Gong, Xinyu , Gan, Qi , Zou, Yusong , Chen, Z. J. , Qian, Yuanxin, Yu, Shuo , Song, Kenan, Sikora, Andrea, Li, Xiang , Wang, Yingfeng , Zhong, Wenxuan, Liu, Rongjie , Huang, Chao , Shen, Ye , Yan, Yajun , Liu, Tianming, Huang, Chao , Song, Kenan , Wang, Peilong, Chen, Jingyuan, Song, Kenan , Ruan, Wei, Shu, Peng , Yang, Ge , Gao, Shang , Wang, Yue , Wang, Peilong , Zhao, Lin , Jiang, Hanqi , Pan, Yi Feng , Chen, Jingyuan , Dou, Yuan, Chen, Z. J. , Qian, Yuanxin, Jin, Lu , Wang, Xianqiao , Sikora, Andrea , Li, Gang , Li, Quanzheng , Zhang, Lu, Abate, Yohannes , He, Lifang , Zhong, Wenxuan, Liu, Wei , Ma, Ping , Zhu, Hongtu , Zhu, Dajiang
Quantitative Biology | September 29, 2025 | Volume: 14 | Issue: 1 | Pages: No page available
Abstract With the rapid advancements in large language model technology and the emergence of bioinformatics‐specific language models (BioLMs), there is a growing need for a comprehensive analysis of the current landscape, computational characteristics, and diverse applications. This survey aims to address this need by providing a thorough review of BioLMs, focusing on their evolution, classification, and distinguishing features, alongside a detailed examination of training methodologies, datasets, and evaluation frameworks. We explore the wide‐ranging applications of BioLMs in critical areas such as disease diagnosis, drug discovery, and vaccine development, highlighting their impact and transformative potential in bioinformatics. We identify key challenges and limitations inherent in BioLMs, including data privacy and security concerns, interpretability issues, biases in training data and model outputs, and domain adaptation complexities. Finally, we highlight emerging trends and future directions, offering valuable insights to guide researchers and clinicians toward advancing BioLMs for increasingly sophisticated biological and clinical applications.
Development of a Core Critical Care Data Dictionary With Common Data Elements to Characterize Critical Illness and Injuries Using a Modified Delphi Method
Anderson, Wesley R., Heavner, Smith H., Al-Hakim, Tamara, Cruz‐Cano, Raul , Engel, Heidi J., Lamb, Keith, MacLaren, Robert , Rincon, Teresa , Sikora, Andrea, Tanner, Donna, Teeter, William , Wong, An-Kwok Ian , Zhang, Xiaohan Tanner , Zimmerman, Jerry J. , Kumar, Vishakha K. , Cobb, J. Perren, Laudański, Krzysztof , Murphy, David J., Anderson, Wesley, Heavner, Smith H., Kamaleswaran, Rishikesan , Badawi, Omar , Grunwell, Jocelyn R. , Herasevich, Vitaly , Khanna, Ashish K. , Sanchez-Pinto, Lazaro Nelson , Sikora, Andrea , Stevens, Robert David , Wynn, James Lawrence , Reuter‐Rice, Karin
Critical Care Medicine | February 21, 2025 | Volume: 53 | Issue: 5 | Pages: e1045-e1054
OBJECTIVES: To develop the first core Critical Care Data Dictionary (C2D2) with common data elements (CDEs) to characterize critical illness and injuries. DESIGN: Group consensus process using modified Delphi approach. SETTING: Electronic surveys and in-person meetings. SUBJECTS: A multidisciplinary workgroup of clinicians and researchers with expertise in the care of the critically ill and injured. INTERVENTIONS: The Delphi process was divided into domain and CDE portions with each composed of two item generation rounds and one item reduction/refinement rounds. Two in-person meetings augmented this process to facilitate review and consideration of the domains and by panel members. The final set of domains and CDEs was then reviewed by the group to meet the competing criteria of utility and feasibility, resulting in the core dataset. MEASUREMENTS AND MAIN RESULTS: The 23-member Delphi panel was provided 1833 candidate variables for potential dataset inclusion. The final dataset includes 226 patient-level CDCs in nine domains, which include anthropometrics and demographics (8), chronic comorbid illnesses (18), advanced directives (1), ICU diagnoses (61), diagnostic tests (42), interventions (27), medications (38), objective assessments (26), and hospital course and outcomes (5). Upon final review, 91% of the panel endorsed the CDCs as meeting criteria for a minimum viable data dictionary. Data elements cross the lifespan of neonate through adult patients. CONCLUSIONS: The resulting C2D2 provides a foundation to facilitate rapid collection, analyses, and dissemination of information necessary for research, quality improvement, and clinical practice to optimize critical care outcomes. Further work is needed to validate the effectiveness of the dataset in a variety of critical care settings.