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
163P - Chemotherapy versus palliative radiotherapy in advanced inoperable gall bladder cancer
Presenter: Vimal Sekar
Session: Poster Display
Resources:
Abstract
164P - Neoadjuvant immune checkpoints inhibitors plus chemoradiotherapy for patients with locally advanced esophageal squamous cell carcinoma
Presenter: Ming-Wei Kao
Session: Poster Display
Resources:
Abstract
165P - BMI impact on the prognosis of unresectable HCC patients receiving first-line lenvatinib or atezolizumab plus bevacizumab
Presenter: Elisabeth Amadeo
Session: Poster Display
Resources:
Abstract
166P - Preoperative risk factors strongly related to early recurrence after R0 resection of gallbladder cancer
Presenter: SANGHUN LEE
Session: Poster Display
Resources:
Abstract
167P - Peripheral blood neutrophil-to-lymphocyte ratio correlated with serum IL-8 level and predict the outcome of hepatocellular carcinoma patients treated with immune-targeted combination therapy
Presenter: Xuenan Peng
Session: Poster Display
Resources:
Abstract
168P - Real-world clinicopathological characteristics and treatment patterns of esophageal cancer patients in China
Presenter: Zhihao Lu
Session: Poster Display
Resources:
Abstract
169P - Conversion response and prognostic factors in HCC patients with macrovascular invasion treated with atezolizumab plus bevacizumab
Presenter: xiaodong Zhu
Session: Poster Display
Resources:
Abstract
170P - Atezolizumab plus bevacizumab (A+B) versus lenvatinib for BCLC-B stage of patients with hepatocellular carcinoma (HCC): A large real-life worldwide population
Presenter: Francesco Vitiello
Session: Poster Display
Resources:
Abstract
171P - Retrospective study of the correlation between proteinuria and renal function in patients (pts) with unresectable hepatocellular carcinoma (uHCC) treated with atezolizumab plus bevacizumab (Atezo+Bev): ARISE study
Presenter: Kazuomi Ueshima
Session: Poster Display
Resources:
Abstract
172P - Trastuzumab deruxtecan (T-DXd) in Chinese patients (pts) with previously treated HER2-positive locally advanced/metastatic gastric cancer (GC) or gastroesophageal junction adenocarcinoma (GEJA): Primary efficacy and safety from the phase II single-arm DESTINY-Gastric06 (DG06) trial
Presenter: Zhi Peng
Session: Poster Display
Resources:
Abstract