Citations

Clear

10 citation(s) found for "Li, Yiwei".

PTEN-AKT2 Regulates Mixed Lineage Liver Cancer Development and Sensitizes Cancer Cells to TGFβ Treatment
Stiles, Bangyan, Tang, Qi , Slarve, Ielyzaveta, Chen, Jingyu , Zeng, Ni , Gu, Yiwei , He, Lina, Hu, Shunan , Alhousari, Diala, Xu, Zifei, Hua, Brittney , Zhang, G, Alba, Mario , Ji, Baoan , Chopra, Shefali , Kanel, Gary C., Yuan, Liyun, Slarve, Ielyzaveta, Chen, Jingyu, Zeng, Ni , He, Lina, Zhang, Guo , Nguyen, Phillip, Bharadwaj, Ajay, Lee, Jihyeon , Kreimer, Simion D. , Xu, Jian, Lu, Shelly C. , Eyk, Jennifer E. Van , Yuan, Liyun , Stiles, Bangyan L.

Mayo Clinic

No container title available | January 30, 2026 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.21203/rs.3.rs-8697220/v1 | PMID 41646383 Get It

Abstract Primary liver cancers, including hepatocellular carcinoma (HCC) and cholangiocarcinoma (CCA), arise from the neoplastic transformation of hepatocytes and cholangiocytes, respectively. Loss or downregulation of PTEN, a tumor suppressor negatively regulating the PI3K/AKT pathway, is frequently observed in CCA and HCC. Notably, PTEN mutations are observed at nearly twice the frequency in combined CCA-HCC tumors than either HCC or CCA alone. Using lineage-specific liver-targeted PTEN-deficient mouse models, we demonstrate that PTEN loss drives cellular dedifferentiation and tumorigenesis, a process that is critically dependent on AKT2. Mechanistically, PTEN deficiency induces activation of NOTCH and upregulation of transcriptional factor SOX9, which plays a central role in tumor cell transformation. In parallel, PTEN loss increases SMAD4 expression and sensitizes the tumor cells to TGFβ signaling, with TGFβ treatment repressing SOX9 expression in tumor cells lacking PTEN. Together, our study defined a critical role for PTEN-AKT2 signaling in maintaining liver epithelial lineage fidelity and revealed how its disruption promotes the conversion of mature hepatocytes or cholangiocytes into liver cancer stem-like cells (LCSCs). Furthermore, we identify a PTEN-dependent crosstalk between NOTCH and TGFβ pathways that governs liver tumor development. Together, this work provides mechanistic insight into lineage plasticity in liver cancer with implications for pathway-directed therapy.
Differences Between Cystatin C- and Creatinine-Based eGFR and the Risk of Postoperative Complications and Mortality
Pu, Wei-yi, Wang, Yiwei, Larson, Nicholas B., Lieske, John C., Zhou, Leting, Pu, Wei-yi, Wang, Yiwei, Larson, Nicholas B., Lieske, John C., Zhou, Leting

Mayo Clinic

Journal of the American Society of Nephrology | November 10, 2025 | Volume: 36 | Issue: 10S | Pages: No page available

10.1681/asn.2025bqw9xg7e Get It

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

Mayo Clinic

Quantitative Biology | September 29, 2025 | Volume: 14 | Issue: 1 | Pages: No page available

10.1002/qub2.70014 | PMID 41676319 Get It

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.
AcuKG: a comprehensive knowledge graph for medical acupuncture
Li, Yiming , Peng, Xueqing , Peng, Suyuan , Li, Jianfu , Pei, Donghong, Zhang, Qin , Lu, Yiwei , Hu, Yan , Li, Fang , Tao, Cui, Xu, Hua , Hong, Na , Xu, Hua , Li, Fang , Li, Yiming , Pei, Donghong, Zhou, Li , He, Yongqun

Mayo Clinic

Journal of the American Medical Informatics Association | September 27, 2025 | Volume: 33 | Issue: 2 | Pages: 359-370

