Japan Clinical Cancer Research Organization

The paramount challenge in precision oncology lies in further improving quality of life and response rates for individual patients. Efforts toward these goals are steadily expanding the scope of clinical implementation, despite ongoing challenges such as standardization, cost-effectiveness, and data harmonization. Building upon this maturing foundation, generative AI—which has evolved dramatically in recent years—is particularly valuable at this stage of advancing efficiency and adoption as an auxiliary technology linking literature, guidelines, trial protocols, and patient data. Specifically, through mutation interpretation, trial eligibility matching, and tumor board support, it is expected to contribute to advancing standardization, improving cost-effectiveness, accelerating data harmonization, and further accelerating human-centered decision-making. Accordingly, this review surveys the development history of generative AI and its current healthcare applications, organizing its implementation potential for precision oncology along three axes: (1) generative AI–based interpretation of genetic mutations and estimation of their pathological significance; (2) generative AI–driven verification of clinical trial eligibility; and (3) multimodal foundation models for imaging and pathology that compute “tumor phenotypes” using real-world data, contributing to report drafting and molecular surrogate estimation. In response, we propose a strategy centered on retrieval-augmented generation (RAG) and human-in-the-loop (HITL) workflows, encompassing data preparation based on OMOP, mCODE, and FHIR; multicenter prospective evaluation; auditable logs and governance aligned with Good Manufacturing Practice (GMP) and the EU AI Act; and a synthetic data strategy including differential privacy. Ultimately, this approach validates value through real-world outcomes and charts a path toward “learning oncology,” accelerating patient-centered decision-making and clinical trial development.

Abstract We analyzed the differences in bacterial composition between 475 Japanese patients with advanced gastric cancer (median age 70 years, median BMI 20.0) and 106 healthy individuals using a comprehensive metagenome shotgun analysis. Among the patients with advanced gastric cancer, 71% were male, 37.% patients had relapsed, and 55.5% previously underwent gastrectomy. Bifidobacterium , Anaerostipes , and Parabacteroides were predominant in healthy individuals, whereas Streptococcus , Lactobacillus , and Odoribacter were predominant in patients with advanced gastric cancer. Additionally, Kyoto Encyclopedia of Genes and Genomes pathway analysis showed that butanoate and pyruvate metabolism was enriched in healthy individuals, whereas factors such as ABC transporters and ribosomes were enriched in patients with advanced gastric cancer. Clustering analysis broadly classified patients with advanced gastric cancer and healthy individuals into two clusters; however, clustering using pathway data enabled a clearer classification of patients with advanced gastric cancer and healthy individuals than clustering using flora analysis. Moreover, healthy individuals showed higher bacterial flora diversity than patients with advanced gastric cancer. Thus, we successfully identified the molecular characteristics of microbial genera and functional pathways in the gut of patients with advanced gastric cancer. Our results suggest that fecal metagenomic shotgun sequencing analysis can be used to detect gastric cancer.

The Rare Disease Consortium Japan (RDCJ) is a newly formalized cross-sector initiative launched to address the urgent and growing needs of individuals living with rare diseases in Japan, aiming to support a wide range of rare conditions, including—but not limited to—neuromuscular diseases. RDCJ hosted its inaugural symposium on July 18, 2023, at the Shonan Health Innovation Park. This symposium aimed to address the unique challenges of rare diseases through a collaborative approach involving industry, government, academia, patients, and the community. The event brought together these stakeholders to discuss the current state and future directions of rare disease research and treatment in Japan. The event featured a range of speakers and panel discussions on the state of drug development, patient journeys, and the future of patient-centered healthcare services. Highlights included a keynote on antisense oligonucleotide therapeutics and sessions on patient-centered healthcare, human-centered design in healthcare, and innovative approaches to rare disease treatment. This report provides a detailed overview of the symposium, the key takeaways from each session, and the future directions for RDCJ.

TPS11586 Background: Cutaneous angiosarcoma (cAS) is a rare cancer that often occurs in elderly people with common recurrence and metastasis after surgery. Chemotherapy, radiation therapy, and their combination are widely used, but their effectiveness is insufficient. With the increasing number of cAS patients due to the aging population, the development of effective treatment is urgently required. Previously, it has been reported that cancer shrank in 18% (5 out of 27) of patients after 2 months of paclitaxel administration in a clinical trial. Therefore, paclitaxel has become more commonly used for cAS. Other options include anthracycline anticancer drugs and gemcitabine. However, even with these anticancer drugs (and radiation therapy), cAS progresses quickly, and some reports have said that the 5-year survival rate is 9%. This study is planned to develop safer and more effective treatment for cAS. Pembrolizumab is an immune checkpoint inhibitor with PD-1 receptor-ligand interaction and lenvatinib is a multikinase inhibitor that inhibits tumor angiogenesis. The combination is expected to have strong therapeutic efficacy due to the immunomodulatory effects of pembrolizumab and the inhibitory effects of lenvatinib. Methods: This investigator-initiated, prospective, multicenter, non-randomized phase II trial evaluates the efficacy and safety of pembrolizumab plus lenvatinib for patients with unresectable cAS. Eligible patients are aged ≥18 years (≤85 years), histologically diagnosed with cAS, and both untreated and previously treated patients. The primary endpoint of this study is to confirm the response rate of pembrolizumab plus lenvatinib combination therapy for unresectable cAS based on RECST 1.1 at central review. The secondary endpoints are response rate (primary investigator assessment), progression-free survival, overall survival, disease control rate, duration of response, time to response, incidence of adverse events (AEs), incidence of drug-related adverse events (adverse drug reactions, ADRs), and incidence of serious AEs/ADRs. We estimated a threshold response rate of 18% and an expected response rate of 35%. The planned sample size is 38 patients (25 untreated patients and 13 treated) to provide a power of 70% with one-sided alpha of 5%. The planned accrual period is 2 years, and the follow-up period is 2 years; interim analysis will be performed at the enrollment of 20 patients is completed. The trial began in February 2025. Clinical trial information: NCT06673628 .