Ultrasensitive plasma-based monitoring of tumor burden using machine-learning-guided signal enrichment Journal Article
| Authors: | Widman, A. J.; Shah, M.; Frydendahl, A.; Halmos, D.; Khamnei, C. C.; Øgaard, N.; Rajagopalan, S.; Arora, A.; Deshpande, A.; Hooper, W. F.; Quentin, J.; Bass, J.; Zhang, M.; Langanay, T.; Andersen, L.; Steinsnyder, Z.; Liao, W.; Rasmussen, M. H.; Henriksen, T. V.; Jensen, S. Ø; Nors, J.; Therkildsen, C.; Sotelo, J.; Brand, R.; Schiffman, J. S.; Shah, R. H.; Cheng, A. P.; Maher, C.; Spain, L.; Krause, K.; Frederick, D. T.; den Brok, W.; Lohrisch, C.; Shenkier, T.; Simmons, C.; Villa, D.; Mungall, A. J.; Moore, R.; Zaikova, E.; Cerda, V.; Kong, E.; Lai, D.; Malbari, M. S.; Marton, M.; Manaa, D.; Winterkorn, L.; Gelmon, K.; Callahan, M. K.; Boland, G.; Potenski, C.; Wolchok, J. D.; Saxena, A.; Turajlic, S.; Imielinski, M.; Berger, M. F.; Aparicio, S.; Altorki, N. K.; Postow, M. A.; Robine, N.; Andersen, C. L.; Landau, D. A. |
| Article Title: | Ultrasensitive plasma-based monitoring of tumor burden using machine-learning-guided signal enrichment |
| Abstract: | In solid tumor oncology, circulating tumor DNA (ctDNA) is poised to transform care through accurate assessment of minimal residual disease (MRD) and therapeutic response monitoring. To overcome the sparsity of ctDNA fragments in low tumor fraction (TF) settings and increase MRD sensitivity, we previously leveraged genome-wide mutational integration through plasma whole-genome sequencing (WGS). Here we now introduce MRD-EDGE, a machine-learning-guided WGS ctDNA single-nucleotide variant (SNV) and copy-number variant (CNV) detection platform designed to increase signal enrichment. MRD-EDGESNV uses deep learning and a ctDNA-specific feature space to increase SNV signal-to-noise enrichment in WGS by ~300× compared to previous WGS error suppression. MRD-EDGECNV also reduces the degree of aneuploidy needed for ultrasensitive CNV detection through WGS from 1 Gb to 200 Mb, vastly expanding its applicability within solid tumors. We harness the improved performance to identify MRD following surgery in multiple cancer types, track changes in TF in response to neoadjuvant immunotherapy in lung cancer and demonstrate ctDNA shedding in precancerous colorectal adenomas. Finally, the radical signal-to-noise enrichment in MRD-EDGESNV enables plasma-only (non-tumor-informed) disease monitoring in advanced melanoma and lung cancer, yielding clinically informative TF monitoring for patients on immune-checkpoint inhibition. © The Author(s), under exclusive licence to Springer Nature America, Inc. 2024. |
| Keywords: | treatment response; single nucleotide polymorphism; genetics; polymorphism, single nucleotide; solid tumor; neoadjuvant therapy; neoplasm; neoplasms; melanoma; lung neoplasms; lung cancer; pathology; tumor marker; colorectal neoplasms; lung tumor; blood; minimal residual disease; neoplasm, residual; tumor burden; colorectal adenoma; colorectal tumor; aneuploidy; plasma; therapy; dna copy number variations; disease surveillance; copy number variation; machine learning; humans; human; article; whole genome sequencing; circulating tumor dna; deep learning; biomarkers, tumor; chloroplast dna |
| Journal Title: | Nature Medicine |
| Volume: | 30 |
| Issue: | 6 |
| ISSN: | 1078-8956 |
| Publisher: | Nature Publishing Group |
| Date Published: | 2024-06-01 |
| Start Page: | 1655 |
| End Page: | 1666 |
| Language: | English |
| DOI: | 10.1038/s41591-024-03040-4 |
| PUBMED: | 38877116 |
| PROVIDER: | scopus |
| PMCID: | PMC7616143 |
| DOI/URL: | |
| Notes: | Article -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
Related MSK Work