Ying-Ju Lai

Ying-Ju Lai

Auto-generated profile, based on publicly available information

Ying-Ju Lai

UPMC Hillman Cancer Center, University of Pittsburgh, 5115 Centre Ave, Pittsburgh, PA, 15232, USA; Department of Biostatistics and Health Data Science, University of Pittsburgh, 130 De Soto Street, Pittsburgh, PA, 15261, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2025 in Cancer Research Communications
Verified
Journal Article
Open access
YLYing-Ju Lai
Ying-Ju Lai
LWLi-Ju Wang
Li-Ju Wang
TYTyler M. Yasaka
Tyler M. Yasaka
YSYuna Shin
Yuna Shin
MNMichael Ning
Michael Ning
YCYu-Chiao Chiu
Yu-Chiao Chiu
Understanding drug–gene relationships is essential for advancing targeted cancer therapies and drug repurposing strategies. However, the vast volume of biomedical literature poses significant challenges in efficiently extracting relevant insights. In this study, we developed an automated pipeline that leverages retrieval-augmented large language models (LLM) to infer drug–gene interactions using the most up-to-date biomedical literature. By integrating PubMed and state-of-the-art LLMs, our pipeline generates accurate, evidence-based inferences while addressing the limitations of static LLMs, such as outdated knowledge and the risk of producing misleading results. We systematically validated the pipeline’s performance using curated databases and demonstrated its ability to accurately identify both well-established and emerging drug targets. Using our pipeline, we constructed a pan-cancer drug–gene interaction network among hundreds of FDA-approved drugs and key oncogenes. In a case study on liver cancer, we identified and validated an association between CTNNB1 mutations and enhanced sensitivity to sorafenib, highlighting a potential therapeutic strategy for this challenging mutation. To facilitate broad accessibility, we developed GeneRxGPT, a user-friendly web application that enables cancer researchers to utilize the pipeline without programming expertise or extensive computational resources. It provides intuitive modules for drug–gene inference and network visualization, streamlining the exploration and interpretation of drug–gene relationships. We anticipate that GeneRxGPT will empower researchers to accelerate drug discovery and development, making it a valuable resource for the cancer research community. Significance: This study presents a novel approach that integrates LLMs with real-time biomedical literature to uncover drug–gene relationships, transforming how cancer researchers identify therapeutic targets, repurpose drugs, and interpret complex molecular interactions. GeneRxGPT, our user-friendly tool, enables researchers to leverage this approach without requiring computational expertise.

2 February 2026 in Cancer Letters
Verified
Journal Article
Open access
HCHsiao-Chun Chen
Hsiao-Chun Chen
LWLi-Ju Wang
Li-Ju Wang
CSChien-Hung Shih
Chien-Hung Shih
HYHuikang Ye
Huikang Ye
YLYing-Ju Lai
Ying-Ju Lai
Yu-Chih ChenYu-Chih Chen
Yu-Chih Chen

13 May 2025
Verified
Other
Open access
YLYing-Ju Lai
Ying-Ju Lai
LWLi-Ju Wang
Li-Ju Wang
TYTyler M. Yasaka
Tyler M. Yasaka
YSYuna Shin
Yuna Shin
MNMichael Ning
Michael Ning
YCYu-Chiao Chiu
Yu-Chiao Chiu
The GeneRxGPT web tool. A, Homepage. The homepage provides access to the main drug–gene inference module, as well as a link to the drug–gene network module. Users can easily test the tool using a built-in example. A comprehensive user manual, along with figure and table legends, is available on the help pages or by clicking the question mark icon in individual output sections. B, Input panel of the drug–gene inference module. Users enter a gene (gene symbol or protein name), drug [name, PubChem CID, or Simplified Molecular Input Line Entry System (SMILES) code], and cancer type into the input panel. Users can select the desired LLMs (either GPT-4o or Gemini-1.5 Pro, currently available) and choose whether the inference is based on sentence- or abstract-level retrieval. C, Output panels of the drug–gene inference module. Based on the abstracts or sentences retrieved from relevant publications in PubMed, the selected LLM generates an inference and detailed explanation of the drug–gene relationship in the specified cancer type, along with a summary of the retrieved information. References to retrieved sentences or abstracts are provided with PubMed PMIDs and hyperlinks. Additionally, detailed drug information from PubChem is presented by an informative table and the drug structure. D, Drug–gene interaction network. This module allows users to visualize a drug–target interaction network among 214 oncogenes and 144 FDA-approved drugs, either across all cancers or within a specific cancer type.