Mode
Text Size
Log in / Sign up

Cohort study finds HPV-DeepSeek liquid biopsy diagnostic accuracy of 99% in HPV+ cancers

Cohort study finds HPV-DeepSeek liquid biopsy diagnostic accuracy of 99% in HPV+ cancers
Photo by Ben Maffin / Unsplash
Key Takeaway
Consider blood-based HPV physical state classification as a potential prognostic tool at cancer diagnosis.

This cohort study included 235 HPV+ cancers across nine anatomic sites. Of these, 181 eligible samples were available for HPV-SIGNAL analysis. The investigation utilized HPV-DeepSeek, an HPV whole-genome sequencing liquid biopsy, and HPV-SIGNAL, a blood-based computational classifier. Researchers compared episomal states versus integrated viral states to assess diagnostic accuracy and prognostic potential.

The primary outcome focused on diagnostic accuracy and prognostic potential regarding progression-free survival and overall survival. Diagnostic accuracy of HPV-DeepSeek demonstrated sensitivity and specificity of 99%. Viral physical state distribution in 181 eligible samples included Episomal-only (N=69), Episomal-rearranged (N=48), Integrated-mixed (N=55), and Integrated-clonal (N=9).

Patients with integrated viral states experienced significantly worse progression-free survival compared to episomal states. The hazard ratio was 3.28 with a 95% CI 1.63-6.58 and p = 0.00084. Overall survival was also significantly worse in patients with integrated viral states. The hazard ratio was 2.98 with a 95% CI 1.16-7.64 and p = 0.023.

Safety data including adverse events, serious adverse events, discontinuations, and tolerability were not reported. A key limitation is that existing clinically utilized ctHPVDNA assays cannot classify the viral physical state. Blood-based HPV physical state classification could be used as a prognostic tool at the time of cancer diagnosis.

Study Details

Study typeCohort
Sample sizen = 69
EvidenceLevel 3
PublishedApr 2026
View Original Abstract ↓
Purpose: HPV-associated carcinomas (HPV+ cancers) account for 5% of all cancers. Circulating tumor HPV DNA (ctHPVDNA) assays for HPV+ cancer surveillance have limited prognostic utility at the time of cancer diagnosis. While HPV integration into the host genome is a proven tissue-based biomarker predicting poor clinical outcomes, existing clinically utilized ctHPVDNA assays cannot classify the viral physical state. Methods: We previously developed HPV-DeepSeek, a multi-feature HPV whole-genome sequencing liquid biopsy with 99% diagnostic accuracy at the time of HPV+ oropharynx cancer diagnosis. We test the diagnostic accuracy of HPV-DeepSeek in a cohort of 235 HPV+ cancers across nine anatomic sites and employ a novel blood-based computational classifier to infer HPV genome physical state from plasma, termed HPV-SIGNAL, to assess its prognostic potential. Results: HPV-DeepSeek demonstrated a sensitivity and specificity of 99%. In 181 eligible samples, HPV-SIGNAL identified four viral physical states: episomal-only (N = 69), episomal-rearranged (N = 48), integrated-mixed (N = 55), and integrated-clonal (N = 9), which were confirmed and further elucidated via three orthogonal tissue and blood approaches. Patients harboring integrated viral states in the blood exhibited significantly worse progression-free survival (HR 3.28, 95% CI 1.63-6.58, p = 0.00084) and overall survival (HR 2.98, 95% CI 1.16-7.64, p = 0.023) compared to patients with episomal states. Conclusion: HPV whole-genome sequencing liquid biopsy has high diagnostic accuracy across HPV+ cancer types and can be used to identify and classify HPV physical state from blood. Patients with integrated viral states detected in the blood demonstrated worse progression-free and overall survival, suggesting blood-based HPV physical state classification could be used as a prognostic tool at the time of cancer diagnosis.
Free Newsletter

Clinical research that matters. Delivered to your inbox.

Join thousands of clinicians and researchers. No spam, unsubscribe anytime.