August 3, 2021
Companion Request for Information: Critical resource gaps and opportunities to support radiological tool development and clinical data interpretation using artificial intelligence (AI)/machine learning (ML) (NOT-OD-21-163)
The National Institutes of Health (NIH) and the Food and Drug Administration (FDA) are requesting information from stakeholders on what critical resource gaps exist to support Next Generation Sequencing (NGS) test validation and development (e.g., highly characterized reference materials, infrastructure) and tool development and data interpretation (e.g., AI/ML technologies). This RFI is being released in parallel with a companion RFI (NOT-OD-21-163) focused on reference material gaps for radiology. If desired, respondents may provide comments that encompass both foci where the fields converge (e.g., linking tumor features with sequencing data). The comment period on this notice is 90 days. Response to this notice is voluntary.
In NGS, demonstrating analytical validity and concordance of results obtained with different methodologies or between different testing sites is critical for ensuring reproducible science (1) and generalizability to the clinical setting. Reference materials are essential for methods development and validation (e.g., to assess reproducibility of results). However, it is widely recognized that many existing resources are insufficient; highly characterized, ethnically diverse, broadly available, and sustainable reference materials are still lacking. Moreover, there is no community consensus on the standards that need to be developed and made available to drive the field forward. This “ground truth” gap is frequently identified as a limiting factor that impedes high-quality research, development, validation, and regulatory science.
The NIH and the FDA are interested in receiving input on the greatest needs and opportunities related to the following four topics: development of reference samples, tools, and infrastructure for clinical and translational research using NGS; application of AI/ML to the interpretation of NGS data and multi-domain data; existing resources that could be leveraged to fill resource gaps; and any general comments related to critical resource gaps and opportunities to support NGS test development and validation.
The NIH and FDA are also interested in the opportunities to improve understanding, efficiency, or transparency of the processes associated with these topics. NIH and FDA welcome input from research investigators, study participants, professional organizations, and other interested members of the public. Respondents are free to address any or all of the information listed below or any relevant topic for NIH and FDA to consider. Respondents should not feel compelled to address all items.
Topic 1: Development of reference samples, tools, and infrastructure for clinical and translational research using NGS
The lack of well-characterized and widely available somatic and germline samples makes NGS test and methodology validation across laboratories difficult. To enable efficient standardization and harmonization of NGS, a diverse range (2,3) of appropriately consented and replenishable reference samples, representing diverse ethnicities, and most potential variations of interest must be made available. In addition, there is a lack of adequate infrastructure to host and support these materials and limitations on tools available to do analysis of reference materials in relation to the product of interest. NIH and FDA seek broad input on the following areas:
Topic 2: Application of AI/ML to the interpretation of NGS data and multi-domain data
There are significant gaps in the availability of validated NGS datasets and related resources. If these gaps can be addressed, it could foster the development and validation of the next generation of AI/ML algorithms capable of analyzing NGS data (and ideally data from multiple clinical domains) to provide researchers, clinicians, physicians, and patients with new “big data” insights on the detection, characterization, treatment, and drug resistance of cancers and other diseases. NIH and FDA seek broad input on the following areas:
Topic 3: Existing resources that could be leveraged to fill resource gaps
NIH and FDA are also interested in receiving broad input about existing resources that could be leveraged to fill gaps identified by respondents. When identifying any relevant, existing resources, commenters may wish to include the following information in their responses where applicable:
Topic 4: General Comments
NIH and FDA welcome general information on any other topics with regard to critical resource gaps and opportunities to support NGS test development and validation, including the use of technologies such as AI/ML to support NGS tool development and data interpretation.
1. NIH Rigor and Reproducibility (https://www.nih.gov/research-training/rigor-reproducibility)
2. OncoSpot NGS Reference Standards (https://www.genecopoeia.com/product/reference-standards/oncospot-ngs-reference-standards/)
3. Seraseq NGS Reference Standards (https://www.seracare.com/resources-and-education/seraseq-ngs-reference-materials/)
4. The Cancer Genome Atlas (TCGA) (https://www.cancer.gov/about-nci/organization/ccg/research/structural-genomics/tcga)
5. Clinical Proteomic Tumor Analysis Consortium (CPTAC) (https://proteomics.cancer.gov/programs/cptac)
6. Applied Proteogenomics Organizational Learning and Outcomes (APOLLO) https://proteomics.cancer.gov/programs/apollo-network
7. The Cancer Imaging Archive (TCIA) https://www.cancerimagingarchive.net/
Submitting a Response
Responses should be submitted electronically by November 1, 2021 using the form at https://osp.od.nih.gov/rfi-comment-resource-gaps-for-NGS. You may provide responses to one or all of the topics in the comment boxes. Responses received will be posted at https://osp.od.nih.gov/nih-fda-rfi-ngs-radiomics without change after NIH and FDA have reviewed all of the responses received. Please do not include any proprietary, classified, confidential, or sensitive information in your response.
This Request for Information (RFI) is for planning purposes only and should not be construed as a policy, solicitation for applications, or as an obligation on the part of the Government to provide support for any ideas identified in response to it. NIH and FDA may use information gathered by this RFI to inform development or modification of websites, policies and practices, processes and procedures, and supporting documentation.
NIH Office of Science Policy
Division of Clinical and Healthcare Research Policy