Abstract 2602: Leveraging cell-free methylome markers for early cancer detection
Bibliographic record
Abstract
Abstract Cancer survival rates are significantly improved when detected at early stages, particularly when the tumor is still localized to the tissue of origin. However, effective screening tools for early cancer detection is currently limited to a subset of cancer types. The early development of human malignancies are difficult to observe as cancers are often detected once it becomes symptomatic, as such many cancer biomarker and evolution studies to date have primarily examined the genomics from solid tumor or liquid biopsies following a diagnosis. Investigating early tumor evolution in the pre-diagnosis context could allow us to better understand how to prevent or detect cancers in the earliest stage when survival rates are significantly higher, however this requires application of new technologies to biologics collected prior to a cancer diagnosis. Here, we leverage blood samples collected from participants in the Canadian Partnership for Tomorrow Project (CPTP), a longitudinal population cohort, prior to the onset of a cancer. Specifically, we utilize hybrid capture approaches to enrich for and characterize early mutations and methylation changes in circulating tumor DNA (ctDNA) of pre-cancer plasma samples collected from patients several months to years prior to clinical diagnosis. Here, we identify the earliest detectability of aberrant genetic and epigenetic events in ctDNA and describe the molecular evolution of these events at various stages prior to clinical detection of cancers. Further, we develop molecular biomarkers and implement machine learning tools to classify individuals with early cancers, and to develop risk scores from survival analyses predictive of cancer development up to 5 years prior to diagnosis. In our current study, we focus specifically on breast, prostate, lung and pancreatic cancer cases, and are extending this to pan-cancer applications in subsequent studies. Citation Format: Nicholas Cheng, Kimberly Skead, David Soave, Jocelyn Meng, Elias Gbeha, Ilinca Lungu, Bernard Lam, Scott Bratman, Daniel De Carvalho, Philip Awadalla. Leveraging cell-free methylome markers for early cancer detection [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 2602.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".