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
193P - Impact of coronavirus disease 2019 on patients with unresectable hepatocellular carcinoma treated with atezolizumab/bevacizumab
Presenter: Hongjae Chon
Session: Poster Display
Resources:
Abstract
194P - Real-world outcomes of cadonilimab (PD-1/CTLA-4 bispecific antibody) plus chemotherapy as first-line treatment in advanced gastric (G) or gastroesophageal junction (GEJ) cancer with PD-L1 CPS≤5
Presenter: Qi Xu
Session: Poster Display
Resources:
Abstract
195P - Ferroptosis signatures in pancreatic ductal adenocarcinomas and their role in patient survival: A translational unsupervised clustering analysis
Presenter: Quoc-Huy Trinh
Session: Poster Display
Resources:
Abstract
196P - Clinical significance of circulating CD8+ and CD4+ T cell proliferation in advanced gastric cancer receiving first-line chemotherapy
Presenter: In-Ho Kim
Session: Poster Display
Resources:
Abstract
197P - Treatment patterns and clinical outcomes of patients with unresectable advanced or metastatic (UAM) gastric/gastroesophageal junction adenocarcinoma (GA/GEJA) in China: A multicenter real-world study
Presenter: Yanqiao Zhang
Session: Poster Display
Resources:
Abstract
198P - Effectiveness of lenvatinib in patients with unresectable hepatocellular carcinoma: A multicenter observational study in Japan
Presenter: Namiki Izumi
Session: Poster Display
Resources:
Abstract
199P - Efficacy of endostar in combination with concurrent chemoradiotherapy in patients with locally advanced squamous cell carcinoma of esophagus: A randomized, open-label, phase II trial
Presenter: Yuexiao Qi
Session: Poster Display
Resources:
Abstract
200P - Prognosis of patients with hepatocellular carcinoma treated with transarterial chemoembolization: Development and validation of the ALFP score
Presenter: Baocuo Gong
Session: Poster Display
Resources:
Abstract
201P - A phase II study of serplulimab (a programmed death-1 inhibitor) with or without HLX04 (a bevacizumab biosimilar) for the treatment of advanced hepatocellular carcinoma
Presenter: Zhenggang Ren
Session: Poster Display
Resources:
Abstract
202P - Comparison of liver injury after transcatheter arterial chemoembolization and hepatic arterial infusion chemotherapy for intermediate and advanced hepatocellular carcinoma
Presenter: Yongru Chen
Session: Poster Display
Resources:
Abstract