10.1093/jamia/ocaf179 | PMID 41124298 Get It

Abstract Background Acupuncture, a key modality in traditional Chinese medicine, is gaining global recognition as a complementary therapy and a subject of increasing scientific interest. However, fragmented and unstructured acupuncture knowledge spread across diverse sources poses challenges for semantic retrieval, reasoning, and in-depth analysis. To address this gap, we developed AcuKG, a comprehensive knowledge graph that systematically organizes acupuncture-related knowledge to support sharing, discovery, and artificial intelligence–driven innovation in the field. Methods AcuKG integrates data from multiple sources, including online resources, guidelines, PubMed literature, ClinicalTrials.gov, and multiple ontologies (SNOMED CT, UBERON, and MeSH). We employed entity recognition, relation extraction, and ontology mapping to establish AcuKG, with human-in-the-loop to ensure data quality. Two cases evaluated AcuKG’s usability: (1) how AcuKG advances acupuncture research for obesity and (2) how AcuKG enhances large language model (LLM) application on acupuncture question-answering. Results AcuKG comprises 1839 entities and 11 527 relations, mapped to 1836 standard concepts in 3 ontologies. Two use cases demonstrated AcuKG’s effectiveness and potential in advancing acupuncture research and supporting LLM applications. In the obesity use case, AcuKG identified highly relevant acupoints (eg, ST25, ST36) and uncovered novel research insights based on evidence from clinical trials and literature. When applied to LLMs in answering acupuncture-related questions, integrating AcuKG with GPT-4o and LLaMA 3 significantly improved accuracy (GPT-4o: 46% → 54%, P = .03; LLaMA 3: 17% → 28%, P = .01). Conclusion AcuKG is an open dataset that provides a structured and computational framework for acupuncture applications, bridging traditional practices with acupuncture research and cutting-edge LLM technologies.
Fine‐tuning open‐source large language models to improve their performance on radiation oncology tasks: A feasibility study to investigate their potential clinical applications in radiation oncology
Wang, P. , Liu, Zhengliang , Li, Yiwei , Shu, Peng , Li, Xiang , Laughlin, Brady, Toesca, Diego Santos, Vargas, Carlos , Vora, Sujay A., Patel, Samir H. , Liu, Tianming , Wang, Peilong, Laughlin, Brady S. , Toesca, Diego A.S. , Wang, Peilong, Holmes, Jason , Shu, Peng, Zhang, Lian , Li, Quanzheng , Sio, Terence T. , Liu, Wei , Li, Xiang

Mayo Clinic

Medical Physics | July 16, 2025 | Volume: 52 | Issue: 7 | Pages: No page available

10.1002/mp.17985 | PMID 40665561 Get It

Abstract Background The radiation oncology clinical practice involves many steps relying on the dynamic interplay of abundant text data. Large language models have displayed remarkable capabilities in processing complex text information. But their direct applications in specific fields like radiation oncology remain underexplored. Purpose This study aims to investigate whether fine‐tuning LLMs with domain knowledge can improve the performance on Task (1) treatment regimen generation, Task (2) treatment modality selection (photon, proton, electron, or brachytherapy), and Task (3) ICD‐10 code prediction in radiation oncology. Methods Data for 15 724 patient cases were extracted. Cases where patients had a single diagnostic record, and a clearly identifiable primary treatment plan were selected for preprocessing and manual annotation to have 7903 cases of the patient diagnosis, treatment plan, treatment modality, and ICD‐10 code. Each case was used to construct a pair consisting of patient diagnostics details and an answer (treatment regimen, treatment modality, or ICD‐10 code, respectively) for the supervised fine‐tuning of these three tasks. Open source LLaMA2‐7B and Mistral‐7B models were utilized for the fine‐tuning with the Low‐Rank Approximations method. Accuracy and ROUGE‐1 score were reported for the fine‐tuned models and original models. Clinical evaluation was performed on Task (1) by radiation oncologists, while precision, recall, and F‐1 score were evaluated for Task (2) and (3). One‐sided Wilcoxon signed‐rank tests were used to statistically analyze the results. Results Fine‐tuned LLMs outperformed original LLMs across all tasks with p value ≤ 0.001. Clinical evaluation demonstrated that over 60% of the fine‐tuned LLMs‐generated treatment regimens were clinically acceptable. Precision, recall, and F1‐score showed improved performance of fine‐tuned LLMs. Conclusion Fine‐tuned LLMs demonstrated statistically significant improvements over original LLMs upon three clinically important tasks in radiation oncology. This study explored the feasibility of applying fine‐tuned LLMs in radiation oncology, inspiring further development of utilizing LLMs to assist with radiation oncology tasks.
JAB-3312, a Potent Allosteric SHP2 Inhibitor That Enhances the Efficacy of RTK/RAS/MAPK and PD-1 Blockade Therapies
Kang, Di , Wang, Yanping , Lin, Yiwei , Wee, Wen , Morgensztern, Daniel , Leventakos, Konstantinos , Bi, Chao , Ding, Yuli , Xiong, Jing , Yan, Man , Sun, Xin , Wang, Peng George , Ma, Cunbo , Wang, Yinxiang , Ma, Wen Wee , Wang, Peng , Ding, Yuli

Mayo Clinic

Clinical Cancer Research | May 7, 2025 | Volume: 31 | Issue: 14 | Pages: 3019-3032

