Abstract 410P
Background
Cell-free DNA (cfDNA) fragmentation patterns hold immense potential for early cancer detection. However, the lack of systematic comparison among these patterns has impeded their broader research and practical implementation.
Methods
Here, we collected over 1,382 plasma cfDNA sequencing samples from diverse sources, covering eight cancer types including breast cancer, cholangiocarcinoma, colorectal cancer, gastric cancer, lung cancer, ovarian cancer, pancreatic cancer, and liver cancer. Considering that cfDNA within open chromatin regions is more susceptible to fragmentation, we leveraged ten fragmentation patterns within open chromatin regions as features and employed machine learning techniques to evaluate their performance. The considered fragmentation patterns included Windowed Protection Score, Preferred end coordinates, Coverage, Orientation-aware Cell-free Fragmentation, DNA Evaluation of Fragments for early Interception, Fragment Size Ratio, Fragment Size Distribution, End Motif preferences, Promoter Fragmentation Entropy, and Integrated Fragmentation Score.
Results
All fragmentation patterns demonstrated discernible classification capabilities, and the category of fragmentation patterns incorporating both fragment length and coverage information exhibited robust predictive capacities. The ensemble model integrating all these fragmentation patterns further improved performance in cancer detection and tissue-of-origin analysis. Biologically, crucial features of the model captured critical regulatory regions involved in cancer pathogenesis.
Conclusions
A comprehensive machine-learning-based evaluation of ten major cfDNA fragmentation patterns for early cancer detection was performed. Enhanced performance in cancer diagnosis and tissue-of-origin estimation was achieved, through integration of these fragmentation patterns in an ensemble model with biological interpretability.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
101P - The coexistence of TP53 gain-of-function mutation and hypermethylation as a poor prognostic factor in BRAF wild-type metastatic colorectal cancer
Presenter: Kota Ouchi
Session: Poster Display
Resources:
Abstract
102P - Enhancing colorectal cancer prevention in high-risk populations through faecal immunochemical test surveillance
Presenter: Li Xie
Session: Poster Display
Resources:
Abstract
103P - Anlotinib plus chemotherapy as first-line therapy for gastrointestinal tumor patients with unresectable liver metastasis: Updated results from a multi-cohort, multi-center phase II trial ALTER-G-001-cohort A
Presenter: Junwei Wu
Session: Poster Display
Resources:
Abstract
104P - The value of functional MR-imaging signature model for early prediction of chemotherapy response and its guidance for regimen adjustment to improve efficacy
Presenter: Wenhua Li
Session: Poster Display
Resources:
Abstract
105P - A single-arm, phase II, multicenter study of iparomlimab (QL1604) in patients (pts) with unresectable/metastatic deficient mismatch repair (dMMR)/microsatellite instability high (MSI-H) solid tumors
Presenter: Weijian Guo
Session: Poster Display
Resources:
Abstract
106P - Efficacy and safety of IBI351 (GFH925) monotherapy in metastatic colorectal cancer harboring KRASG12C mutation: Updated results from a pooled analysis of two phase I studies
Presenter: Ying Yuan
Session: Poster Display
Resources:
Abstract
107P - Tumor-stromal ratio in a new age fibroblast activated protein PET imaging as a biomarker for prediction of response to neoadjuvant chemoradiotherapy in carcinoma rectum
Presenter: swetha Suresh
Session: Poster Display
Resources:
Abstract
108P - Detection of HER2 overexpression in colorectal cancer: Comparison of a HANDLE classic NGS panel with standard IHC/FISH
Presenter: Lijuan Luan
Session: Poster Display
Resources:
Abstract
109P - Early onset metastatic colorectal cancer: Clinical-prognostic characteristics and correlation to molecular status
Presenter: Andrea Pretta
Session: Poster Display
Resources:
Abstract
110P - The correlation between multi-dimensional characteristics of circulating tumor cells (CTC) and treatment response in patients with initially unresectable metastatic colorectal cancer
Presenter: Yu Liu
Session: Poster Display
Resources:
Abstract