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
592P - Treatment patterns and outcomes in patients with advanced non-small cell lung cancer with MET exon 14 skipping alterations in China
Presenter: Hanxiao Chen
Session: Poster Display
Resources:
Abstract
593P - MET TKIs in Asian patients (pts) with MET exon 14 skipping NSCLC: A matching-adjusted indirect comparison (MAIC)
Presenter: E-e Ke
Session: Poster Display
Resources:
Abstract
594P - The treatment pattern and clinical outcome in NSCLC patients with MET alteration: A retrospective real-world analysis in China
Presenter: Yongfeng Yu
Session: Poster Display
Resources:
Abstract
595P - Durable efficacy of zenocutuzumab, a HER2 x HER3 bispecific antibody, in advanced NRG1 fusion-positive (NRG1+) non-small cell lung cancer (NSCLC)
Presenter: Koichi Goto
Session: Poster Display
Resources:
Abstract
596P - Repotrectinib in patients (pts) from Asia and China with ROS1 fusion-positive (ROS1+) non-small cell lung cancer (NSCLC): Results from the phase I/II TRIDENT-1 trial
Presenter: Ross Soo
Session: Poster Display
Resources:
Abstract
597TiP - A phase I/II study to evaluate the safety and anti-tumor activity of JIN-A02 in patients with EGFR TKI-refractory, EGFR-mutant advanced NSCLC
Presenter: Sun Min Lim
Session: Poster Display
Resources:
Abstract
598TiP - Exploration of aumolertinib in first-line treatment for advanced non-small cell lung cancer patients of performance status 3 with EGFR mutations (19del and L858R)
Presenter: Haiyi Deng
Session: Poster Display
Resources:
Abstract
599TiP - A prospective study of savolitinib plus docetaxel in pretreated EGFR/ALK/ROS1/METex14m-wildtype advanced NSCLC patients with MET overexpression (FirstMET)
Presenter: Shuting Zhan
Session: Poster Display
Resources:
Abstract
600TiP - Phase III study of telisotuzumab vedotin (Teliso-V) vs docetaxel in pretreated c-Met overexpressing EGFR wildtype (WT) non-squamous (NSQ) locally advanced/metastatic non-small cell lung cancer (a/mNSCLC)
Presenter: Junko Tanizaki
Session: Poster Display
Resources:
Abstract
601P - Pembrolizumab in patients of Chinese descent with microsatellite instability-high/mismatch repair deficient advanced solid tumors: KEYNOTE-158
Presenter: Xiaohua Wu
Session: Poster Display
Resources:
Abstract