Advancing Childhood and Adolescent & Young Adult (AYA) Cancer Research

Post Date: April 15, 2026

Expiration Date: April 15, 2027

Purpose

The National Institutes of Health (NIH) aims to accelerate progress in preventing, diagnosing, and treating pediatric and AYA patients diagnosed with cancer by supporting innovation and discovery across the full continuum of cancer research and care. This continuum spans molecular characterization, mechanisms of oncogenesis and cancer progression, genetic epidemiology, functional genomics, therapeutic development, preclinical testing, clinical trials, population-based surveillance, and survivorship studies.

research is sought on the use and development of artificial intelligence (AI) and other machine learning (ML) approaches to analyze and integrate existing and new pediatric cancer data, address small sample sizes, and enable privacy-preserving data sharing. It also encourages the creation of tools that make these data AI-ready and accessible, with the goal of accelerating discovery and improving outcomes for children and AYAs with cancer.

Background

Pediatric, adolescent, and young adult (AYA) cancers present unique challenges due to small patient numbers, diverse and often rare disease subtypes, and biologic features that differ from adult cancers. Current standard-of-care therapy for these cancers can result in acute and long-term toxicities (e.g., secondary malignancies, chronic health conditions) that affect survival and quality of life. Lack of robust preclinical models, limited availability of well-annotated biospecimens, and data silos all constrain the pace of translational research. Disparities in access to care, molecular testing, and clinical trials further compound these challenges, particularly for geographically remote populations. More research is needed to better understand the molecular mechanisms driving these cancers and related adverse outcomes and to ultimately inform prevention, early diagnosis, as well as novel targeted approaches for risk assessments to reduce mortality and morbidity. 

As the volume and complexity of pediatric and AYA cancer data continue to grow, there is potential to use advanced computational methods to facilitate pediatric cancer research and optimize care. Examples of these data types include multi-omics data, epidemiologic/risk factor data, imaging, pathology, electronic health records, clinical trial data, real-world evidence, and long-term follow-up and survivorship cohort studies. Computational tools, including artificial intelligence (AI) and machine learning (ML), can rapidly integrate diverse data streams, reveal patterns, and generate testable hypotheses about disease biology, treatment response, toxicity, and late effects.