Stanford Advisors

All Publications

  • From Chatbots to Co-Scientists: The Impact of Knowledge-Generating AI (AI 4.0) on Healthcare and Research. Advanced science (Weinheim, Baden-Wurttemberg, Germany) Liu, W., Peltz, G. 2026: e76484

    Abstract

    While artificial intelligence (AI) has developed as a computational concept for 70 years, its transformative impact on biomedical research and healthcare has explosively accelerated over just the last five years. We are now standing at the precipice of a profound paradigm shift: The emergence of fourth-generation, knowledge-generating AI (AI 4.0). Unlike its predecessors, which primarily synthesized existing information, AI 4.0 possesses advanced reasoning and multi-agentic capabilities that elevate it from a passive tool to an autonomous "co-scientist." By independently formulating novel, testable hypotheses, AI 4.0 promises to catalyze biomedical discoveries, dramatically accelerate the development of new treatments, and redefine patient care. In this perspective, we trace the evolutionary arc of AI through its first three generations to contextualize this historic leap. We then explore the transformative potential of AI 4.0 across drug repurposing, genomic medicine, and scientific peer review. Finally, we highlight a critical emerging bottleneck: The urgent need to overhaul our traditional laboratory infrastructure to keep pace with the sheer volume of AI-generated scientific insight.

    View details for DOI 10.1002/advs.76484

    View details for PubMedID 42411463

    View details for PubMedCentralID PMC13339104

  • Genetic Diagnosis and Discovery Enabled by Large Language Models. Advanced science (Weinheim, Baden-Wurttemberg, Germany) Tu, T., Saab, K., Liu, W., Fang, Z., Cheng, Z., Spasic, S., Djurisic, M., Mohri, H., Ren, W., Palepu, A., Gottweis, J., Karthikesalingam, A., Kulkarni, K., Pawlosky, A., Bonner, D., Kravets, E., Marwaha, S., Mendez, H. R., Wheeler, M. T., Bernstein, J. A., Tsai, C. Y., Wu, C. C., Stankovic, K. M., Natarajan, V., Peltz, G. 2026: e18656

    Abstract

    Artificial intelligence (AI) has been used in many areas of medicine, and large language models (LLMs) have shown potential utility for various clinical applications. However, to determine if LLMs can accelerate the pace of genetic diagnosis and discovery, we examined whether recently developed LLMs (Med-PaLM 2 and Gemini) could assist in solving four types of genetic problems with sequentially increasing complexity. First, in response to free-text input, Med-PaLM 2 correctly identified murine genes with experimentally verified causative genetic factors for six previously studied murine models of biomedical traits. Second, Med-PaLM 2 identified a novel causative murine genetic factor for spontaneous hearing loss that was validated using knock-in mice. Third, we developed a retrieval and grounding pipeline that enabled Gemini 2.5 Pro to analyze large lists of genes, which contained genetic variants that were identified in the genomic sequences of 20 human subjects with hearing loss, and demonstrated that it can assist in identifying causative genetic factors for hearing loss. Fourth, we modified the genetic analysis pipeline to enable Gemini 2.5 Pro without any task-specific fine-tuning to identify causative genetic factors for six subjects with rare genetic diseases, which required 14 to 34 different terms to describe their multi-faceted symptom complexes. These results demonstrate that an AI pipeline can facilitate genetic diagnosis and discovery in mice and humans.

    View details for DOI 10.1002/advs.202518656

    View details for PubMedID 41655254

  • A tandem repeat atlas for the genome of inbred mouse strains: A genetic variation resource. iScience Ren, W., Liu, W., Fang, Z., Dolzhenko, E., Weisburd, B., Cheng, Z., Peltz, G. 2025; 28 (11): 113703

    Abstract

    Tandem repeats (TRs) are a significant source of genetic variation in the human population, and TR alleles are responsible for over 60 human genetic diseases and for inter-individual differences in many biomedical traits. Therefore, we utilized long-read sequencing and state of the art computational programs to produce a database with 2,528,854 TRs covering 39 inbred mouse strains. As in humans, murine TRs are abundant and were primarily located in intergenic regions. However, there were important species differences: murine TRs did not have the extensive number of repeat expansions such as those associated with human repeat expansion diseases, and they were not associated with transposable elements. We demonstrate by analysis of two biomedical phenotypes, which were identified over 40 years ago, that this TR database enhances our ability to characterize the genetic basis for trait differences among inbred strains.

    View details for DOI 10.1016/j.isci.2025.113703

    View details for PubMedID 41142115

    View details for PubMedCentralID PMC12552916