Leveraging Enriched Genomic Data to Develop a
Next-Generation Afirma Gene Expression Classifier


Interview with Giulia Kennedy, Ph.D., Chief Scientific Officer, Senior Vice President of Research and Development, Veracyte

Dr. Giulia Kennedy is chief scientific officer at Veracyte where her team led development of the Afirma Gene Expression Classifier (GEC), a genomic test that is becoming a new standard of care in the evaluation of indeterminate thyroid nodules. Dr. Kennedy is now overseeing development of an enhanced Afirma GEC, which is designed to further increase the number of patients who can avoid unnecessary surgery as part of thyroid cancer diagnosis. Here she spoke with us about the enhanced test, which is being previewed at a Product Theater event at ENDO 2017.

Q: What is the enhanced Afirma GEC designed to do?

Dr. Kennedy: The current Afirma GEC has a high sensitivity and reclassifies approximately half of indeterminate thyroid nodules as benign, which enables most of these patients to avoid unnecessary diagnostic surgery. This is a huge improvement for patients compared to diagnostic surgery. But we wanted to use more recently available RNA sequencing technology to further increase the test’s specificity so that we can save even more thyroids and keep patients out of the operating room.

Q: How is the technology behind the enhanced Afirma GEC different from the current test?

Dr. Kennedy: The current test combines RNA-based gene expression, which is measured on a microarray platform, with machine learning algorithms to recognize benign thyroid nodules among those diagnosed indeterminate by cytology. The rates of transcription from expressed genes are the “features” that feed into the algorithm, which predicts the likelihood the nodule is benign.

With the enhanced Afirma GEC, we are using an RNA-sequencing platform, which enables us to measure not only gene expression, but also the presence of gene variants, fusions, copy number variants and other content that may be predictive of thyroid cancer. This gives us much richer genomic information that we then feed into the algorithm to enhance its ability to distinguish benign from malignant nodules. Think of it as going from standard to high-definition television. We have much richer genomic content, which enables enhanced performance.

Q: How is this approach different from other molecular tests for indeterminate thyroid nodules?

Dr. Kennedy: Other tests look at targeted sets of gene mutations or small bits of microRNA. These approaches have limited clinical utility because numerous studies show that gene mutations and microRNA don’t tell the whole story and frequently miss cancers. Our approach to RNA sequencing interrogates the entire genome and uses machine learning to determine which genomic content is clinically significant. This information is then incorporated into the test algorithm. Back to the imaging metaphor, gene mutations and microRNA approaches use only a small set of pixels, whereas RNA sequencing allow us to see the overall picture with greater resolution and clarity. We are not aware of anyone else who is using machine learning and RNA sequencing in a single commercially available test for any oncology indication. This is truly cutting-edge work!

Q: What do the data show about the test’s performance?

Dr. Kennedy: We are presenting cross-validation data at the ENDO 2017 meeting, which suggest that our enhanced Afirma GEC maintains the high sensitivity of the current test and significantly increases the specificity. Our findings predict that the test will enable more people to avoid unnecessary thyroid surgery and that a greater proportion of patients who undergo surgery will prove to have malignant or NIFTP tumors. We plan to unveil clinical validation data for the enhanced test, from an independent test set, at a medical conference in the near future.

Q: Is the enhanced Afirma GEC available yet?

Dr. Kennedy: We plan to begin making the test available to physicians later this year.