10.1158/1078-0432.ccr-24-3691 | PMID 40333694 Get It

Abstract Purpose: Recent advances have seen the development of targeted therapeutics against the receptor tyrosine kinase (RTK)/RAS/MAPK pathway, which, when aberrantly activated, drives the malignant transformation of many cancer indications. However, the efficacy of inhibitors targeting single molecules is dampened by pathway feedback activation and acquired drug resistance. We seek to evaluate the application of JAB-3312 (sitneprotafib), a potent inhibitor of SHP2, in RTK/RAS/MAPK pathway–targeted combination therapies. Furthermore, SHP2 plays a vital role in PD-1–mediated immunosuppression. The rational combination of JAB-3312 with PD-1 blocking therapies is also explored. Experimental Design: Biochemical and cellular assays were applied to evaluate the potency of JAB-3312 in SHP2 inhibition. Tumor cell lines and cell line– and patient-derived xenografts were used to test different combinations of JAB-3312 with KRASG12C, MEK, EGFR, and PD-1 inhibitors. Results: JAB-3312 produced potent in vitro inhibition of SHP2 activity and downstream ERK phosphorylation, with IC50 values of 1.44 nmol/L and 0.68 to 4.84 nmol/L, respectively. When used in combination, JAB-3312 significantly increased the antitumor activity of the KRASG12C inhibitor glecirasib in naïve and resistant models. The combination of JAB-3312 with MEK inhibitors significantly delayed RTK signaling reactivation and enhanced tumor growth inhibition in KRAS-mutated cancer models. The JAB-3312–osimertinib combination exhibited great efficacy in osimertinib-resistant non–small cell lung cancer models. Additionally, JAB-3312 enhanced the efficacy of PD-1 blockade therapies by promoting an antitumor microenvironment. Representative cases of patients who responded to the combination therapies from two ongoing clinical trials (NCT05288205 and NCT04720976) were reported. Conclusions: JAB-3312 in combination with RTK/RAS/MAPK or PD-1 blockade therapies is a promising strategy that warrants further clinical investigation.
Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task
Wu, Zihao , Zhang, Lu , Cao, Chao , Liu, Zhengliang , Zhao, Lin , Li, Yiwei , Dai, Haixing , Ma, Chong , Li, Gang , Liu, Tianming , Wu, Zihao , Zhang, Lu , Yu, Xiaowei , Liu, Wei , Li, Quanzheng , Shen, Dinggang G. , Li, Xiang , Zhu, Dajiang , Liu, Tianming , Zhao, Lin

Mayo Clinic

IEEE Transactions on Big Data | February 13, 2025 | Volume: 11 | Issue: 3 | Pages: 1027-1041

10.1109/tbdata.2025.3536928 Get It

Artificial General Intelligence for Medical Imaging Analysis
Li, Xiang , Zhao, Lin , Zhang, Lu , Wu, Zihao , Liu, Zhengliang , Jiang, Hanqi , Cao, Chao , Xu, Shaochen , Li, Yiwei , Dai, Haixing , Liu, Jun , Liu, Tianming , Yuan, Yixuan , Li, Gang , Zhu, Dajiang , Yan, Pingkun , Li, Quanzheng , Liu, Wei , Shen, Dinggang G. , Li, Xiang , Wu, Zihao , Zhao, Lin , Liu, Jun

Mayo Clinic

IEEE Reviews in Biomedical Engineering | November 7, 2024 | Volume: 18 | Issue: No issue available | Pages: 113-129

10.1109/rbme.2024.3493775 | PMID 39509310 Get It

Decreased Gut Microbiome Tryptophan Metabolism and Serotonergic Signaling in Patients With Persistent Mental Health and Gastrointestinal Symptoms After COVID-19
Blackett, John W. , Sun, Yiwei , Elkind, Mitchell S.V. , O’Byrne, Sheila M., Freedberg, Daniel E. , Purpura, Lawrence J. , Margolis, Kara Gross , Wainberg, Milton L. , Abrams, Julian A , Wang, Harris H. , Chang, Lin

Mayo Clinic

Clinical and Translational Gastroenterology | September 1, 2022 | Volume: 13 | Issue: 10 | Pages: e00524

10.14309/ctg.0000000000000524 | PMID 36049050 Get It

INTRODUCTION: An estimated 15%–29% of patients report new gastrointestinal (GI) symptoms after coronavirus-19 disease (COVID-19) while 4%–31% report new depressive symptoms. These symptoms may be secondary to gut microbiome tryptophan metabolism and 5-hydroxytryptamine (5-HT)-based signaling. METHODS: This study used specimens from 2 patient cohorts: (i) fecal samples from patients with acute COVID-19 who participated in a randomized controlled trial testing prebiotic fiber and (ii) blood samples from patients with acute COVID-19. Six months after recovering from COVID-19, both cohorts answered questions related to GI symptoms and anxiety or depression. Microbiome composition and function, focusing on tryptophan metabolism-associated pathways, and plasma 5-HT were assessed. RESULTS: In the first cohort (n = 13), gut microbiome L-tryptophan biosynthesis during acute COVID-19 was decreased among those who developed more severe GI symptoms (2.0-fold lower log activity comparing those with the most severe GI symptoms vs those with no symptoms, P = 0.06). All tryptophan pathways showed decreased activity among those with more GI symptoms. The same pathways were also decreased in those with the most severe mental health symptoms after COVID-19. In an untargeted analysis, 5 additional metabolic pathways significantly differed based on subsequent development of GI symptoms. In the second cohort (n = 39), plasma 5-HT concentration at the time of COVID-19 was increased 5.1-fold in those with GI symptoms alone compared with those with mental health symptoms alone ( P = 0.02). DISCUSSION: Acute gut microbiome-mediated reduction in 5-HT signaling may contribute to long-term GI and mental health symptoms after COVID-19. Future studies should explore modification of 5-HT signaling to reduce post-COVID symptoms.